{"paper_id":"2d6ccde6-3e7c-4bfc-9a3d-48a2fd5d603e","body_text":"Optimizing Neonatal MRI Efficiency: Deep Learning-Assisted Feed and Wrap Technique Versus General Anaesthesia Using a Neonatal Brain MRI Stabilizer in Infants Under 4 Months | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Optimizing Neonatal MRI Efficiency: Deep Learning-Assisted Feed and Wrap Technique Versus General Anaesthesia Using a Neonatal Brain MRI Stabilizer in Infants Under 4 Months Ahmed Aldraihem, Moayad Almaimani, Mohamed Bayoumi, Abdulhamid Abunadi, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6786816/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 06 Nov, 2025 Read the published version in Pediatric Radiology → Version 1 posted 9 You are reading this latest preprint version Abstract Introduction: Magnetic Resonance Imaging (MRI) in neonates presents unique challenges due to patient motion and the need for sedation. While general anaesthesia (GA) offers motion suppression, it increases procedural risk and resource demands. The Feed and Wrap (FW) technique, enhanced with deep learning (DL)-based image reconstruction, presents a potential alternative by reducing scan time and eliminating sedation requirements. Methods: This retrospective cohort study included 49 neonates under four months who underwent routine brain MRI at a tertiary care centre. Two groups were compared: one scanned using a DL-assisted Feed and Wrap (DL-FW) technique, and the other under GA. Standardized MRI protocols were applied across both groups, with GE AIR™ Recon DL used to accelerate scans in the DL-FW group. Turnover time (defined as the interval from the last DICOM sequence of one exam to the localizer of the next) was the primary metric. Statistical analyses included the Shapiro-Wilk test for normality and the Mann-Whitney U test for group comparisons. Results: Among 49 infants, 27 underwent MRI under GA and 22 with DL-FW. The DL-FW group demonstrated a shorter mean turnover time (26.77 ± 11.33 minutes) compared to the GA group (32.6 ± 9.6 minutes), though variability was higher in the DL-FW group. The application of DL-based reconstruction reduced individual scan durations by approximately 30%, saving around 7.5 minutes per scan. When extrapolated, this translates to over 62 hours of annual scanner time saved, supporting improved throughput and resource utilization. Conclusion: The DL-FW technique significantly enhances MRI workflow efficiency in neonates while avoiding the risks associated with anaesthesia. Despite some variability, DL-FW offers a viable, safer, and cost-effective alternative to GA, aligning with patient-centered, sedation-free imaging practices in neonatal care. Neonatal MRI Deep Learning Feed and Wrap General Anaesthesia Image Acceleration Paediatric Imaging MRI Efficiency Sedation-Free Imaging AIR Recon DL Workflow Optimization Introduction Magnetic resonance imaging (MRI) is essential in pediatric imaging due to its superior soft-tissue contrast and non-invasive nature. However, prolonged scan times pose a significant challenge, particularly in neonates prone to motion artifacts and often requiring sedation for immobility (Antonov et al., 2017; Smith et al., 2020). Traditional motion reduction strategies, such as general anesthesia (GA), ensure compliance but prolong procedural time and carry risks like respiratory complications (Antonov et al., 2017). The feed and wrap technique—using natural sleep post-feeding combined with swaddling and a neonatal MRI stabilizer—offers a non-invasive alternative but still faces challenges with unpredictable infant movement (PMC Study Group, 2024). Recent advancements in neonatal MRI technology, including the use of deep learning (DL), have revolutionized MRI by enabling high-quality image reconstruction from undersampled k-space data, dramatically reducing scan times while preserving diagnostic accuracy (Lin et al., 2021; Tamir et al., 2020). DL leverages convolutional neural networks (CNNs) trained on vast datasets to predict missing information in accelerated scans. For example, GE Healthcare’s AIR™ Recon DL employs a CNN trained on over 2 million MRI slices to remove noise, correct artifacts, and reconstruct images up to 50% faster than conventional methods (GE Healthcare, 2022). In neonatal imaging, this technology complements the feed and wrap technique by minimizing the time infants must remain motionless, thereby reducing reliance on GA (Lee et al., 2021). This study quantifies efficiency gains by comparing turnover times between DL-augmented feed and wrap and GA cohorts using a neonatal MRI stabilizer while exploring DL’s role in optimizing neonatal workflows and minimizing risks. Methods This is a retrospective, cohort study in NICU infants under 4 months who underwent routine brain MRI. It involves acquiring MRI examinations at a 1.5 T scanner (GE Signa Voyager) using the Deep Learning-Assisted Feed and Wrap (DL-FW) technique versus a 1.5 T scanner (GE Optima MR 450w) in a patient under General Anesthesia (GA) with Neonatal MRI Stabilizer. Patient data was extracted from the MRI archive, which includes the start and end time of the exam as well as calculated turnover time in NICU infants who underwent routine brain MRI between December 2024 and March 2025. The study was approved by the Institutional Review Board (IRB), and informed consent was obtained before the scan. Inclusion and exclusion criteria The inclusion criteria for this study consisted of infants aged 0–4 months who underwent routine brain MRI. These patients were scanned using either the Feed and Wrap (FW) technique with a Neonatal MRI Stabilizer or under General Anesthesia (GA) with a Neonatal MRI Stabilizer. The exclusion criteria were infants with incomplete medical records or missing MRI sequences, as well as those older than 4 months, for whom routine brain MRI examination was not indicated. Additionally, patients with congenital anomalies or neurological conditions that significantly impair the ability to remain still were excluded. Infants who required both GA and FW within the same session were also excluded, following the guidelines set by Moltoni et al. (2024). Patients were retrospectively categorized into two groups based on procedural documentation. Technique In the Deep Learning-Assisted Feed and Wrap (DL-FW) group, infants were fed before scanning to promote natural sleep. Swaddling was performed using a standardized neonatal MRI stabilizer, and motion correction software utilizing a deep learning-based algorithm was applied post-acquisition to optimize image quality. This technique notably shortened the duration of T2-weighted and diffusion sequences. Importantly, MRI was performed without the use of sedation or anesthesia. In contrast, the General Anesthesia (GA) group received anesthesia according to institutional protocols, which included intravenous Propofol or oral chloral hydrate. An anesthesiologist continuously monitored the infants during the procedure and at its conclusion. The same neonatal MRI stabilizer was used for positioning in both groups. All neonates in the study underwent a departmental NICU brain MRI protocol, which was performed on a 1.5T scanner equipped with a dedicated neonatal head coil. The MRI protocol included standardized sequences to ensure comprehensive imaging, consisting of sagittal T1 CUBE, sagittal T2 CUBE, axial Diffusion-Weighted Echo (DWE), coronal DWE, axial T1 FLAIR Spin-Echo (SE), coronal T2 Fat-Suppressed (FS), and axial SWAN sequences. These sequences were carefully selected to provide detailed anatomical and functional imaging of the neonatal brain. Imaging duration is defined as the interval between the DICOM timestamp of the start time of the localizer sequence and the final sequence for the same patient. The duration was approximately 30–40 minutes without DL-FW, whereas with DL-FW, it was reduced to 15–20 minutes per session. Turnover time is defined as the interval between the DICOM timestamp of the final sequence from the previous patient’s exam and the start time of the localizer sequence for the next patient. This standardized measurement ensures consistent capture of the time required for patient disposition, room preparation, and setup for the subsequent exam. DL Workflow where GE AIR™ Recon DL software utilized a CNN to reconstruct undersampled k-space data (GE Healthcare, 2022). Motion Free Brain technology corrected minor motion artifacts post-acquisition (GE Healthcare, 2023). Statistical Analysis: Descriptive and inferential statistics were performed using Python and SPSS (Version 29.0, IBM Corp.). Turnover time (in minutes) was compared between two independent groups: infants scanned using the DL-FW technique and those scanned under GA. To assess the distribution of turnover times, the Shapiro-Wilk test was performed for both groups. The results indicated that turnover times for the DL-FW group were not normally distributed (W = 0.797, p = 0.00045), whereas those for the GA group were normally distributed (W = 0.940, p = 0.119). Given the non-normal distribution of the DL-FW group, the non-parametric Mann-Whitney U test was used to compare turnover times between the two groups. The Mann-Whitney U test revealed a statistically significant difference in turnover times between the DL-FW and GA groups (U = 159.0, p = 0.0056), indicating that the DL-FW technique significantly reduced turnover times compared to the GA approach. Results The mean turnover time for the DL-FW group was 26.77 ± 11.33 minutes (range: 14–52 minutes), while the mean turnover time for the GA group was 34.74 ± 11.28 minutes (range: 19–59 minutes). The median turnover time was 23 minutes for DL-FW and 31 minutes for GA, indicating a notable difference favoring the DL-FW technique (Table 1 ). Table 1 Descriptive statistics for turnover times in both the DL-FW and GA groups Group N Mean (min) SD (min) Median (min) IQR (min) Min (min) Max (min) DL-FW 22 26.77 11.33 23 20.5–27 14 52 GA 27 34.74 11.28 31 28–42.5 19 59 The interquartile range (IQR) for the DL-FW group was 20.5–27 minutes , while for the GA group , it was 28–42.5 minutes , highlighting that the GA turnover times tended to be longer and more consistent, whereas the DL-FW technique exhibited slightly more variability (Table 1 ). Interpretation: The DL-FW technique demonstrated significantly shorter turnover times compared to GA, reflecting improved procedural efficiency. The observed difference is statistically significant, as indicated by the Mann-Whitney U test (p = 0.0056). This suggests that the DL-FW technique effectively reduces turnover time, enhancing workflow and patient throughput in the neonatal MRI setting. Despite some variability in the DL-FW group, the overall reduction in turnover time aligns with previous findings that emphasize the efficiency of non-sedative imaging techniques combined with deep learning reconstruction. The integration of GE AIR™ Recon DL technology played a critical role in scan acceleration, further contributing to reduced turnaround times and optimized operational efficiency. These findings support the adoption of the DL-FW technique in neonatal imaging, particularly in resource-constrained settings where sedation carries additional risks and logistical demands. This approach not only minimizes sedation-related complications but also facilitates higher scanner utilization, aligning with patient-centered, sedation-free imaging protocols in pediatric radiology. Discussion Procedural Efficiency and Throughput with DL-FW versus GA Adopting a deep learning–assisted feed-and-wrap (DL-FW) approach in neonatal MRI offers marked gains in procedural efficiency compared to traditional general anesthesia (GA). One major advantage is the reduction in total examination and turnover time. Sedation and anesthesia introduce extra steps – induction, physiological stabilization, and post-scan recovery – which significantly extend a neonate’s stay in the MRI suite [ 44 ]. In one hospital workflow analysis, unsedated pediatric MRI patients spent approximately 2.3 hours in the department on average, versus 3.6 hours with sedation and over 4 hours with GA [ 44 ]. This aligns with earlier findings that an anesthetized MRI can require nearly double the total procedure time of a natural sleep scan [ 44 ]. By eliminating induction and recovery, the feed-and-wrap method inherently shortens visit duration and simplifies patient flow. Our findings are consistent with large cohort studies demonstrating that 90–95% of neonatal MRIs can be completed using feed-and-wrap techniques [ 51 ]. For example, Lollert et al. reported a 95% success rate with feed-and-wrap in neonates, with only a slight increase in motion artifact and a minor reduction in average image-quality scores compared to deep sedation [ 12 ]. Importantly, the instances of nondiagnostic scans with feed-and-wrap are low (roughly 5–15% in experienced centers) and are strongly associated with older infant age [ 12 ]. Infants under approximately 10 weeks old are ideal candidates, with one study finding the odds of feed-and-wrap failure to be 16-fold higher beyond 10 weeks of age [ 45 ]. Incorporating deep learning (DL) acceleration further augments this efficiency. Advanced DL-based image reconstruction tools (such as GE Healthcare’s AIR Recon DL) significantly reduce scan times per sequence while maintaining or improving image quality. In pediatric MRI applications, DL reconstructions have enabled 20–40% reductions in sequence acquisition times without loss of diagnostic information [ 46 ]. For instance, Yoo et al. achieved approximately 29–41% faster 3D T1-weighted brain acquisitions in children using an AI-based reconstruction algorithm [ 46 ]. Economic Implications and Cost Analyses The shift from GA to a DL-assisted feed-and-wrap paradigm has significant economic implications. Anesthetized pediatric MRIs are resource-intensive, requiring specialized staff, monitoring equipment, and extended peri-procedural care. A time-driven costing study found that an outpatient pediatric brain MRI under sedation had a mean total cost of approximately $ 842, compared to $ 262 for the same MRI performed without sedation [ 47 ]. Labor was the largest cost component, and the sedation workflow’s extra time and personnel accounted for most of the $ 580 per-case cost differential [ 47 ]. When extrapolated to an annual departmental scale, the potential cost savings are significant. By eliminating anesthesia in 500 neonatal MRI cases, hospitals can save approximately $ 290,000. Larger centers performing 600–900 exams annually could save between $ 325,000 and $ 543,000 per year [ 47 ]. This estimate aligns with analyses from Brix et al., who reported that integrating DL reconstruction to boost MRI productivity allowed their hospital to forgo the purchase of an additional MRI scanner, saving approximately $ 436,000 annually [ 49 ]. Beyond direct cost considerations, there are broader economic benefits to the DL-FW model. Increased throughput allows for more billable exams, improving revenue capture. Avoiding anesthesia also reduces downstream costs, such as managing anesthesia-related complications or extended hospital stays [ 48 ]. Safety, Validity, and Workflow Integration Transitioning to a DL-assisted, sedation-free imaging workflow requires careful implementation to ensure clinical safety. Avoiding anesthesia circumvents the risks associated with airway manipulation and anesthetic drugs in infants, such as respiratory depression and potential neurotoxicity [ 50 , 51 ]. Sedation-free imaging is inherently safer, and our results showed no procedure-related complications with DL-FW, consistent with other reports [ 12 , 45 ]. Proper scan scheduling is crucial for the success of feed-and-wrap protocols, ideally aligning MRI appointments with feeding and sleep times. Parental involvement and preparation enhance the likelihood of successful unsedated imaging [ 55 ]. Additionally, staff training on using DL-based reconstruction tools is essential to maintain diagnostic consistency. Radiologists should be oriented to the image appearance changes brought about by DL-enhanced reconstructions, which often reduce noise and improve contrast [ 56]. Implementing DL-based protocols requires multidisciplinary coordination, including neonatal care teams and MRI technologists. By creating standardized sedation-free pathways and ensuring efficient workflow integration, radiology departments can enhance patient throughput while maintaining high diagnostic standards. Conclusion DL-FW significantly reduces infant MRI turnover time compared to GA, with a 6.5-minute median reduction and moderate effect size. This supports DL-FW as a promising alternative to GA in neonatal imaging, balancing efficiency and safety. Declarations Ethics approval and consent to participate: The application for ethical approval was done by the institutional review board office. Consent for publication: Not applicable. Competing interest: The authors declare that they have no conflict of interest. Funding: This research received no specific grant from any funding agency. Author Contribution Dr. Aldraihem acted as the person who conducted this study. Dr. Bayoumi and Dr. Almaimani were involved in the literature review, methodology, and started writing this manuscript, and followed the patient data. Mr.Abunadi, Mr. Alswaileh, Mr. Alannaz, Mrs Raneem and MRs. Noorah were involved in the literature search, conception, study design, and acquisition, as well as in developing the research idea, as well as reviewing the manuscript. Dr. Aljabr was involved in writing the introduction and discussion sections. Availability of supporting data: The data used during the current study are not publicly available due to patient privacy, but are available from the corresponding author upon reasonable request. References Allison J, Yanasak N, What MRI (2015) Sequences Produce the Highest Specific Absorption Rate (SAR), and Is There Something We Should Be Doing to Reduce the SAR During Standard Examinations? AJR Am J Roentgenol 205(2):W140. 10.2214/AJR.14.14173 Antonov NK, Ruzal-Shapiro CB, Morel KD et al (2017) Feed and Wrap MRI Technique in Infants. Clin Pediatr (Phila) 56(12):1095–1103. 10.1177/0009922816677806 Clifford B, Conklin J, Huang SY et al (2022) An artificial intelligence-accelerated 2-minute multi-shot echo planar imaging protocol for comprehensive high-quality clinical brain imaging. Magn Reson Med 87(5):2453–2463. 10.1002/mrm.29117 GE Healthcare (2025) MR image reconstruction with AIR™ Recon DL [Internet]. Available from: https://www.gehealthcare.com/products/magnetic-resonance-imaging/air-recon-dl . Accessed May 24 GE Healthcare launches new AI-enabled MRI system at RSNA23 [Internet]. Imaging Technology News (2023) [cited 2025 May 18]. Available from: https://www.itnonline.com/content/ge-healthcare-launches-new-ai-enabled-mri-system-rsna23 GE Healthcare (2025) Life-speed imaging with Sonic DL™: deep learning MRI acceleration [Internet]. Available from: https://www.gehealthcare.com/products/magnetic-resonance-imaging/sonic-dl-deep-learning-mri-acceleration . Accessed May 24 Hammernik K, Schlemper J, Qin C, Duan J, Summers RM, Rueckert D (2021) Systematic evaluation of iterative deep neural networks for fast parallel MRI reconstruction with sensitivity-weighted coil combination. Magn Reson Med 86(4):1859–1872. 10.1002/mrm.28827 Kashiwagi N, Tanaka H, Yamashita Y et al (2021) Applicability of deep learning-based reconstruction trained by brain and knee 3T MRI to lumbar 1.5T MRI. Acta Radiol Open 10(6):20584601211023939. 10.1177/20584601211023939 Lin DJ, Johnson PM, Knoll F, Lui YW (2021) Artificial Intelligence for MR Image Reconstruction: An Overview for Clinicians. J Magn Reson Imaging 53(4):1015–1028. 10.1002/jmri.27078 Montalt-Tordera J, Muthurangu V, Hauptmann A, Steeden JA (2021) Machine learning in Magnetic Resonance Imaging: Image reconstruction. Phys Med 83:79–87. 10.1016/j.ejmp.2021.02.020 Yang A, Finkelstein M, Koo C, Doshi AH (2024) Impact of Deep Learning Image Reconstruction Methods on MRI Throughput. Radiol Artif Intell 6(3):e230181. 10.1148/ryai.230181 Lollert A, Frey KS, Hoffmann C et al (2024) Feed-and-wrap technique versus deep sedation for neonatal magnetic resonance imaging: a retrospective comparative study. Eur Radiol 34(11):7104–7114. 10.1007/s00330-024-10777-6 Moltoni G, Lucignani G, Sgrò S et al (2024) MRI scan with the feed and wrap technique and with an optimized anesthesia protocol: a retrospective analysis of a single-center experience. Front Pediatr 12:1415603. 10.3389/fped.2024.1415603 Kim E, Cho HH, Cho SH et al (2022) Accelerated Synthetic MRI with Deep Learning-Based Reconstruction for Pediatric Neuroimaging. AJNR Am J Neuroradiol 43(11):1653–1659. 10.3174/ajnr.A7664 Dong SZ, Zhu M, Bulas D (2019) Techniques for minimizing sedation in pediatric MRI. J Magn Reson Imaging 50(4):1047–1054. 10.1002/jmri.26703 Barth M, Breuer F, Koopmans PJ, Norris DG, Poser BA (2016) Simultaneous multislice (SMS) imaging techniques. Magn Reson Med 75(1):63–81. 10.1002/mrm.25897 Yoo YM, Park JE, Park MS, Lee JH (2021) Implementation of the feed and swaddle technique as a non-pharmacological strategy to conduct brain magnetic resonance imaging in very low birth weight infants. Neonatal Med 28(3):108–115. 10.5385/nm.2021.28.3.108 Tian Q, Li Z, Fan Q et al (2022) SDnDTI: Self-supervised deep learning-based denoising for diffusion tensor MRI. NeuroImage 253:119033. 10.1016/j.neuroimage.2022.119033 Teixeira AG, Malik RP, Hajnal SJ (2019) Fast quantitative MRI using controlled saturation magnetization transfer. Magn Reson Med 81(2):907–920. 10.1002/mrm.27442 Gulani V, Calamante F, Shellock FG, Kanal E, Reeder SB (2017) Gadolinium deposition in the brain: summary of evidence and recommendations. Lancet Neurol 16(7):564–570. 10.1016/S1474-4422(17)30158-8 Edwards AD, Arthurs OJ (2011) Paediatric MRI under sedation: is it necessary? What is the evidence for the alternatives? Pediatr Radiol 41(11):1353–1364. 10.1007/s00247-011-2147-7 Kim SH, Choi YH, Lee JS et al (2023) Deep learning reconstruction in pediatric brain MRI: comparison of image quality with conventional T2-weighted MRI. Neuroradiology 65(1):207–214. 10.1007/s00234-022-03053-1 Gilmore JH, Knickmeyer RC, Gao W (2018) Imaging structural and functional brain development in early childhood. Nat Rev Neurosci 19(3):123–137. 10.1038/nrn.2018.1 Rothman S, Gonen A, Vodonos A, Novack V, Shelef I (2016) Does preparation of children before MRI reduce the need for anesthesia? Prospective randomized control trial. Pediatr Radiol 46(11):1599–1605. 10.1007/s00247-016-3651-6 Badke D’Andrea C, Kenley JK, Montez DF et al (2022) Real-time motion monitoring improves functional MRI data quality in infants. Dev Cogn Neurosci 55:101116. 10.1016/j.dcn.2022.101116 Chen C, Qin C, Qiu H et al (2020) Deep Learning for Cardiac Image Segmentation: A Review. Front Cardiovasc Med . ;7:25. Published 2020 Mar 5. 10.3389/fcvm.2020.00025 Ebinesh A, Saxena S (2024) Principles of a controlled imaging environment for neonatal brain MRI: Strategies for optimal image quality and safety. Neuroradiol J Published online November 22. 10.1177/19714009241303149 Dong SZ, Zhu M, Bulas D (2019) Techniques for minimizing sedation in pediatric MRI. J Magn Reson Imaging 50(4):1047–1054. 10.1002/jmri.26703 Hughes EJ, Winchman T, Padormo F et al (2017) A dedicated neonatal brain imaging system. Magn Reson Med 78(2):794–804. 10.1002/mrm.26462 Richter L, Fetit AE (2022) Accurate segmentation of neonatal brain MRI with deep learning. Front Neuroinform 16:1006532. 10.3389/fninf.2022.1006532 Oishi K, Faria AV, Mori S (2012) Advanced neonatal NeuroMRI. Magn Reson Imaging Clin N Am 20(1):81–91. 10.1016/j.mric.2011.08.009 Artunduaga M, Liu CA, Morin CE et al (2021) Safety challenges related to the use of sedation and general anesthesia in pediatric patients undergoing magnetic resonance imaging examinations. Pediatr Radiol 51(5):724–735. 10.1007/s00247-021-05044-5 Kuperman JM, Brown TT, Ahmadi ME et al (2011) Prospective motion correction improves diagnostic utility of pediatric MRI scans. Pediatr Radiol 41(12):1578–1582. 10.1007/s00247-011-2205-1 Meshaka R, Gaunt T, Shelmerdine SC (2023) Artificial intelligence applied to fetal MRI: A scoping review of current research. Br J Radiol 96(1147):20211205. 10.1259/bjr.20211205 Uramatsu M, Takahashi H, Barach P, Fujisawa Y, Takahashi M, Mishima S, Yamanaka G (2024) Improving pediatric magnetic resonance imaging safety by enhanced non-technical skills and team collaboration. Brain Dev 46(6):395–403. 10.1016/j.braindev.2024.104311 Zhang T, Pauly JM, Levesque IR (2015) Accelerating parameter mapping with a locally low rank constraint. Magn Reson Med 73(2):655–661. 10.1002/mrm.25161 Kebiri H, Gholipour A, Vasung L, Krsnik Ž, Karimi D, Cuadra MB (2023) Deep learning microstructure estimation of developing brains from diffusion MRI: a newborn and fetal study. Preprint bioRxiv. 2023.07.01.547351. Published 2023 Jul 2 10.1101/2023.07.01.547351 Harrington SG, Jaimes C, Weagle KM, Greer ML, Gee MS (2021) Strategies to perform magnetic resonance imaging in infants and young children without sedation. Pediatr Radiol 51(3):374–381. 10.1007/s00247-021-04960-8 Heckel R, Jacob M, Chaudhari A, Perlman O, Shimron E (2024) Deep learning for accelerated and robust MRI reconstruction. MAGMA 37(3):335–368. 10.1007/s10334-024-01173-8 Montalt-Tordera J, Muthurangu V, Hauptmann A, Steeden JA (2021) Machine learning in Magnetic Resonance Imaging: Image reconstruction. Phys Med 83:79–87. 10.1016/j.ejmp.2021.02.020 Yang A, Finkelstein M, Koo C, Doshi AH (2024) Impact of Deep Learning Image Reconstruction Methods on MRI Throughput. Radiol Artif Intell 6(3):e230181. 10.1148/ryai.230181 Williams M (2024) Innovations in pediatric sedation: improving procedural comfort and safety. J Clin Anesthesiol 8:264. 10.37421/2684-6004.2024.8.264 Arvinte M, Vishwanath S, Tewfik AH, Tamir JI, Deep J-S (2021) Accelerated MRI Reconstruction via Unrolled Alternating Optimization. In: de Bruijne M, Cattin P, Cotin S et al (eds) Medical Image Computing and Computer-Assisted Intervention – MICCAI 2021. Lecture Notes in Computer Science, vol 12906. Springer, pp 350–360. doi: 10.1007/978-3-030-87231-1_34 . Vanderby SA, Babyn PS, Carter MW, Jewell SM, McKeever PD (2010) Effect of anesthesia and sedation on pediatric MR imaging patient flow. Radiology 256(1):229–237. 10.1148/radiol.10091124 Weng W, Reid A, Thompson A, Kuthubutheen J (2020) Evaluating the success of a newly introduced Feed and Wrap protocol in magnetic resonance imaging scanning of the temporal bone for the evaluation of congenital sensorineural hearing loss. Int J Pediatr Otorhinolaryngol 132:109910. 10.1016/j.ijporl.2020.109910 Yoo H, Moon HE, Kim S et al (2025) Evaluation of Image Quality and Scan Time Efficiency in Accelerated 3D T1-Weighted Pediatric Brain MRI Using Deep Learning-Based Reconstruction. Korean J Radiol 26(2):180–192. 10.3348/kjr.2024.0701 Hayatghaibi SE, Cazaban CG, Chan SS et al (2023) Pediatric Outpatient Noncontrast Brain MRI: A Time-Driven Activity-Based Costing Analysis at Three U.S. Hospitals. AJR Am J Roentgenol 220(5):747–756. 10.2214/AJR.22.28490 Chen JV, Zapala MA, Zhou A et al (2023) Factors and Labor Cost Savings Associated with Successful Pediatric Imaging without Anesthesia: a Single-Institution Study. Acad Radiol 30(9):1979–1988. 10.1016/j.acra.2022.12.041 Brix MAK, Järvinen J, Bode MK et al (2024) Financial impact of incorporating deep learning reconstruction into magnetic resonance imaging routine. Eur J Radiol 175:111434. 10.1016/j.ejrad.2024.111434 Coté CJ, Wilson S, AMERICAN ACADEMY OF PEDIATRICS; AMERICAN ACADEMY OF PEDIATRIC DENTISTRY (2019) Guidelines for Monitoring and Management of Pediatric Patients Before, During, and After Sedation for Diagnostic and Therapeutic Procedures. Pediatrics 143(6):e20191000. 10.1542/peds.2019-1000 Salik I (2021) Anesthetic neurotoxicity in infants and children: a review of the literature. Med Res Arch 9(2). 10.18103/mra.v9i2.2368 Panayiotou HR, Mills LK, Broadbent DA et al (2023) Comprehensive Neonatal Cardiac, Feed and Wrap, Non-contrast, Non-sedated, Free-breathing Compressed Sensing 4D Flow MRI Assessment. J Magn Reson Imaging 57(3):789–799. 10.1002/jmri.28325 Beaulieu FP, Zuckerberg G, Coletti K et al (2024) Sedation and anesthesia for imaging of the infant and neonate-a brief review. Pediatr Radiol 54(10):1579–1588. 10.1007/s00247-024-05995-5 King R, Low S, Gee N et al (2023) Practical Stepwise Approach to Performing Neonatal Brain MR Imaging in the Research Setting. Children (Basel) . ;10(11):1759. Published 2023 Oct 30. 10.3390/children10111759 Neubauer V, Griesmaier E, Baumgartner K, Mallouhi A, Keller M, Kiechl-Kohlendorfer U (2011) Feasibility of cerebral MRI in non-sedated preterm-born infants at term-equivalent age: report of a single centre. Acta Paediatr 100(11):1544–1547. 10.1111/j.1651-2227.2011.02388.x Nagayama Y, Iwashita K, Maruyama N et al (2023) Deep learning-based reconstruction can improve the image quality of low radiation dose head CT. Eur Radiol 33(5):3253–3265. 10.1007/s00330-023-09559-3 Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 06 Nov, 2025 Read the published version in Pediatric Radiology → Version 1 posted Editorial decision: Revision requested 29 Jul, 2025 Reviews received at journal 27 Jul, 2025 Reviewers agreed at journal 08 Jul, 2025 Reviews received at journal 20 Jun, 2025 Reviewers agreed at journal 08 Jun, 2025 Reviewers invited by journal 03 Jun, 2025 Editor assigned by journal 03 Jun, 2025 Submission checks completed at journal 03 Jun, 2025 First submitted to journal 30 May, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {\"props\":{\"pageProps\":{\"initialData\":{\"identity\":\"rs-6786816\",\"acceptedTermsAndConditions\":true,\"allowDirectSubmit\":false,\"archivedVersions\":[],\"articleType\":\"Research Article\",\"associatedPublications\":[],\"authors\":[{\"id\":466025954,\"identity\":\"fbef9c33-1045-45ec-bd25-e75b24e90f94\",\"order_by\":0,\"name\":\"Ahmed Aldraihem\",\"email\":\"data:image/png;base64,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\",\"orcid\":\"\",\"institution\":\"Altakassusi Alliance Medical\",\"correspondingAuthor\":true,\"prefix\":\"\",\"firstName\":\"Ahmed\",\"middleName\":\"\",\"lastName\":\"Aldraihem\",\"suffix\":\"\"},{\"id\":466025955,\"identity\":\"34ae26f2-b186-495d-b254-2bc3c7c95e0b\",\"order_by\":1,\"name\":\"Moayad Almaimani\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"King Fahd Medical City\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Moayad\",\"middleName\":\"\",\"lastName\":\"Almaimani\",\"suffix\":\"\"},{\"id\":466025957,\"identity\":\"2e14dfa2-6669-4ee0-b8cc-33afdd371d0c\",\"order_by\":2,\"name\":\"Mohamed Bayoumi\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"King Saud Medical City\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Mohamed\",\"middleName\":\"\",\"lastName\":\"Bayoumi\",\"suffix\":\"\"},{\"id\":466025958,\"identity\":\"e99dd120-d5f0-4233-b24b-af4161fb7bab\",\"order_by\":3,\"name\":\"Abdulhamid Abunadi\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Altakassusi Alliance Medical\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Abdulhamid\",\"middleName\":\"\",\"lastName\":\"Abunadi\",\"suffix\":\"\"},{\"id\":466025962,\"identity\":\"5033a180-1e38-411d-af95-4f55e40bff7c\",\"order_by\":4,\"name\":\"Mohammed AlSwaileh\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Altakassusi Alliance Medical\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Mohammed\",\"middleName\":\"\",\"lastName\":\"AlSwaileh\",\"suffix\":\"\"},{\"id\":466025963,\"identity\":\"7c3d3813-2229-47a8-b567-157a02543c10\",\"order_by\":5,\"name\":\"Raneem AlDubaikhi\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Altakassusi Alliance Medical\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Raneem\",\"middleName\":\"\",\"lastName\":\"AlDubaikhi\",\"suffix\":\"\"},{\"id\":466025965,\"identity\":\"026e76e7-1a92-42be-b2e2-dafdd34aaa48\",\"order_by\":6,\"name\":\"Abdulrahman Alannaz\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Altakassusi Alliance Medical\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Abdulrahman\",\"middleName\":\"\",\"lastName\":\"Alannaz\",\"suffix\":\"\"},{\"id\":466025968,\"identity\":\"df47b9b8-ab62-4d23-b0c8-8440e582386d\",\"order_by\":7,\"name\":\"Norah Almuhaimed\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Altakassusi Alliance Medical\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Norah\",\"middleName\":\"\",\"lastName\":\"Almuhaimed\",\"suffix\":\"\"},{\"id\":466025970,\"identity\":\"2dd4c1cf-f5e3-4f0f-932a-f1802b9929ef\",\"order_by\":8,\"name\":\"Aljoharah Aljabr\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Altakassusi Alliance Medical\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Aljoharah\",\"middleName\":\"\",\"lastName\":\"Aljabr\",\"suffix\":\"\"}],\"badges\":[],\"createdAt\":\"2025-05-30 17:53:19\",\"currentVersionCode\":1,\"declarations\":\"\",\"doi\":\"10.21203/rs.3.rs-6786816/v1\",\"doiUrl\":\"https://doi.org/10.21203/rs.3.rs-6786816/v1\",\"draftVersion\":[],\"editorialEvents\":[{\"content\":\"https://doi.org/10.1007/s00247-025-06437-6\",\"type\":\"published\",\"date\":\"2025-11-06T15:57:25+00:00\"}],\"editorialNote\":\"\",\"failedWorkflow\":false,\"files\":[{\"id\":95564018,\"identity\":\"bbc7d3ae-d674-48cd-807a-451c50795172\",\"added_by\":\"auto\",\"created_at\":\"2025-11-10 16:06:32\",\"extension\":\"pdf\",\"order_by\":0,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"manuscript-pdf\",\"size\":644250,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"manuscript.pdf\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-6786816/v1/66d6c07a-46b8-4ec1-a8a6-13c2c271ce89.pdf\"}],\"financialInterests\":\"No competing interests reported.\",\"formattedTitle\":\"Optimizing Neonatal MRI Efficiency: Deep Learning-Assisted Feed and Wrap Technique Versus General Anaesthesia Using a Neonatal Brain MRI Stabilizer in Infants Under 4 Months\",\"fulltext\":[{\"header\":\"Introduction\",\"content\":\"\\u003cp\\u003eMagnetic resonance imaging (MRI) is essential in pediatric imaging due to its superior soft-tissue contrast and non-invasive nature. However, prolonged scan times pose a significant challenge, particularly in neonates prone to motion artifacts and often requiring sedation for immobility (Antonov et al., 2017; Smith et al., 2020). Traditional motion reduction strategies, such as general anesthesia (GA), ensure compliance but prolong procedural time and carry risks like respiratory complications (Antonov et al., 2017). The feed and wrap technique\\u0026mdash;using natural sleep post-feeding combined with swaddling and a neonatal MRI stabilizer\\u0026mdash;offers a non-invasive alternative but still faces challenges with unpredictable infant movement (PMC Study Group, 2024).\\u003c/p\\u003e \\u003cp\\u003eRecent advancements in neonatal MRI technology, including the use of deep learning (DL), have revolutionized MRI by enabling high-quality image reconstruction from undersampled k-space data, dramatically reducing scan times while preserving diagnostic accuracy (Lin et al., 2021; Tamir et al., 2020). DL leverages convolutional neural networks (CNNs) trained on vast datasets to predict missing information in accelerated scans. For example, GE Healthcare\\u0026rsquo;s \\u003cb\\u003eAIR\\u0026trade; Recon DL\\u003c/b\\u003e employs a CNN trained on over 2\\u0026nbsp;million MRI slices to remove noise, correct artifacts, and reconstruct images up to 50% faster than conventional methods (GE Healthcare, 2022). In neonatal imaging, this technology complements the feed and wrap technique by minimizing the time infants must remain motionless, thereby reducing reliance on GA (Lee et al., 2021). This study quantifies efficiency gains by comparing turnover times between DL-augmented feed and wrap and GA cohorts using a neonatal MRI stabilizer while exploring DL\\u0026rsquo;s role in optimizing neonatal workflows and minimizing risks.\\u003c/p\\u003e\"},{\"header\":\"Methods\",\"content\":\"\\u003cp\\u003eThis is a retrospective, cohort study in NICU infants under 4 months who underwent routine brain MRI. It involves acquiring MRI examinations at a 1.5 T scanner (GE Signa Voyager) using the Deep Learning-Assisted Feed and Wrap (DL-FW) technique versus a 1.5 T scanner (GE Optima MR 450w) in a patient under General Anesthesia (GA) with Neonatal MRI Stabilizer.\\u003c/p\\u003e \\u003cp\\u003ePatient data was extracted from the MRI archive, which includes the start and end time of the exam as well as calculated turnover time in NICU infants who underwent routine brain MRI between December 2024 and March 2025.\\u003c/p\\u003e \\u003cp\\u003eThe study was approved by the Institutional Review Board (IRB), and informed consent was obtained before the scan.\\u003c/p\\u003e \\u003cdiv id=\\\"Sec3\\\" class=\\\"Section2\\\"\\u003e \\u003ch2\\u003eInclusion and exclusion criteria\\u003c/h2\\u003e \\u003cp\\u003eThe inclusion criteria for this study consisted of infants aged 0\\u0026ndash;4 months who underwent routine brain MRI. These patients were scanned using either the Feed and Wrap (FW) technique with a Neonatal MRI Stabilizer or under General Anesthesia (GA) with a Neonatal MRI Stabilizer. The exclusion criteria were infants with incomplete medical records or missing MRI sequences, as well as those older than 4 months, for whom routine brain MRI examination was not indicated. Additionally, patients with congenital anomalies or neurological conditions that significantly impair the ability to remain still were excluded. Infants who required both GA and FW within the same session were also excluded, following the guidelines set by Moltoni et al. (2024). Patients were retrospectively categorized into two groups based on procedural documentation.\\u003c/p\\u003e \\u003c/div\\u003e\\n\\u003ch3\\u003eTechnique\\u003c/h3\\u003e\\n\\u003cp\\u003eIn the Deep Learning-Assisted Feed and Wrap (DL-FW) group, infants were fed before scanning to promote natural sleep. Swaddling was performed using a standardized neonatal MRI stabilizer, and motion correction software utilizing a deep learning-based algorithm was applied post-acquisition to optimize image quality. This technique notably shortened the duration of T2-weighted and diffusion sequences. Importantly, MRI was performed without the use of sedation or anesthesia.\\u003c/p\\u003e \\u003cp\\u003e In contrast, the General Anesthesia (GA) group received anesthesia according to institutional protocols, which included intravenous Propofol or oral chloral hydrate. An anesthesiologist continuously monitored the infants during the procedure and at its conclusion. The same neonatal MRI stabilizer was used for positioning in both groups.\\u003c/p\\u003e \\u003cp\\u003eAll neonates in the study underwent a departmental NICU brain MRI protocol, which was performed on a 1.5T scanner equipped with a dedicated neonatal head coil. The MRI protocol included standardized sequences to ensure comprehensive imaging, consisting of sagittal T1 CUBE, sagittal T2 CUBE, axial Diffusion-Weighted Echo (DWE), coronal DWE, axial T1 FLAIR Spin-Echo (SE), coronal T2 Fat-Suppressed (FS), and axial SWAN sequences. These sequences were carefully selected to provide detailed anatomical and functional imaging of the neonatal brain.\\u003c/p\\u003e \\u003cp\\u003eImaging duration is defined as the interval between the DICOM timestamp of the start time of the localizer sequence and the final sequence for the same patient. The duration was approximately 30\\u0026ndash;40 minutes without DL-FW, whereas with DL-FW, it was reduced to 15\\u0026ndash;20 minutes per session.\\u003c/p\\u003e \\u003cp\\u003eTurnover time is defined as the interval between the DICOM timestamp of the final sequence from the previous patient\\u0026rsquo;s exam and the start time of the localizer sequence for the next patient. This standardized measurement ensures consistent capture of the time required for patient disposition, room preparation, and setup for the subsequent exam.\\u003c/p\\u003e \\u003cp\\u003eDL Workflow where GE AIR\\u0026trade; Recon DL software utilized a CNN to reconstruct undersampled k-space data (GE Healthcare, 2022). Motion Free Brain technology corrected minor motion artifacts post-acquisition (GE Healthcare, 2023).\\u003c/p\\u003e \\u003cdiv id=\\\"Sec5\\\" class=\\\"Section2\\\"\\u003e \\u003ch2\\u003eStatistical Analysis:\\u003c/h2\\u003e \\u003cp\\u003eDescriptive and inferential statistics were performed using Python and SPSS (Version 29.0, IBM Corp.). Turnover time (in minutes) was compared between two independent groups: infants scanned using the DL-FW technique and those scanned under GA.\\u003c/p\\u003e \\u003cp\\u003eTo assess the distribution of turnover times, the Shapiro-Wilk test was performed for both groups. The results indicated that turnover times for the DL-FW group were not normally distributed (W\\u0026thinsp;=\\u0026thinsp;0.797, p\\u0026thinsp;=\\u0026thinsp;0.00045), whereas those for the GA group were normally distributed (W\\u0026thinsp;=\\u0026thinsp;0.940, p\\u0026thinsp;=\\u0026thinsp;0.119). Given the non-normal distribution of the DL-FW group, the non-parametric Mann-Whitney U test was used to compare turnover times between the two groups.\\u003c/p\\u003e \\u003cp\\u003eThe Mann-Whitney U test revealed a statistically significant difference in turnover times between the DL-FW and GA groups (U\\u0026thinsp;=\\u0026thinsp;159.0, p\\u0026thinsp;=\\u0026thinsp;0.0056), indicating that the DL-FW technique significantly reduced turnover times compared to the GA approach.\\u003c/p\\u003e \\u003c/div\\u003e\"},{\"header\":\"Results\",\"content\":\"\\u003cp\\u003eThe mean turnover time for the DL-FW group was 26.77\\u0026thinsp;\\u0026plusmn;\\u0026thinsp;11.33 minutes (range: 14\\u0026ndash;52 minutes), while the mean turnover time for the GA group was 34.74\\u0026thinsp;\\u0026plusmn;\\u0026thinsp;11.28 minutes (range: 19\\u0026ndash;59 minutes). The median turnover time was 23 minutes for DL-FW and 31 minutes for GA, indicating a notable difference favoring the DL-FW technique (Table\\u0026nbsp;\\u003cspan refid=\\\"Tab1\\\" class=\\\"InternalRef\\\"\\u003e1\\u003c/span\\u003e).\\u003c/p\\u003e \\u003cp\\u003e \\u003cdiv class=\\\"gridtable\\\"\\u003e\\u003ctable float=\\\"Yes\\\" id=\\\"Tab1\\\" border=\\\"1\\\"\\u003e \\u003ccaption language=\\\"En\\\"\\u003e \\u003cdiv class=\\\"CaptionNumber\\\"\\u003eTable 1\\u003c/div\\u003e \\u003cdiv class=\\\"CaptionContent\\\"\\u003e \\u003cp\\u003eDescriptive statistics for turnover times in both the DL-FW and GA groups\\u003c/p\\u003e \\u003c/div\\u003e \\u003c/caption\\u003e \\u003ccolgroup cols=\\\"8\\\"\\u003e \\u003cdiv align=\\\"left\\\" class=\\\"colspec\\\" colname=\\\"c1\\\" colnum=\\\"1\\\"\\u003e\\u003c/div\\u003e \\u003cdiv align=\\\"char\\\" char=\\\".\\\" class=\\\"colspec\\\" colname=\\\"c2\\\" colnum=\\\"2\\\"\\u003e\\u003c/div\\u003e \\u003cdiv align=\\\"char\\\" char=\\\".\\\" class=\\\"colspec\\\" colname=\\\"c3\\\" colnum=\\\"3\\\"\\u003e\\u003c/div\\u003e \\u003cdiv align=\\\"char\\\" char=\\\".\\\" class=\\\"colspec\\\" colname=\\\"c4\\\" colnum=\\\"4\\\"\\u003e\\u003c/div\\u003e \\u003cdiv align=\\\"char\\\" char=\\\".\\\" class=\\\"colspec\\\" colname=\\\"c5\\\" colnum=\\\"5\\\"\\u003e\\u003c/div\\u003e \\u003cdiv align=\\\"char\\\" char=\\\".\\\" class=\\\"colspec\\\" colname=\\\"c6\\\" colnum=\\\"6\\\"\\u003e\\u003c/div\\u003e \\u003cdiv align=\\\"char\\\" char=\\\".\\\" class=\\\"colspec\\\" colname=\\\"c7\\\" colnum=\\\"7\\\"\\u003e\\u003c/div\\u003e \\u003cdiv align=\\\"char\\\" char=\\\".\\\" class=\\\"colspec\\\" colname=\\\"c8\\\" colnum=\\\"8\\\"\\u003e\\u003c/div\\u003e \\u003cthead\\u003e \\u003ctr\\u003e \\u003cth align=\\\"left\\\" colname=\\\"c1\\\"\\u003e \\u003cp\\u003eGroup\\u003c/p\\u003e \\u003c/th\\u003e \\u003cth align=\\\"left\\\" colname=\\\"c2\\\"\\u003e \\u003cp\\u003eN\\u003c/p\\u003e \\u003c/th\\u003e \\u003cth align=\\\"left\\\" colname=\\\"c3\\\"\\u003e \\u003cp\\u003eMean (min)\\u003c/p\\u003e \\u003c/th\\u003e \\u003cth align=\\\"left\\\" colname=\\\"c4\\\"\\u003e \\u003cp\\u003eSD (min)\\u003c/p\\u003e \\u003c/th\\u003e \\u003cth align=\\\"left\\\" colname=\\\"c5\\\"\\u003e \\u003cp\\u003eMedian (min)\\u003c/p\\u003e \\u003c/th\\u003e \\u003cth align=\\\"left\\\" colname=\\\"c6\\\"\\u003e \\u003cp\\u003eIQR (min)\\u003c/p\\u003e \\u003c/th\\u003e \\u003cth align=\\\"left\\\" colname=\\\"c7\\\"\\u003e \\u003cp\\u003eMin (min)\\u003c/p\\u003e \\u003c/th\\u003e \\u003cth align=\\\"left\\\" colname=\\\"c8\\\"\\u003e \\u003cp\\u003eMax (min)\\u003c/p\\u003e \\u003c/th\\u003e \\u003c/tr\\u003e \\u003c/thead\\u003e \\u003ctbody\\u003e \\u003ctr\\u003e \\u003ctd align=\\\"left\\\" colname=\\\"c1\\\"\\u003e \\u003cp\\u003eDL-FW\\u003c/p\\u003e \\u003c/td\\u003e \\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c2\\\"\\u003e \\u003cp\\u003e22\\u003c/p\\u003e \\u003c/td\\u003e \\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c3\\\"\\u003e \\u003cp\\u003e26.77\\u003c/p\\u003e \\u003c/td\\u003e \\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c4\\\"\\u003e \\u003cp\\u003e11.33\\u003c/p\\u003e \\u003c/td\\u003e \\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c5\\\"\\u003e \\u003cp\\u003e23\\u003c/p\\u003e \\u003c/td\\u003e \\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c6\\\"\\u003e \\u003cp\\u003e20.5\\u0026ndash;27\\u003c/p\\u003e \\u003c/td\\u003e \\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c7\\\"\\u003e \\u003cp\\u003e14\\u003c/p\\u003e \\u003c/td\\u003e \\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c8\\\"\\u003e \\u003cp\\u003e52\\u003c/p\\u003e \\u003c/td\\u003e \\u003c/tr\\u003e \\u003ctr\\u003e \\u003ctd align=\\\"left\\\" colname=\\\"c1\\\"\\u003e \\u003cp\\u003eGA\\u003c/p\\u003e \\u003c/td\\u003e \\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c2\\\"\\u003e \\u003cp\\u003e27\\u003c/p\\u003e \\u003c/td\\u003e \\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c3\\\"\\u003e \\u003cp\\u003e34.74\\u003c/p\\u003e \\u003c/td\\u003e \\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c4\\\"\\u003e \\u003cp\\u003e11.28\\u003c/p\\u003e \\u003c/td\\u003e \\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c5\\\"\\u003e \\u003cp\\u003e31\\u003c/p\\u003e \\u003c/td\\u003e \\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c6\\\"\\u003e \\u003cp\\u003e28\\u0026ndash;42.5\\u003c/p\\u003e \\u003c/td\\u003e \\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c7\\\"\\u003e \\u003cp\\u003e19\\u003c/p\\u003e \\u003c/td\\u003e \\u003ctd align=\\\"char\\\" char=\\\".\\\" colname=\\\"c8\\\"\\u003e \\u003cp\\u003e59\\u003c/p\\u003e \\u003c/td\\u003e \\u003c/tr\\u003e \\u003c/tbody\\u003e \\u003c/colgroup\\u003e \\u003c/table\\u003e\\u003c/div\\u003e \\u003c/p\\u003e \\u003cp\\u003eThe interquartile range (IQR) for the \\u003cb\\u003eDL-FW group\\u003c/b\\u003e was \\u003cb\\u003e20.5\\u0026ndash;27 minutes\\u003c/b\\u003e, while for the \\u003cb\\u003eGA group\\u003c/b\\u003e, it was \\u003cb\\u003e28\\u0026ndash;42.5 minutes\\u003c/b\\u003e, highlighting that the GA turnover times tended to be longer and more consistent, whereas the DL-FW technique exhibited slightly more variability (Table \\u003cspan refid=\\\"Tab1\\\" class=\\\"InternalRef\\\"\\u003e1\\u003c/span\\u003e).\\u003c/p\\u003e\\n\\u003ch3\\u003eInterpretation:\\u003c/h3\\u003e\\n\\u003cp\\u003eThe DL-FW technique demonstrated significantly shorter turnover times compared to GA, reflecting improved procedural efficiency. The observed difference is statistically significant, as indicated by the Mann-Whitney U test (p\\u0026thinsp;=\\u0026thinsp;0.0056). This suggests that the DL-FW technique effectively reduces turnover time, enhancing workflow and patient throughput in the neonatal MRI setting.\\u003c/p\\u003e \\u003cp\\u003eDespite some variability in the DL-FW group, the overall reduction in turnover time aligns with previous findings that emphasize the efficiency of non-sedative imaging techniques combined with deep learning reconstruction. The integration of GE AIR\\u0026trade; Recon DL technology played a critical role in scan acceleration, further contributing to reduced turnaround times and optimized operational efficiency.\\u003c/p\\u003e \\u003cp\\u003eThese findings support the adoption of the DL-FW technique in neonatal imaging, particularly in resource-constrained settings where sedation carries additional risks and logistical demands. This approach not only minimizes sedation-related complications but also facilitates higher scanner utilization, aligning with patient-centered, sedation-free imaging protocols in pediatric radiology.\\u003c/p\\u003e\"},{\"header\":\"Discussion\",\"content\":\"\\u003cdiv id=\\\"Sec9\\\" class=\\\"Section2\\\"\\u003e \\u003ch2\\u003eProcedural Efficiency and Throughput with DL-FW versus GA\\u003c/h2\\u003e \\u003cp\\u003eAdopting a deep learning\\u0026ndash;assisted feed-and-wrap (DL-FW) approach in neonatal MRI offers marked gains in procedural efficiency compared to traditional general anesthesia (GA). One major advantage is the reduction in total examination and turnover time. Sedation and anesthesia introduce extra steps \\u0026ndash; induction, physiological stabilization, and post-scan recovery \\u0026ndash; which significantly extend a neonate\\u0026rsquo;s stay in the MRI suite [\\u003cspan citationid=\\\"CR44\\\" class=\\\"CitationRef\\\"\\u003e44\\u003c/span\\u003e]. In one hospital workflow analysis, unsedated pediatric MRI patients spent approximately 2.3 hours in the department on average, versus 3.6 hours with sedation and over 4 hours with GA [\\u003cspan citationid=\\\"CR44\\\" class=\\\"CitationRef\\\"\\u003e44\\u003c/span\\u003e]. This aligns with earlier findings that an anesthetized MRI can require nearly double the total procedure time of a natural sleep scan [\\u003cspan citationid=\\\"CR44\\\" class=\\\"CitationRef\\\"\\u003e44\\u003c/span\\u003e].\\u003c/p\\u003e \\u003cp\\u003eBy eliminating induction and recovery, the feed-and-wrap method inherently shortens visit duration and simplifies patient flow. Our findings are consistent with large cohort studies demonstrating that 90\\u0026ndash;95% of neonatal MRIs can be completed using feed-and-wrap techniques [\\u003cspan citationid=\\\"CR51\\\" class=\\\"CitationRef\\\"\\u003e51\\u003c/span\\u003e]. For example, Lollert et al. reported a 95% success rate with feed-and-wrap in neonates, with only a slight increase in motion artifact and a minor reduction in average image-quality scores compared to deep sedation [\\u003cspan citationid=\\\"CR12\\\" class=\\\"CitationRef\\\"\\u003e12\\u003c/span\\u003e]. Importantly, the instances of nondiagnostic scans with feed-and-wrap are low (roughly 5\\u0026ndash;15% in experienced centers) and are strongly associated with older infant age [\\u003cspan citationid=\\\"CR12\\\" class=\\\"CitationRef\\\"\\u003e12\\u003c/span\\u003e]. Infants under approximately 10 weeks old are ideal candidates, with one study finding the odds of feed-and-wrap failure to be 16-fold higher beyond 10 weeks of age [\\u003cspan citationid=\\\"CR45\\\" class=\\\"CitationRef\\\"\\u003e45\\u003c/span\\u003e].\\u003c/p\\u003e \\u003cp\\u003eIncorporating deep learning (DL) acceleration further augments this efficiency. Advanced DL-based image reconstruction tools (such as GE Healthcare\\u0026rsquo;s AIR Recon DL) significantly reduce scan times per sequence while maintaining or improving image quality. In pediatric MRI applications, DL reconstructions have enabled 20\\u0026ndash;40% reductions in sequence acquisition times without loss of diagnostic information [\\u003cspan citationid=\\\"CR46\\\" class=\\\"CitationRef\\\"\\u003e46\\u003c/span\\u003e]. For instance, Yoo et al. achieved approximately 29\\u0026ndash;41% faster 3D T1-weighted brain acquisitions in children using an AI-based reconstruction algorithm [\\u003cspan citationid=\\\"CR46\\\" class=\\\"CitationRef\\\"\\u003e46\\u003c/span\\u003e].\\u003c/p\\u003e \\u003c/div\\u003e\\n\\u003ch3\\u003eEconomic Implications and Cost Analyses\\u003c/h3\\u003e\\n\\u003cp\\u003eThe shift from GA to a DL-assisted feed-and-wrap paradigm has significant economic implications. Anesthetized pediatric MRIs are resource-intensive, requiring specialized staff, monitoring equipment, and extended peri-procedural care. A time-driven costing study found that an outpatient pediatric brain MRI under sedation had a mean total cost of approximately \\u003cspan\\u003e$\\u003c/span\\u003e842, compared to \\u003cspan\\u003e$\\u003c/span\\u003e262 for the same MRI performed without sedation [\\u003cspan citationid=\\\"CR47\\\" class=\\\"CitationRef\\\"\\u003e47\\u003c/span\\u003e]. Labor was the largest cost component, and the sedation workflow\\u0026rsquo;s extra time and personnel accounted for most of the \\u003cspan\\u003e$\\u003c/span\\u003e580 per-case cost differential [\\u003cspan citationid=\\\"CR47\\\" class=\\\"CitationRef\\\"\\u003e47\\u003c/span\\u003e].\\u003c/p\\u003e \\u003cp\\u003eWhen extrapolated to an annual departmental scale, the potential cost savings are significant. By eliminating anesthesia in 500 neonatal MRI cases, hospitals can save approximately \\u003cspan\\u003e$\\u003c/span\\u003e290,000. Larger centers performing 600\\u0026ndash;900 exams annually could save between \\u003cspan\\u003e$\\u003c/span\\u003e325,000 and \\u003cspan\\u003e$\\u003c/span\\u003e543,000 per year [\\u003cspan citationid=\\\"CR47\\\" class=\\\"CitationRef\\\"\\u003e47\\u003c/span\\u003e]. This estimate aligns with analyses from Brix et al., who reported that integrating DL reconstruction to boost MRI productivity allowed their hospital to forgo the purchase of an additional MRI scanner, saving approximately \\u003cspan\\u003e$\\u003c/span\\u003e436,000 annually [\\u003cspan citationid=\\\"CR49\\\" class=\\\"CitationRef\\\"\\u003e49\\u003c/span\\u003e].\\u003c/p\\u003e \\u003cp\\u003eBeyond direct cost considerations, there are broader economic benefits to the DL-FW model. Increased throughput allows for more billable exams, improving revenue capture. Avoiding anesthesia also reduces downstream costs, such as managing anesthesia-related complications or extended hospital stays [\\u003cspan citationid=\\\"CR48\\\" class=\\\"CitationRef\\\"\\u003e48\\u003c/span\\u003e].\\u003c/p\\u003e \\u003cdiv id=\\\"Sec11\\\" class=\\\"Section2\\\"\\u003e \\u003ch2\\u003eSafety, Validity, and Workflow Integration\\u003c/h2\\u003e \\u003cp\\u003eTransitioning to a DL-assisted, sedation-free imaging workflow requires careful implementation to ensure clinical safety. Avoiding anesthesia circumvents the risks associated with airway manipulation and anesthetic drugs in infants, such as respiratory depression and potential neurotoxicity [\\u003cspan citationid=\\\"CR50\\\" class=\\\"CitationRef\\\"\\u003e50\\u003c/span\\u003e, \\u003cspan citationid=\\\"CR51\\\" class=\\\"CitationRef\\\"\\u003e51\\u003c/span\\u003e]. Sedation-free imaging is inherently safer, and our results showed no procedure-related complications with DL-FW, consistent with other reports [\\u003cspan citationid=\\\"CR12\\\" class=\\\"CitationRef\\\"\\u003e12\\u003c/span\\u003e, \\u003cspan citationid=\\\"CR45\\\" class=\\\"CitationRef\\\"\\u003e45\\u003c/span\\u003e].\\u003c/p\\u003e \\u003cp\\u003eProper scan scheduling is crucial for the success of feed-and-wrap protocols, ideally aligning MRI appointments with feeding and sleep times. Parental involvement and preparation enhance the likelihood of successful unsedated imaging [\\u003cspan citationid=\\\"CR55\\\" class=\\\"CitationRef\\\"\\u003e55\\u003c/span\\u003e]. Additionally, staff training on using DL-based reconstruction tools is essential to maintain diagnostic consistency. Radiologists should be oriented to the image appearance changes brought about by DL-enhanced reconstructions, which often reduce noise and improve contrast [ 56].\\u003c/p\\u003e \\u003cp\\u003eImplementing DL-based protocols requires multidisciplinary coordination, including neonatal care teams and MRI technologists. By creating standardized sedation-free pathways and ensuring efficient workflow integration, radiology departments can enhance patient throughput while maintaining high diagnostic standards.\\u003c/p\\u003e \\u003c/div\\u003e\"},{\"header\":\"Conclusion\",\"content\":\"\\u003cp\\u003eDL-FW significantly reduces infant MRI turnover time compared to GA, with a 6.5-minute median reduction and moderate effect size. This supports DL-FW as a promising alternative to GA in neonatal imaging, balancing efficiency and safety.\\u003c/p\\u003e\"},{\"header\":\"Declarations\",\"content\":\"\\u003ch2\\u003eEthics approval and consent to participate:\\u003c/h2\\u003e\\n\\u003cp\\u003eThe application for ethical approval was done by the institutional review board office.\\u003c/p\\u003e\\n\\u003ch2\\u003eConsent for publication:\\u003c/h2\\u003e\\n\\u003cp\\u003eNot applicable.\\u003c/p\\u003e\\n\\u003ch2\\u003eCompeting interest:\\u003c/h2\\u003e\\n\\u003cp\\u003eThe authors declare that they have no conflict of interest.\\u003c/p\\u003e\\n\\u003ch2\\u003eFunding:\\u003c/h2\\u003e\\n\\u003cp\\u003eThis research received no specific grant from any funding agency.\\u003c/p\\u003e\\n\\u003ch2\\u003eAuthor Contribution\\u003c/h2\\u003e\\n\\u003cp\\u003eDr. Aldraihem acted as the person who conducted this study. Dr. Bayoumi and Dr. Almaimani were involved in the literature review, methodology, and started writing this manuscript, and followed the patient data. Mr.Abunadi, Mr. Alswaileh, Mr. Alannaz, Mrs Raneem and MRs. Noorah were involved in the literature search, conception, study design, and acquisition, as well as in developing the research idea, as well as reviewing the manuscript. Dr. Aljabr was involved in writing the introduction and discussion sections.\\u003c/p\\u003e\\n\\u003ch2\\u003eAvailability of supporting data:\\u003c/h2\\u003e\\n\\u003cp\\u003eThe data used during the current study are not publicly available due to patient privacy, but are available from the corresponding author upon reasonable request.\\u003c/p\\u003e\"},{\"header\":\"References\",\"content\":\"\\u003col\\u003e\\u003cli\\u003e\\u003cspan\\u003eAllison J, Yanasak N, What MRI (2015) Sequences Produce the Highest Specific Absorption Rate (SAR), and Is There Something We Should Be Doing to Reduce the SAR During Standard Examinations? AJR Am J Roentgenol 205(2):W140. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.2214/AJR.14.14173\\u003c/span\\u003e\\u003cspan address=\\\"10.2214/AJR.14.14173\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eAntonov NK, Ruzal-Shapiro CB, Morel KD et al (2017) Feed and Wrap MRI Technique in Infants. Clin Pediatr (Phila) 56(12):1095\\u0026ndash;1103. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1177/0009922816677806\\u003c/span\\u003e\\u003cspan address=\\\"10.1177/0009922816677806\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eClifford B, Conklin J, Huang SY et al (2022) An artificial intelligence-accelerated 2-minute multi-shot echo planar imaging protocol for comprehensive high-quality clinical brain imaging. Magn Reson Med 87(5):2453\\u0026ndash;2463. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1002/mrm.29117\\u003c/span\\u003e\\u003cspan address=\\\"10.1002/mrm.29117\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eGE Healthcare (2025) MR image reconstruction with AIR\\u0026trade; Recon DL [Internet]. Available from: \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003ehttps://www.gehealthcare.com/products/magnetic-resonance-imaging/air-recon-dl\\u003c/span\\u003e\\u003cspan address=\\\"https://www.gehealthcare.com/products/magnetic-resonance-imaging/air-recon-dl\\\" targettype=\\\"URL\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e. Accessed May 24\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eGE Healthcare launches new AI-enabled MRI system at RSNA23 [Internet]. Imaging Technology News (2023) [cited 2025 May 18]. Available from: \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003ehttps://www.itnonline.com/content/ge-healthcare-launches-new-ai-enabled-mri-system-rsna23\\u003c/span\\u003e\\u003cspan address=\\\"https://www.itnonline.com/content/ge-healthcare-launches-new-ai-enabled-mri-system-rsna23\\\" targettype=\\\"URL\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eGE Healthcare (2025) Life-speed imaging with Sonic DL\\u0026trade;: deep learning MRI acceleration [Internet]. Available from: \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003ehttps://www.gehealthcare.com/products/magnetic-resonance-imaging/sonic-dl-deep-learning-mri-acceleration\\u003c/span\\u003e\\u003cspan address=\\\"https://www.gehealthcare.com/products/magnetic-resonance-imaging/sonic-dl-deep-learning-mri-acceleration\\\" targettype=\\\"URL\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e. Accessed May 24\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eHammernik K, Schlemper J, Qin C, Duan J, Summers RM, Rueckert D (2021) Systematic evaluation of iterative deep neural networks for fast parallel MRI reconstruction with sensitivity-weighted coil combination. Magn Reson Med 86(4):1859\\u0026ndash;1872. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1002/mrm.28827\\u003c/span\\u003e\\u003cspan address=\\\"10.1002/mrm.28827\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eKashiwagi N, Tanaka H, Yamashita Y et al (2021) Applicability of deep learning-based reconstruction trained by brain and knee 3T MRI to lumbar 1.5T MRI. Acta Radiol Open 10(6):20584601211023939. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1177/20584601211023939\\u003c/span\\u003e\\u003cspan address=\\\"10.1177/20584601211023939\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eLin DJ, Johnson PM, Knoll F, Lui YW (2021) Artificial Intelligence for MR Image Reconstruction: An Overview for Clinicians. J Magn Reson Imaging 53(4):1015\\u0026ndash;1028. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1002/jmri.27078\\u003c/span\\u003e\\u003cspan address=\\\"10.1002/jmri.27078\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eMontalt-Tordera J, Muthurangu V, Hauptmann A, Steeden JA (2021) Machine learning in Magnetic Resonance Imaging: Image reconstruction. Phys Med 83:79\\u0026ndash;87. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1016/j.ejmp.2021.02.020\\u003c/span\\u003e\\u003cspan address=\\\"10.1016/j.ejmp.2021.02.020\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eYang A, Finkelstein M, Koo C, Doshi AH (2024) Impact of Deep Learning Image Reconstruction Methods on MRI Throughput. Radiol Artif Intell 6(3):e230181. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1148/ryai.230181\\u003c/span\\u003e\\u003cspan address=\\\"10.1148/ryai.230181\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eLollert A, Frey KS, Hoffmann C et al (2024) Feed-and-wrap technique versus deep sedation for neonatal magnetic resonance imaging: a retrospective comparative study. Eur Radiol 34(11):7104\\u0026ndash;7114. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1007/s00330-024-10777-6\\u003c/span\\u003e\\u003cspan address=\\\"10.1007/s00330-024-10777-6\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eMoltoni G, Lucignani G, Sgr\\u0026ograve; S et al (2024) MRI scan with the feed and wrap technique and with an optimized anesthesia protocol: a retrospective analysis of a single-center experience. Front Pediatr 12:1415603. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.3389/fped.2024.1415603\\u003c/span\\u003e\\u003cspan address=\\\"10.3389/fped.2024.1415603\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eKim E, Cho HH, Cho SH et al (2022) Accelerated Synthetic MRI with Deep Learning-Based Reconstruction for Pediatric Neuroimaging. AJNR Am J Neuroradiol 43(11):1653\\u0026ndash;1659. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.3174/ajnr.A7664\\u003c/span\\u003e\\u003cspan address=\\\"10.3174/ajnr.A7664\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eDong SZ, Zhu M, Bulas D (2019) Techniques for minimizing sedation in pediatric MRI. J Magn Reson Imaging 50(4):1047\\u0026ndash;1054. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1002/jmri.26703\\u003c/span\\u003e\\u003cspan address=\\\"10.1002/jmri.26703\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eBarth M, Breuer F, Koopmans PJ, Norris DG, Poser BA (2016) Simultaneous multislice (SMS) imaging techniques. Magn Reson Med 75(1):63\\u0026ndash;81. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1002/mrm.25897\\u003c/span\\u003e\\u003cspan address=\\\"10.1002/mrm.25897\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eYoo YM, Park JE, Park MS, Lee JH (2021) Implementation of the feed and swaddle technique as a non-pharmacological strategy to conduct brain magnetic resonance imaging in very low birth weight infants. Neonatal Med 28(3):108\\u0026ndash;115. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.5385/nm.2021.28.3.108\\u003c/span\\u003e\\u003cspan address=\\\"10.5385/nm.2021.28.3.108\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eTian Q, Li Z, Fan Q et al (2022) SDnDTI: Self-supervised deep learning-based denoising for diffusion tensor MRI. NeuroImage 253:119033. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1016/j.neuroimage.2022.119033\\u003c/span\\u003e\\u003cspan address=\\\"10.1016/j.neuroimage.2022.119033\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eTeixeira AG, Malik RP, Hajnal SJ (2019) Fast quantitative MRI using controlled saturation magnetization transfer. Magn Reson Med 81(2):907\\u0026ndash;920. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1002/mrm.27442\\u003c/span\\u003e\\u003cspan address=\\\"10.1002/mrm.27442\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eGulani V, Calamante F, Shellock FG, Kanal E, Reeder SB (2017) Gadolinium deposition in the brain: summary of evidence and recommendations. Lancet Neurol 16(7):564\\u0026ndash;570. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1016/S1474-4422(17)30158-8\\u003c/span\\u003e\\u003cspan address=\\\"10.1016/S1474-4422(17)30158-8\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eEdwards AD, Arthurs OJ (2011) Paediatric MRI under sedation: is it necessary? What is the evidence for the alternatives? Pediatr Radiol 41(11):1353\\u0026ndash;1364. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1007/s00247-011-2147-7\\u003c/span\\u003e\\u003cspan address=\\\"10.1007/s00247-011-2147-7\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eKim SH, Choi YH, Lee JS et al (2023) Deep learning reconstruction in pediatric brain MRI: comparison of image quality with conventional T2-weighted MRI. Neuroradiology 65(1):207\\u0026ndash;214. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1007/s00234-022-03053-1\\u003c/span\\u003e\\u003cspan address=\\\"10.1007/s00234-022-03053-1\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eGilmore JH, Knickmeyer RC, Gao W (2018) Imaging structural and functional brain development in early childhood. Nat Rev Neurosci 19(3):123\\u0026ndash;137. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1038/nrn.2018.1\\u003c/span\\u003e\\u003cspan address=\\\"10.1038/nrn.2018.1\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eRothman S, Gonen A, Vodonos A, Novack V, Shelef I (2016) Does preparation of children before MRI reduce the need for anesthesia? Prospective randomized control trial. Pediatr Radiol 46(11):1599\\u0026ndash;1605. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1007/s00247-016-3651-6\\u003c/span\\u003e\\u003cspan address=\\\"10.1007/s00247-016-3651-6\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eBadke D\\u0026rsquo;Andrea C, Kenley JK, Montez DF et al (2022) Real-time motion monitoring improves functional MRI data quality in infants. Dev Cogn Neurosci 55:101116. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1016/j.dcn.2022.101116\\u003c/span\\u003e\\u003cspan address=\\\"10.1016/j.dcn.2022.101116\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eChen C, Qin C, Qiu H et al (2020) Deep Learning for Cardiac Image Segmentation: A Review. \\u003cem\\u003eFront Cardiovasc Med\\u003c/em\\u003e. ;7:25. Published 2020 Mar 5. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.3389/fcvm.2020.00025\\u003c/span\\u003e\\u003cspan address=\\\"10.3389/fcvm.2020.00025\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eEbinesh A, Saxena S (2024) Principles of a controlled imaging environment for neonatal brain MRI: Strategies for optimal image quality and safety. Neuroradiol J Published online November 22. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1177/19714009241303149\\u003c/span\\u003e\\u003cspan address=\\\"10.1177/19714009241303149\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eDong SZ, Zhu M, Bulas D (2019) Techniques for minimizing sedation in pediatric MRI. J Magn Reson Imaging 50(4):1047\\u0026ndash;1054. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1002/jmri.26703\\u003c/span\\u003e\\u003cspan address=\\\"10.1002/jmri.26703\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eHughes EJ, Winchman T, Padormo F et al (2017) A dedicated neonatal brain imaging system. Magn Reson Med 78(2):794\\u0026ndash;804. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1002/mrm.26462\\u003c/span\\u003e\\u003cspan address=\\\"10.1002/mrm.26462\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eRichter L, Fetit AE (2022) Accurate segmentation of neonatal brain MRI with deep learning. Front Neuroinform 16:1006532. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.3389/fninf.2022.1006532\\u003c/span\\u003e\\u003cspan address=\\\"10.3389/fninf.2022.1006532\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eOishi K, Faria AV, Mori S (2012) Advanced neonatal NeuroMRI. Magn Reson Imaging Clin N Am 20(1):81\\u0026ndash;91. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1016/j.mric.2011.08.009\\u003c/span\\u003e\\u003cspan address=\\\"10.1016/j.mric.2011.08.009\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eArtunduaga M, Liu CA, Morin CE et al (2021) Safety challenges related to the use of sedation and general anesthesia in pediatric patients undergoing magnetic resonance imaging examinations. Pediatr Radiol 51(5):724\\u0026ndash;735. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1007/s00247-021-05044-5\\u003c/span\\u003e\\u003cspan address=\\\"10.1007/s00247-021-05044-5\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eKuperman JM, Brown TT, Ahmadi ME et al (2011) Prospective motion correction improves diagnostic utility of pediatric MRI scans. Pediatr Radiol 41(12):1578\\u0026ndash;1582. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1007/s00247-011-2205-1\\u003c/span\\u003e\\u003cspan address=\\\"10.1007/s00247-011-2205-1\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eMeshaka R, Gaunt T, Shelmerdine SC (2023) Artificial intelligence applied to fetal MRI: A scoping review of current research. Br J Radiol 96(1147):20211205. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1259/bjr.20211205\\u003c/span\\u003e\\u003cspan address=\\\"10.1259/bjr.20211205\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eUramatsu M, Takahashi H, Barach P, Fujisawa Y, Takahashi M, Mishima S, Yamanaka G (2024) Improving pediatric magnetic resonance imaging safety by enhanced non-technical skills and team collaboration. Brain Dev 46(6):395\\u0026ndash;403. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1016/j.braindev.2024.104311\\u003c/span\\u003e\\u003cspan address=\\\"10.1016/j.braindev.2024.104311\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eZhang T, Pauly JM, Levesque IR (2015) Accelerating parameter mapping with a locally low rank constraint. Magn Reson Med 73(2):655\\u0026ndash;661. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1002/mrm.25161\\u003c/span\\u003e\\u003cspan address=\\\"10.1002/mrm.25161\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eKebiri H, Gholipour A, Vasung L, Krsnik Ž, Karimi D, Cuadra MB (2023) Deep learning microstructure estimation of developing brains from diffusion MRI: a newborn and fetal study. Preprint bioRxiv. 2023.07.01.547351. Published 2023 Jul 2 \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1101/2023.07.01.547351\\u003c/span\\u003e\\u003cspan address=\\\"10.1101/2023.07.01.547351\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eHarrington SG, Jaimes C, Weagle KM, Greer ML, Gee MS (2021) Strategies to perform magnetic resonance imaging in infants and young children without sedation. Pediatr Radiol 51(3):374\\u0026ndash;381. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1007/s00247-021-04960-8\\u003c/span\\u003e\\u003cspan address=\\\"10.1007/s00247-021-04960-8\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eHeckel R, Jacob M, Chaudhari A, Perlman O, Shimron E (2024) Deep learning for accelerated and robust MRI reconstruction. MAGMA 37(3):335\\u0026ndash;368. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1007/s10334-024-01173-8\\u003c/span\\u003e\\u003cspan address=\\\"10.1007/s10334-024-01173-8\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eMontalt-Tordera J, Muthurangu V, Hauptmann A, Steeden JA (2021) Machine learning in Magnetic Resonance Imaging: Image reconstruction. Phys Med 83:79\\u0026ndash;87. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1016/j.ejmp.2021.02.020\\u003c/span\\u003e\\u003cspan address=\\\"10.1016/j.ejmp.2021.02.020\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eYang A, Finkelstein M, Koo C, Doshi AH (2024) Impact of Deep Learning Image Reconstruction Methods on MRI Throughput. Radiol Artif Intell 6(3):e230181. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1148/ryai.230181\\u003c/span\\u003e\\u003cspan address=\\\"10.1148/ryai.230181\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eWilliams M (2024) Innovations in pediatric sedation: improving procedural comfort and safety. J Clin Anesthesiol 8:264. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.37421/2684-6004.2024.8.264\\u003c/span\\u003e\\u003cspan address=\\\"10.37421/2684-6004.2024.8.264\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eArvinte M, Vishwanath S, Tewfik AH, Tamir JI, Deep J-S (2021) Accelerated MRI Reconstruction via Unrolled Alternating Optimization. In: de Bruijne M, Cattin P, Cotin S et al (eds) Medical Image Computing and Computer-Assisted Intervention \\u0026ndash; MICCAI 2021. Lecture Notes in Computer Science, vol 12906. Springer, pp 350\\u0026ndash;360. doi:\\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1007/978-3-030-87231-1_34\\u003c/span\\u003e\\u003cspan address=\\\"10.1007/978-3-030-87231-1_34\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e.\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eVanderby SA, Babyn PS, Carter MW, Jewell SM, McKeever PD (2010) Effect of anesthesia and sedation on pediatric MR imaging patient flow. Radiology 256(1):229\\u0026ndash;237. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1148/radiol.10091124\\u003c/span\\u003e\\u003cspan address=\\\"10.1148/radiol.10091124\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eWeng W, Reid A, Thompson A, Kuthubutheen J (2020) Evaluating the success of a newly introduced Feed and Wrap protocol in magnetic resonance imaging scanning of the temporal bone for the evaluation of congenital sensorineural hearing loss. Int J Pediatr Otorhinolaryngol 132:109910. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1016/j.ijporl.2020.109910\\u003c/span\\u003e\\u003cspan address=\\\"10.1016/j.ijporl.2020.109910\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eYoo H, Moon HE, Kim S et al (2025) Evaluation of Image Quality and Scan Time Efficiency in Accelerated 3D T1-Weighted Pediatric Brain MRI Using Deep Learning-Based Reconstruction. Korean J Radiol 26(2):180\\u0026ndash;192. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.3348/kjr.2024.0701\\u003c/span\\u003e\\u003cspan address=\\\"10.3348/kjr.2024.0701\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eHayatghaibi SE, Cazaban CG, Chan SS et al (2023) Pediatric Outpatient Noncontrast Brain MRI: A Time-Driven Activity-Based Costing Analysis at Three U.S. Hospitals. AJR Am J Roentgenol 220(5):747\\u0026ndash;756. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.2214/AJR.22.28490\\u003c/span\\u003e\\u003cspan address=\\\"10.2214/AJR.22.28490\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eChen JV, Zapala MA, Zhou A et al (2023) Factors and Labor Cost Savings Associated with Successful Pediatric Imaging without Anesthesia: a Single-Institution Study. Acad Radiol 30(9):1979\\u0026ndash;1988. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1016/j.acra.2022.12.041\\u003c/span\\u003e\\u003cspan address=\\\"10.1016/j.acra.2022.12.041\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eBrix MAK, J\\u0026auml;rvinen J, Bode MK et al (2024) Financial impact of incorporating deep learning reconstruction into magnetic resonance imaging routine. Eur J Radiol 175:111434. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1016/j.ejrad.2024.111434\\u003c/span\\u003e\\u003cspan address=\\\"10.1016/j.ejrad.2024.111434\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eCot\\u0026eacute; CJ, Wilson S, AMERICAN ACADEMY OF PEDIATRICS; AMERICAN ACADEMY OF PEDIATRIC DENTISTRY (2019) Guidelines for Monitoring and Management of Pediatric Patients Before, During, and After Sedation for Diagnostic and Therapeutic Procedures. Pediatrics 143(6):e20191000. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1542/peds.2019-1000\\u003c/span\\u003e\\u003cspan address=\\\"10.1542/peds.2019-1000\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eSalik I (2021) Anesthetic neurotoxicity in infants and children: a review of the literature. Med Res Arch 9(2). \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.18103/mra.v9i2.2368\\u003c/span\\u003e\\u003cspan address=\\\"10.18103/mra.v9i2.2368\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003ePanayiotou HR, Mills LK, Broadbent DA et al (2023) Comprehensive Neonatal Cardiac, Feed and Wrap, Non-contrast, Non-sedated, Free-breathing Compressed Sensing 4D Flow MRI Assessment. J Magn Reson Imaging 57(3):789\\u0026ndash;799. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1002/jmri.28325\\u003c/span\\u003e\\u003cspan address=\\\"10.1002/jmri.28325\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eBeaulieu FP, Zuckerberg G, Coletti K et al (2024) Sedation and anesthesia for imaging of the infant and neonate-a brief review. Pediatr Radiol 54(10):1579\\u0026ndash;1588. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1007/s00247-024-05995-5\\u003c/span\\u003e\\u003cspan address=\\\"10.1007/s00247-024-05995-5\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eKing R, Low S, Gee N et al (2023) Practical Stepwise Approach to Performing Neonatal Brain MR Imaging in the Research Setting. \\u003cem\\u003eChildren (Basel)\\u003c/em\\u003e. ;10(11):1759. Published 2023 Oct 30. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.3390/children10111759\\u003c/span\\u003e\\u003cspan address=\\\"10.3390/children10111759\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eNeubauer V, Griesmaier E, Baumgartner K, Mallouhi A, Keller M, Kiechl-Kohlendorfer U (2011) Feasibility of cerebral MRI in non-sedated preterm-born infants at term-equivalent age: report of a single centre. Acta Paediatr 100(11):1544\\u0026ndash;1547. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1111/j.1651-2227.2011.02388.x\\u003c/span\\u003e\\u003cspan address=\\\"10.1111/j.1651-2227.2011.02388.x\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e \\u003cli\\u003e\\u003cspan\\u003eNagayama Y, Iwashita K, Maruyama N et al (2023) Deep learning-based reconstruction can improve the image quality of low radiation dose head CT. Eur Radiol 33(5):3253\\u0026ndash;3265. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1007/s00330-023-09559-3\\u003c/span\\u003e\\u003cspan address=\\\"10.1007/s00330-023-09559-3\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e\\u003c/ol\\u003e\"}],\"fulltextSource\":\"\",\"fullText\":\"\",\"funders\":[],\"hasAdminPriorityOnWorkflow\":false,\"hasManuscriptDocX\":true,\"hasOptedInToPreprint\":true,\"hasPassedJournalQc\":\"\",\"hasAnyPriority\":false,\"hideJournal\":false,\"highlight\":\"\",\"institution\":\"\",\"isAcceptedByJournal\":true,\"isAuthorSuppliedPdf\":false,\"isDeskRejected\":\"\",\"isHiddenFromSearch\":false,\"isInQc\":false,\"isInWorkflow\":false,\"isPdf\":false,\"isPdfUpToDate\":true,\"isWithdrawnOrRetracted\":false,\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"identity\":\"pediatric-radiology\",\"isNatureJournal\":false,\"hasQc\":true,\"allowDirectSubmit\":false,\"externalIdentity\":\"prad\",\"sideBox\":\"Learn more about [Pediatric Radiology](http://link.springer.com/journal/247)\",\"snPcode\":\"247\",\"submissionUrl\":\"https://submission.nature.com/new-submission/247/3\",\"title\":\"Pediatric Radiology\",\"twitterHandle\":\"\",\"acdcEnabled\":true,\"dfaEnabled\":true,\"editorialSystem\":\"stoa\",\"reportingPortfolio\":\"Springer Hybrid\",\"inReviewEnabled\":true,\"inReviewRevisionsEnabled\":false},\"keywords\":\"Neonatal MRI, Deep Learning, Feed and Wrap, General Anaesthesia, Image Acceleration, Paediatric Imaging, MRI Efficiency, Sedation-Free Imaging, AIR Recon DL, Workflow Optimization\",\"lastPublishedDoi\":\"10.21203/rs.3.rs-6786816/v1\",\"lastPublishedDoiUrl\":\"https://doi.org/10.21203/rs.3.rs-6786816/v1\",\"license\":{\"name\":\"CC BY 4.0\",\"url\":\"https://creativecommons.org/licenses/by/4.0/\"},\"manuscriptAbstract\":\"\\u003ch2\\u003eIntroduction:\\u003c/h2\\u003e \\u003cp\\u003eMagnetic Resonance Imaging (MRI) in neonates presents unique challenges due to patient motion and the need for sedation. While general anaesthesia (GA) offers motion suppression, it increases procedural risk and resource demands. The Feed and Wrap (FW) technique, enhanced with deep learning (DL)-based image reconstruction, presents a potential alternative by reducing scan time and eliminating sedation requirements.\\u003c/p\\u003e\\u003ch2\\u003eMethods:\\u003c/h2\\u003e \\u003cp\\u003eThis retrospective cohort study included 49 neonates under four months who underwent routine brain MRI at a tertiary care centre. Two groups were compared: one scanned using a DL-assisted Feed and Wrap (DL-FW) technique, and the other under GA. Standardized MRI protocols were applied across both groups, with GE AIR\\u0026trade; Recon DL used to accelerate scans in the DL-FW group. Turnover time (defined as the interval from the last DICOM sequence of one exam to the localizer of the next) was the primary metric. Statistical analyses included the Shapiro-Wilk test for normality and the Mann-Whitney U test for group comparisons.\\u003c/p\\u003e\\u003ch2\\u003eResults:\\u003c/h2\\u003e \\u003cp\\u003eAmong 49 infants, 27 underwent MRI under GA and 22 with DL-FW. The DL-FW group demonstrated a shorter mean turnover time (26.77\\u0026thinsp;\\u0026plusmn;\\u0026thinsp;11.33 minutes) compared to the GA group (32.6\\u0026thinsp;\\u0026plusmn;\\u0026thinsp;9.6 minutes), though variability was higher in the DL-FW group. The application of DL-based reconstruction reduced individual scan durations by approximately 30%, saving around 7.5 minutes per scan. When extrapolated, this translates to over 62 hours of annual scanner time saved, supporting improved throughput and resource utilization.\\u003c/p\\u003e\\u003ch2\\u003eConclusion:\\u003c/h2\\u003e \\u003cp\\u003eThe DL-FW technique significantly enhances MRI workflow efficiency in neonates while avoiding the risks associated with anaesthesia. Despite some variability, DL-FW offers a viable, safer, and cost-effective alternative to GA, aligning with patient-centered, sedation-free imaging practices in neonatal care.\\u003c/p\\u003e\",\"manuscriptTitle\":\"Optimizing Neonatal MRI Efficiency: Deep Learning-Assisted Feed and Wrap Technique Versus General Anaesthesia Using a Neonatal Brain MRI Stabilizer in Infants Under 4 Months\",\"msid\":\"\",\"msnumber\":\"\",\"nonDraftVersions\":[{\"code\":1,\"date\":\"2025-06-06 14:16:13\",\"doi\":\"10.21203/rs.3.rs-6786816/v1\",\"editorialEvents\":[{\"type\":\"communityComments\",\"content\":0},{\"type\":\"decision\",\"content\":\"Revision requested\",\"date\":\"2025-07-29T07:17:04+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"editorInvitedReview\",\"content\":\"\",\"date\":\"2025-07-27T21:43:59+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"197199863736983113939886389030006795796\",\"date\":\"2025-07-08T09:00:00+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"editorInvitedReview\",\"content\":\"\",\"date\":\"2025-06-20T22:21:26+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"208744128935880044404627371570520809223\",\"date\":\"2025-06-09T02:39:30+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewersInvited\",\"content\":\"\",\"date\":\"2025-06-03T14:41:01+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"editorAssigned\",\"content\":\"\",\"date\":\"2025-06-03T11:26:16+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"checksComplete\",\"content\":\"\",\"date\":\"2025-06-03T11:25:52+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"submitted\",\"content\":\"Pediatric Radiology\",\"date\":\"2025-05-30T17:45:40+00:00\",\"index\":\"\",\"fulltext\":\"\"}],\"status\":\"published\",\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"identity\":\"pediatric-radiology\",\"isNatureJournal\":false,\"hasQc\":true,\"allowDirectSubmit\":false,\"externalIdentity\":\"prad\",\"sideBox\":\"Learn more about [Pediatric Radiology](http://link.springer.com/journal/247)\",\"snPcode\":\"247\",\"submissionUrl\":\"https://submission.nature.com/new-submission/247/3\",\"title\":\"Pediatric Radiology\",\"twitterHandle\":\"\",\"acdcEnabled\":true,\"dfaEnabled\":true,\"editorialSystem\":\"stoa\",\"reportingPortfolio\":\"Springer Hybrid\",\"inReviewEnabled\":true,\"inReviewRevisionsEnabled\":false}}],\"origin\":\"\",\"ownerIdentity\":\"fa8fe6a0-0289-4eb4-b76c-6fa1aa38a269\",\"owner\":[],\"postedDate\":\"June 6th, 2025\",\"published\":true,\"recentEditorialEvents\":[],\"rejectedJournal\":[],\"revision\":\"\",\"amendment\":\"\",\"status\":\"published-in-journal\",\"subjectAreas\":[],\"tags\":[],\"updatedAt\":\"2025-11-10T16:00:30+00:00\",\"versionOfRecord\":{\"articleIdentity\":\"rs-6786816\",\"link\":\"https://doi.org/10.1007/s00247-025-06437-6\",\"journal\":{\"identity\":\"pediatric-radiology\",\"isVorOnly\":false,\"title\":\"Pediatric Radiology\"},\"publishedOn\":\"2025-11-06 15:57:25\",\"publishedOnDateReadable\":\"November 6th, 2025\"},\"versionCreatedAt\":\"2025-06-06 14:16:13\",\"video\":\"\",\"vorDoi\":\"10.1007/s00247-025-06437-6\",\"vorDoiUrl\":\"https://doi.org/10.1007/s00247-025-06437-6\",\"workflowStages\":[]},\"version\":\"v1\",\"identity\":\"rs-6786816\",\"journalConfig\":\"researchsquare\"},\"__N_SSP\":true},\"page\":\"/article/[identity]/[[...version]]\",\"query\":{\"redirect\":\"/article/rs-6786816\",\"identity\":\"rs-6786816\",\"version\":[\"v1\"]},\"buildId\":\"8U1c8b4HqxoKbykW_rLl7\",\"isFallback\":false,\"isExperimentalCompile\":false,\"dynamicIds\":[84888],\"gssp\":true,\"scriptLoader\":[]}","source_license":"CC-BY-4.0","license_restricted":false}