{"paper_id":"215cfca5-9fae-472c-8471-748a7c1d52cb","body_text":"Instant3D: A User-Friendly GUI Integrating TotalSegmentator for Immediate Medical Image Segmentation and 3D Reconstruction | 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 Method Article Instant3D: A User-Friendly GUI Integrating TotalSegmentator for Immediate Medical Image Segmentation and 3D Reconstruction Satoru Muro, Takuya Ibara, Akimoto Nimura, Keiichi Akita This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8150723/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Background: Automatic segmentation is indispensable in medical imaging, yet advanced tools often remain confined to experts due to command-line complexity. TotalSegmentator delivers accurate multi-organ segmentation, but lacks accessibility for clinicians and educators. To overcome this barrier, we developed Instant3D, an open-source graphical user interface (GUI) that makes high-quality 3D reconstruction straightforward and intuitive. Objective: The purpose of this study was to introduce the Instant3D GUI and validate its performance. Methods: We developed Instant3D in Python using PyQt6. It accepts DICOM, NIfTI, or NRRD input. Users select regions of interest through a suggestion-enabled interface, and the tool automatically runs TotalSegmentator. Outputs include STL meshes for 3D visualization, CSV files with volumetric data, and per-slice SVG masks. Crucially, these SVG files are interoperable with SegRef3D, enabling interactive correction and refinement of automated results—combining the strengths of artificial intelligence segmentation and user-driven adjustment. Batch processing is supported for large datasets. We validated Instant3D by testing it on representative computed tomography (CT) and magnetic resonance imaging (MRI) datasets, including publicly available example data from the 3D Slicer Sample Data module. Results: Instant3D reliably produced 3D models from CT and MRI scans. STL meshes preserved anatomical fidelity, SVG masks facilitated slice-level review and editing in SegRef3D, and CSV outputs provided quantitative volume data. The GUI eliminated the need for command-line knowledge, lowering the entry barrier for diverse users across research and education. Conclusions: We developed Instant3D, an open-source and user-friendly platform that democratizes advanced segmentation by combining automation with practical usability. It provides a seamless GUI, bridging advanced automatic segmentation with practical applications in research and development. Clinical Impact: Instant3D 3D reconstructions extend beyond visualization, offering immediate value for radiomics-driven quantitative research, virtual reality-based surgical simulation, 3D printing for surgical planning and patient education, and glasses-free 3D display teaching tools. Nuclear Medicine & Medical Imaging Automatic segmentation 3D reconstruction Medical imaging Graphical user interface (GUI) Radiomics 3D printing Figures Figure 1 Figure 2 Figure 3 Highlights Key Finding: We developed Instant3D, an open-source and user-friendly platform that combines intuitive usability with powerful batch processing capabilities. It reliably produced 3D models from CT and MRI scans. The GUI eliminated the need for command-line knowledge, lowering the entry barrier for diverse users. Importance of the Key Finding: Instant3D represents a practical bridge between automated segmentation and real-world applications. Its 3D reconstructions can serve as versatile resources for a range of medical applications. BACKGROUND Automatic segmentation is indispensable in medical imaging, supporting clinical research, education, and surgical simulation applications. Recent advances such as TotalSegmentator provide accurate multi-organ segmentation for computed tomography (CT) and magnetic resonance imaging (MRI) data [ 1 – 5 ], yet their use often requires command-line expertise. This presents a substantial barrier for clinicians, educators, and students who lack programming experience. Graphical platforms such as 3D Slicer and OsiriX/OsiriX MD have become well-established solutions for image visualization and segmentation. 3D Slicer provides a suite of manual, semi-automatic, and artificial intelligence-assisted tools, and a dedicated extension allows the integration of TotalSegmentator ( https://github.com/lassoan/SlicerTotalSegmentator ) [ 6 , 7 ]. However, its complex interface and extensive module system may overwhelm non-expert users, and the extension is not optimized for streamlined batch processing or rapid generation of STL outputs. In practice, obtaining a simple 3D mesh often requires navigating multiple modules and performing several export steps, making routine use cumbersome in research and teaching environments. OsiriX/OsiriX MD, a popular DICOM viewer with plugin support, also offers automatic segmentation via a TotalSegmentator plugin ( https://www.osirix-viewer.com/osirix_plugins/TotalSegmentator/html/index.html ); however, it is limited to macOS and requires a paid license for clinical-grade use. To address these limitations, we developed Instant3D, an open-source graphical user interface (GUI) designed for streamlined workflows. Instant3D emphasizes intuitive region of interest (ROI) selection, one-click multi-format export (STL, SVG, and CSV), and interoperability with SegRef3D for interactive refinement [ 8 , 9 ]. Therefore, it may bridge the gap between automated segmentation and practical application in clinical and educational contexts. The aim of this study was to introduce the Instant3D GUI and validate its performance. METHODS Software Architecture and Distribution Instant3D was developed in Python (version 3.12) using the PyQt6 framework for the GUI. Core libraries include nibabel and pydicom for image handling, SimpleITK for preprocessing, and trimesh for mesh processing. The application is packaged as a standalone executable via PyInstaller and distributed through GitHub ( https://github.com/SatoruMuro/Instant3D ), enabling Windows users to run the program without setting up a Python environment. Users must install TotalSegmentator separately (pip install TotalSegmentator; totalsegmentator --download_model), after which Instant3D automatically calls the backend. Core Workflow (Basic Functions) Instant3D was designed around a simple three-step workflow (Fig. 1 ): data import, ROI selection, and execution. Regarding, data import, it supports DICOM folders, NIfTI, and NRRD formats. Input is automatically converted to NIfTI if needed. ROI selection involves a suggestion-enabled interface with alias recognition. Multiple ROIs can be added sequentially using the Add ROI function. Regarding execution, with a single button press, Instant3D runs TotalSegmentator and generates an STL mesh by default. Files are named consistently and saved in organized directories. Advanced Options (Detailed Functions) Instant3D has numerous advanced options, these include: Batch processing: Sequential processing of multiple input datasets. Imaging modality: Toggle between CT and MRI modes. Segmentation task selection: Choose among available TotalSegmentator subtasks. Multiple ROI selection: Process several anatomical structures simultaneously. Plane specification: Select axial, coronal, or sagittal orientation. Slice order and flips: Reverse slice order, flip left/right, or flip up/down. Performance settings: Force central processing unit execution or enable the “Fast” 3 mm model. Mesh smoothing: Adjustable smoothing iterations (default = 10). Output options: Optionally export per-slice SVG masks (compatible with SegRef3D [ 8 , 9 ] [ https://github.com/SatoruMuro/SAM2GUIfor3Drecon ]) and volumetric CSV files by enabling the corresponding checkboxes. ROI/task search utility: Built-in searchable list for confirming supported ROIs and tasks. By combining a streamlined default workflow with optional advanced adjustments, Instant3D ensures accessibility for non-technical users while providing flexibility for expert use. Furthermore, interoperability with SegRef3D extends functionality beyond automatic segmentation by enabling interactive refinement when necessary. Instant3D Validation Instant3D was tested on representative CT and MRI datasets, including publicly available example data from the 3D Slicer Sample Data module ( https://www.slicer.org ). RESULTS Output Formats The software generated three types of expected output formats: STL meshes, SVG masks, and CSV files. STL meshes comprised 3D models of selected ROIs produced with anatomical fidelity sufficient for visualization and downstream use (Fig. 2 ). When enabled, per-slice segmentation masks were generated in SVG format. These files were confirmed to be directly editable in SegRef3D, allowing interactive refinement of automatically segmented boundaries (Fig. 3 ). Optional volumetric data were exported as CSV files. Workflow Efficiency Using the default workflow, STL meshes could be generated immediately after data import and ROI selection once the segmentation was initiated with the Run button. Optional advanced settings—including batch processing, modality and task selection, and output toggles—functioned as intended, and provided additional flexibility without affecting stability. Functionality and Platform Validation In all cases, the program successfully executed TotalSegmentator through the GUI, producing segmentation results without requiring manual command-line interaction. The application consistently handled both DICOM folder inputs and pre-converted NIfTI or NRRD files. Regarding platform validation, the executable distribution was confirmed to operate on Windows 10/11 systems, with TotalSegmentator installed in a standard Python environment. No additional dependencies were required beyond the backend installation. DISCUSSION Instant3D provides an open-source, user-friendly GUI that bridges advanced automatic segmentation and practical application in research and education. By simplifying data import, ROI selection, and STL mesh generation through a streamlined workflow, the tool enables broader adoption of TotalSegmentator without requiring programming expertise. Optional outputs, including SVG masks and CSV volume data, extend its functionality and maintain interoperability with SegRef3D for interactive refinement. Existing tools such as 3D Slicer are powerful for multimodal segmentation and surgical planning but typically require several modules and manual export steps, making STL generation cumbersome for non-technical users [ 10 , 11 ]. OsiriX/OsiriX MD offers similar capabilities but is limited to macOS and paid licensing [ 10 ]. Deep-learning frameworks including MONAI Label and recent 3D CNN architectures [ 12 ], as well as U-Net-based pipelines for 3D tumor modeling [ 13 ], achieve high accuracy but generally demand programming skills and GPU configuration. Broader 3D reconstruction surveys also note that most vision- or artificial intelligence-based methods require complex preprocessing and parameter tuning [ 14 ]. Instant3D integrates TotalSegmentator into a single open-source GUI with one-click STL export and SegRef3D interoperability [ 8 , 9 ], lowering technical barriers and enabling immediate, reproducible 3D reconstruction without command-line operations. In radiomics research, statistical and machine learning-based analyses of a wide variety of features extracted from medical images have been increasingly used to improve diagnostic accuracy, predict prognosis, and assess therapeutic outcomes [ 15 , 16 ]. Among these, radiomics analyses based on 3D surface or volumetric data of entire organs or lesions require precise segmentation as a critical preprocessing step, which has long been a major bottleneck in research [ 17 , 18 ]. Traditionally, manual contour tracing or semi-automated methods have been commonly employed, but these are time consuming and have reproducibility limitations. Instant3D substantially streamlines this process by enabling high-accuracy automatic segmentation using TotalSegmentator directly within a GUI and by providing immediate output in STL and CSV formats, including volumetric data [ 4 , 6 ]. Moreover, the ability to revise and share slice-based SVG masks in SegRef3D facilitates cross-institutional collaboration and data quality improvement [ 8 , 9 ]. Collectively, these features position Instant3D as a foundational tool for enhancing the reproducibility and scalability of 3D radiomics research. The primary strengths of Instant3D lie in its ease of use and batch processing capability. Previously, TotalSegmentator required command-line operation, which posed a steep learning curve for users without programming experience [ 6 , 7 ]. In contrast, Instant3D runs entirely through a GUI, allowing physicians, dentists, researchers, and students to perform high-quality segmentation and 3D reconstruction without any coding skills. Furthermore, its batch processing function reproduces the efficiency of command-line workflows within an intuitive GUI environment. Conventional DICOM viewers are designed to handle one patient’s data at a time, focusing on detailed image reading. Even software equipped with 3D reconstruction tools typically process cases individually. Instant3D, however, enables organ-specific batch output of 3D meshes, contour data, and volumetric measurements from multiple CT datasets simultaneously. This functionality offers a major advantage for radiomics research, where extracting morphological information quantitatively from large image datasets is essential. Beyond radiomics, Instant3D can serve as a foundational tool for developing software for mixed reality or virtual reality/augmented reality-based surgical simulation and glasses-free 3D displays [ 12 , 19 – 23 ], generating training data for machine-learning models, and creating 3D-printed models for surgical rehearsal [ 23 ]. In summary, Instant3D represents a flexible and accessible foundational platform bridging automated segmentation with diverse applications in research and development. This study has some limitations. First, the validation was confined to representative datasets and may therefore not encompass the full diversity of clinical imaging conditions. Second, a comparative performance analysis with other segmentation tools was not undertaken. Finally, the segmentable structure scope was constrained by the TotalSegmentator framework, and regulatory or clinical validations have not yet been performed. CONCLUSIONS We developed Instant3D, an open-source and user-friendly platform that combines intuitive usability with powerful batch processing capabilities. This tool enables broader adoption of TotalSegmentator without requiring programming expertise. Collectively, its features position it as a foundational tool for enhancing the reproducibility and scalability of 3D radiomics research. The 3D reconstructions generated by Instant3D are not just limited to visualization, they can serve as versatile resources for a range of applications, including radiomics and quantitative imaging research, machine-learning dataset generation, virtual or mixed reality-based model development, 3D printing for experimental prototyping or simulation, and visualization on glasses-free 3D displays. By lowering technical barriers while enabling scalable and data-driven analysis, Instant3D provides a seamless GUI, representing a practical bridge between automated segmentation and real-world research and development applications. References Isensee F, Jaeger PF, Kohl SAA, Petersen J, Maier-Hein KH (2021) nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation. Nat Methods 18(2):203–211. 10.1038/s41592-020-01008-z [EPub] 2020 Dec 7. PMID: 33288961 Diaz-Pinto A, Alle S, Nath V et al (2024) MONAI Label: A framework for AI-assisted interactive labeling of 3D medical images. Med Image Anal 95:103207. 10.1016/j.media.2024.103207 [EPub]. PMID: 38776843 Gao Y, Jiang Y, Peng Y, Yuan F, Zhang X, Wang J (2025) Medical image segmentation: A comprehensive review of deep learning-based methods. Tomography 11(5):52. 10.3390/tomography11050052, PMID: 40423254, PMCID: PMC12115501 Sebro R, Mongan J (2023) TotalSegmentator: A gift to the biomedical imaging community. Radiol Artif Intell 5(5):e230235. 10.1148/ryai.230235, PMID: 37795136, PMCID: PMC10546367 Lindholz M, Ruppel R, Schulze-Weddige S et al (2025) Analyzing the TotalSegmentator for facial feature removal in head CT scans. Radiography (Lond) ;31(1):372–8. doi: 10.1016/j.radi.2024.12.018 [EPub]. PMID: 39754865 Wasserthal J, Breit HC, Meyer MT et al (2023) TotalSegmentator: Robust segmentation of 104 anatomic structures in CT images. Radiol Artif Intell 5(5):e230024. 10.1148/ryai.230024, PMID: 37795137, PMCID: PMC10546353 Reisert M, Küstner T, Walter A et al (2025) TotalSegmentator MRI: Robust sequence-independent segmentation of multiple anatomic structures in MRI. Radiology ;314(2):e241613. 10.1148/radiol.241613 . PMID: 39964271 Muro S, Ibara T, Nimura A, Akita K (2025) Seg and ref: A newly developed toolset for artificial intelligence-powered segmentation and interactive refinement for labor-saving three-dimensional reconstruction. Microscopy (Oxf) . :dfaf015. 10.1093/jmicro/dfaf015 . Epub ahead of print. PMID: 40037547 Muro S, Ibara T, Nimura A, Akita K (2025) SegRef3D: A versatile open-source platform for artificial intelligence-assisted segmentation and three-dimensional reconstruction in morphological research. SSRN. www.ssrn.com/abstract=5547238. Published Sep 26, 2025. Accessed Nov 10. 10.2139/ssrn.5547238 Virzì A, Muller CO, Marret JB et al (2020) Comprehensive review of 3D segmentation software tools for MRI usable for pelvic surgery planning. J Digit Imaging 33(1):99–110. 10.1007/s10278-019-00239-7, PMID: 31236743, PMCID: PMC7064712 Kimura T, Takiguchi K, Tsukita S et al (2025) Development of anatomically accurate digital organ models for surgical simulation and training. PLoS ONE 20(4):e0320816. 10.1371/journal.pone.0320816, PMID: 40203219, PMCID: PMC11981654 Ilesanmi AE, Ilesanmi TO, Ajayi BO (2024) Reviewing 3D convolutional neural network approaches for medical image segmentation. Heliyon 10(6):e27398. 10.1016/j.heliyon.2024.e27398, PMID: 38496891, PMCID: PMC10944240 Wang K, Han Y, Ye Y et al (2025) Mixed reality infrastructure based on deep learning medical image segmentation and 3D visualization for bone tumors using DCU-Net. J Bone Oncol 50:100654. 10.1016/j.jbo.2024.100654, PMID: 39839577, PMCID: PMC11745962 Zhou L, Wu G, Zuo Y, Chen X, Hu H (2024) A comprehensive review of vision-based 3D reconstruction methods. Sens (Basel) 24(7):2314. 10.3390/s24072314, PMID: 38610525, PMCID: PMC11014007 Lambin P, Rios-Velazquez E, Leijenaar R et al (2012) Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer 48(4):441–446 PMID: 22257792, PMCID: PMC4533986 Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278(2):563–567. 10.1148/radiol.2015151169, PMID: 26579733, PMCID: PMC4734157 Aerts H, Velazquez E, Leijenaar R et al (2014) Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun ;5(1):4006. doi: 400610.1038/ncomms5006, PMCID: PMC5784306 Traverso A, Wee L, Dekker A, Gillies R (2018) Repeatability and reproducibility of radiomic features: a systematic review. Int J Radiat Oncol Biol Phys 102(4):1143–1158. 10.1016/j.ijrobp.2018.05.053, PMID: 30170872, PMCID: PMC6690209 Meidai K, Aihara T, Yamanaka N (2024) Enhancing liver surgery and transplantation: the role of 3D printing and virtual reality. Artif Intell Surg 4(3):180–186. 10.20517/ais.2024.07 Chen-Yoshikawa TF (2024) Evolution of three-dimensional computed tomography imaging in thoracic surgery. Cancers (Basel) 16(11):2161 : 10.3390/cancers16112161, PMID: 38893279, PMCID: PMC11172068 Naito S, Kajiwara M, Nakashima R, Sasaki T, Hasegawa S (2023) Application of extended reality (virtual reality and mixed reality) technology in laparoscopic liver resections. Cureus 15(9):e44520. 10.7759/cureus.44520, PMID: 37790042, PMCID: PMC10544840 Satoru M, Miyosawa K, Yamaguchi K et al (2025) Evaluation of glasses-free 3D anatomy learning materials through a randomized control study with a puzzle‐like method. Anat Sci Edu 18(7):684–696. 10.1002/ase.70063, PMID: 40452128, PMCID: PMC12222575 Ueda H, Inami S, Moridaira H et al (2025) The usefulness and potential of high-fidelity three-dimensional models in spine surgery training: Cross-sectional empirical study. BMC Med Educ 25(1):387. 10.1186/s12909-025-06936-y, PMID: 40089703, PMCID: PMC11910854 Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 1 posted 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-8150723\",\"acceptedTermsAndConditions\":true,\"allowDirectSubmit\":true,\"archivedVersions\":[],\"articleType\":\"Method Article\",\"associatedPublications\":[],\"authors\":[{\"id\":547260380,\"identity\":\"c567961a-d2fd-4591-951b-7f7fe28aaacc\",\"order_by\":0,\"name\":\"Satoru Muro\",\"email\":\"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAzUlEQVRIiWNgGAWjYNACGyBmb2Bg4AHzDhCjJQ2IeQ6TrEUiGaaFANCdkfvwAUOCXR7/zPdHN7xhsJNnYDyL3xqzG+nGBgwJycUSt5PZbs5hSDZsYDiXQEBLGpsE4w/mxAaglts8DMxA5WcMCGthSKhPnH/zMEhLPdFaDiduuMEM0nKYCC1nnjEbJCQcT9x4Jtns5hyD44ZtBP1yPI3xwYeE6sR5xw8+u/GmolqeX4JAiIEBwlSgk9gkzhDWgQb4e0jWMgpGwSgYBcMbAABod0WBISj6QgAAAABJRU5ErkJggg==\",\"orcid\":\"\",\"institution\":\"\",\"correspondingAuthor\":true,\"prefix\":\"\",\"firstName\":\"Satoru\",\"middleName\":\"\",\"lastName\":\"Muro\",\"suffix\":\"\"},{\"id\":547260381,\"identity\":\"bf7171e5-3325-433d-98de-b8839e024bd3\",\"order_by\":1,\"name\":\"Takuya Ibara\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Takuya\",\"middleName\":\"\",\"lastName\":\"Ibara\",\"suffix\":\"\"},{\"id\":547260382,\"identity\":\"251b4a4f-2d5c-4f45-b281-2b4ddbd3c70f\",\"order_by\":2,\"name\":\"Akimoto Nimura\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Akimoto\",\"middleName\":\"\",\"lastName\":\"Nimura\",\"suffix\":\"\"},{\"id\":547260383,\"identity\":\"6da9a494-bed8-4248-a458-90b97927eb10\",\"order_by\":3,\"name\":\"Keiichi Akita\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Keiichi\",\"middleName\":\"\",\"lastName\":\"Akita\",\"suffix\":\"\"}],\"badges\":[],\"createdAt\":\"2025-11-19 04:25:00\",\"currentVersionCode\":1,\"declarations\":{\"humanSubjects\":false,\"vertebrateSubjects\":false,\"conflictsOfInterestStatement\":false,\"humanSubjectEthicalGuidelines\":false,\"humanSubjectConsent\":false,\"humanSubjectClinicalTrial\":false,\"humanSubjectCaseReport\":false,\"vertebrateSubjectEthicalGuidelines\":false},\"doi\":\"10.21203/rs.3.rs-8150723/v1\",\"doiUrl\":\"https://doi.org/10.21203/rs.3.rs-8150723/v1\",\"draftVersion\":[],\"editorialEvents\":[],\"editorialNote\":\"\",\"failedWorkflow\":false,\"files\":[{\"id\":96367622,\"identity\":\"5bf39910-b333-417b-bc5f-9674425f6589\",\"added_by\":\"auto\",\"created_at\":\"2025-11-20 10:13:38\",\"extension\":\"docx\",\"order_by\":0,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":2670948,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"Instant3Dmanuscriptv07.docx\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8150723/v1/b322f54796566f5ca6870eb2.docx\"},{\"id\":96355727,\"identity\":\"805cfcb1-cb11-480e-80fe-1916356c3f49\",\"added_by\":\"auto\",\"created_at\":\"2025-11-20 08:19:13\",\"extension\":\"json\",\"order_by\":1,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":342,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"rs8150723.json\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8150723/v1/8adc3682dcb53812307531d4.json\"},{\"id\":96355728,\"identity\":\"ebef17ee-f55c-47ff-aeb2-c23a614ad3ed\",\"added_by\":\"auto\",\"created_at\":\"2025-11-20 08:19:13\",\"extension\":\"xml\",\"order_by\":2,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":57004,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"rs81507230enriched.xml\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8150723/v1/c0ebef8bd625b3ed4279c99f.xml\"},{\"id\":96355732,\"identity\":\"99c70fb8-52a3-4e75-81d9-5cadc6922638\",\"added_by\":\"auto\",\"created_at\":\"2025-11-20 08:19:13\",\"extension\":\"jpeg\",\"order_by\":3,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":436826,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"floatimage1.jpeg\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8150723/v1/e15e4be97ecf7808eb15a430.jpeg\"},{\"id\":96355734,\"identity\":\"c9ad14c0-4c46-493f-be52-a725a8660d54\",\"added_by\":\"auto\",\"created_at\":\"2025-11-20 08:19:13\",\"extension\":\"jpeg\",\"order_by\":4,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":1521060,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"floatimage2.jpeg\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8150723/v1/4c7aa1ae998400dc313c5064.jpeg\"},{\"id\":96355738,\"identity\":\"c40259b4-df56-4172-bedb-bf0dfcc77276\",\"added_by\":\"auto\",\"created_at\":\"2025-11-20 08:19:16\",\"extension\":\"jpeg\",\"order_by\":5,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":670842,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"floatimage3.jpeg\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8150723/v1/43bfd09034df210629670314.jpeg\"},{\"id\":96355739,\"identity\":\"52420a2e-27bc-4a30-af92-edd82f5e86d3\",\"added_by\":\"auto\",\"created_at\":\"2025-11-20 08:19:19\",\"extension\":\"png\",\"order_by\":6,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":52265,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"Onlinefloatimage1.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8150723/v1/426faa611a529b24cd566c22.png\"},{\"id\":96367048,\"identity\":\"110558f1-86d2-4925-ae79-3b44067dfe75\",\"added_by\":\"auto\",\"created_at\":\"2025-11-20 10:12:08\",\"extension\":\"png\",\"order_by\":7,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":163023,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"Onlinefloatimage2.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8150723/v1/28b566a698812514c1b96086.png\"},{\"id\":96355730,\"identity\":\"55765190-9099-4ad4-b7f5-bc1c076b4cd9\",\"added_by\":\"auto\",\"created_at\":\"2025-11-20 08:19:13\",\"extension\":\"png\",\"order_by\":8,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":58604,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"Onlinefloatimage3.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8150723/v1/5856b6d1ba32b91698903866.png\"},{\"id\":96355736,\"identity\":\"e5e316bf-f0d0-468e-8bc4-fcbc206d4d35\",\"added_by\":\"auto\",\"created_at\":\"2025-11-20 08:19:14\",\"extension\":\"xml\",\"order_by\":9,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":56462,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"rs81507230structuring.xml\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8150723/v1/a28339921f5f073e088fd178.xml\"},{\"id\":96367171,\"identity\":\"781299af-1dd7-44ca-b82b-c3c08586ee2e\",\"added_by\":\"auto\",\"created_at\":\"2025-11-20 10:12:15\",\"extension\":\"html\",\"order_by\":10,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":61550,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"earlyproof.html\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8150723/v1/d4bb3069a19cd3792e886b6f.html\"},{\"id\":96355740,\"identity\":\"0b0fede7-647c-426e-935c-6d7bea3ab0a4\",\"added_by\":\"auto\",\"created_at\":\"2025-11-20 08:19:20\",\"extension\":\"png\",\"order_by\":1,\"title\":\"Figure 1\",\"display\":\"\",\"copyAsset\":false,\"role\":\"figure\",\"size\":1292707,\"visible\":true,\"origin\":\"\",\"legend\":\"\\u003cp\\u003eInstant3D graphical user interface screenshot.\\u003c/p\\u003e\\n\\u003cp\\u003eRepresentative screenshot of the Instant3D graphical user interface (GUI). The region of interest (ROI) input field, Run button, and optional settings panel are visible, illustrating the simple three-step workflow and the intuitive, user-friendly design that facilitates efficient 3D reconstruction.\\u003c/p\\u003e\",\"description\":\"\",\"filename\":\"fig1.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8150723/v1/7eeb64fa431b2e7567644c39.png\"},{\"id\":96355735,\"identity\":\"2669c9af-82b0-44a5-ad0f-09712f77d66e\",\"added_by\":\"auto\",\"created_at\":\"2025-11-20 08:19:13\",\"extension\":\"png\",\"order_by\":2,\"title\":\"Figure 2\",\"display\":\"\",\"copyAsset\":false,\"role\":\"figure\",\"size\":10565692,\"visible\":true,\"origin\":\"\",\"legend\":\"\\u003cp\\u003eThree-dimensional STL models generated by Instant3D.\\u003c/p\\u003e\\n\\u003cp\\u003eExample of 3D-rendered STL models of the abdominal organs (A), brain structures (B), skull and teeth (C), and thoracic organs (D) generated by Instant3D. The images demonstrate the high anatomical fidelity of the reconstructed meshes and their suitability for downstream applications such as surgical planning, education, and 3D printing. Instant3D itself does not contain an STL viewer; the models were displayed with 3D Slicer.\\u003c/p\\u003e\",\"description\":\"\",\"filename\":\"fig2.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8150723/v1/511b6530e28ae661c497599a.png\"},{\"id\":96355731,\"identity\":\"4549b81e-e3dc-469f-a927-4cb1c516bea0\",\"added_by\":\"auto\",\"created_at\":\"2025-11-20 08:19:13\",\"extension\":\"png\",\"order_by\":3,\"title\":\"Figure 3\",\"display\":\"\",\"copyAsset\":false,\"role\":\"figure\",\"size\":2542643,\"visible\":true,\"origin\":\"\",\"legend\":\"\\u003cp\\u003eCompatibility with SegRef3D for interactive refinement.\\u003c/p\\u003e\\n\\u003cp\\u003eRepresentative slice image with an overlaid SVG mask exported from Instant3D, demonstrating seamless compatibility with SegRef3D for slice-by-slice mask editing and interactive refinement. This interoperability enables iterative improvements of the segmentation prior to final 3D reconstruction. After mask refinement, SegRef3D allows direct export of the finalized data as STL models.\\u003c/p\\u003e\",\"description\":\"\",\"filename\":\"fig3.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8150723/v1/28ea3e27d21aba165773cd26.png\"},{\"id\":96369560,\"identity\":\"09bc202d-b395-472b-91cb-dbb528f0c7a0\",\"added_by\":\"auto\",\"created_at\":\"2025-11-20 10:21:18\",\"extension\":\"pdf\",\"order_by\":0,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"manuscript-pdf\",\"size\":13723616,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"manuscript.pdf\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8150723/v1/82b1104f-56c3-4459-850c-ceba468a14e9.pdf\"}],\"financialInterests\":\"The authors declare no competing interests.\",\"formattedTitle\":\"\\u003cp\\u003eInstant3D: A User-Friendly GUI Integrating TotalSegmentator for Immediate Medical Image Segmentation and 3D Reconstruction\\u003c/p\\u003e\",\"fulltext\":[{\"header\":\"Highlights\",\"content\":\"\\u003cp\\u003e\\u003cstrong\\u003eKey Finding:\\u0026nbsp;\\u003c/strong\\u003e\\u003c/p\\u003e\\n\\u003cp\\u003eWe developed Instant3D, an open-source and user-friendly platform that combines intuitive usability with powerful batch processing capabilities. It reliably produced 3D models from CT and MRI scans. The GUI eliminated the need for command-line knowledge, lowering the entry barrier for diverse users.\\u003c/p\\u003e\\n\\u003cp\\u003e\\u003cstrong\\u003eImportance of the Key Finding:\\u003c/strong\\u003e\\u003c/p\\u003e\\n\\u003cp\\u003eInstant3D represents a practical bridge between automated segmentation and real-world applications. Its 3D reconstructions can serve as versatile resources for a range of medical applications.\\u003c/p\\u003e\"},{\"header\":\"BACKGROUND\",\"content\":\"\\u003cp\\u003eAutomatic segmentation is indispensable in medical imaging, supporting clinical research, education, and surgical simulation applications. Recent advances such as TotalSegmentator provide accurate multi-organ segmentation for computed tomography (CT) and magnetic resonance imaging (MRI) data [\\u003cspan additionalcitationids=\\\"CR2 CR3 CR4\\\" citationid=\\\"CR1\\\" class=\\\"CitationRef\\\"\\u003e1\\u003c/span\\u003e\\u0026ndash;\\u003cspan citationid=\\\"CR5\\\" class=\\\"CitationRef\\\"\\u003e5\\u003c/span\\u003e], yet their use often requires command-line expertise. This presents a substantial barrier for clinicians, educators, and students who lack programming experience.\\u003c/p\\u003e\\u003cp\\u003eGraphical platforms such as 3D Slicer and OsiriX/OsiriX MD have become well-established solutions for image visualization and segmentation. 3D Slicer provides a suite of manual, semi-automatic, and artificial intelligence-assisted tools, and a dedicated extension allows the integration of TotalSegmentator (\\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003ehttps://github.com/lassoan/SlicerTotalSegmentator\\u003c/span\\u003e\\u003cspan address=\\\"https://github.com/lassoan/SlicerTotalSegmentator\\\" targettype=\\\"URL\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e) [\\u003cspan citationid=\\\"CR6\\\" class=\\\"CitationRef\\\"\\u003e6\\u003c/span\\u003e, \\u003cspan citationid=\\\"CR7\\\" class=\\\"CitationRef\\\"\\u003e7\\u003c/span\\u003e]. However, its complex interface and extensive module system may overwhelm non-expert users, and the extension is not optimized for streamlined batch processing or rapid generation of STL outputs. In practice, obtaining a simple 3D mesh often requires navigating multiple modules and performing several export steps, making routine use cumbersome in research and teaching environments. OsiriX/OsiriX MD, a popular DICOM viewer with plugin support, also offers automatic segmentation via a TotalSegmentator plugin (\\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003ehttps://www.osirix-viewer.com/osirix_plugins/TotalSegmentator/html/index.html\\u003c/span\\u003e\\u003cspan address=\\\"https://www.osirix-viewer.com/osirix_plugins/TotalSegmentator/html/index.html\\\" targettype=\\\"URL\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e); however, it is limited to macOS and requires a paid license for clinical-grade use.\\u003c/p\\u003e\\u003cp\\u003eTo address these limitations, we developed Instant3D, an open-source graphical user interface (GUI) designed for streamlined workflows. Instant3D emphasizes intuitive region of interest (ROI) selection, one-click multi-format export (STL, SVG, and CSV), and interoperability with SegRef3D for interactive refinement [\\u003cspan citationid=\\\"CR8\\\" class=\\\"CitationRef\\\"\\u003e8\\u003c/span\\u003e, \\u003cspan citationid=\\\"CR9\\\" class=\\\"CitationRef\\\"\\u003e9\\u003c/span\\u003e]. Therefore, it may bridge the gap between automated segmentation and practical application in clinical and educational contexts. The aim of this study was to introduce the Instant3D GUI and validate its performance.\\u003c/p\\u003e\"},{\"header\":\"METHODS\",\"content\":\"\\u003cdiv id=\\\"Sec3\\\" class=\\\"Section2\\\"\\u003e\\u003ch2\\u003eSoftware Architecture and Distribution\\u003c/h2\\u003e\\u003cp\\u003eInstant3D was developed in Python (version 3.12) using the PyQt6 framework for the GUI. Core libraries include nibabel and pydicom for image handling, SimpleITK for preprocessing, and trimesh for mesh processing. The application is packaged as a standalone executable via PyInstaller and distributed through GitHub (\\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003ehttps://github.com/SatoruMuro/Instant3D\\u003c/span\\u003e\\u003cspan address=\\\"https://github.com/SatoruMuro/Instant3D\\\" targettype=\\\"URL\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e), enabling Windows users to run the program without setting up a Python environment. Users must install TotalSegmentator separately (pip install TotalSegmentator; totalsegmentator --download_model), after which Instant3D automatically calls the backend.\\u003c/p\\u003e\\u003c/div\\u003e\\n\\u003ch3\\u003eCore Workflow (Basic Functions)\\u003c/h3\\u003e\\n\\u003cp\\u003eInstant3D was designed around a simple three-step workflow (Fig.\\u0026nbsp;\\u003cspan refid=\\\"Fig1\\\" class=\\\"InternalRef\\\"\\u003e1\\u003c/span\\u003e): data import, ROI selection, and execution. Regarding, data import, it supports DICOM folders, NIfTI, and NRRD formats. Input is automatically converted to NIfTI if needed. ROI selection involves a suggestion-enabled interface with alias recognition. Multiple ROIs can be added sequentially using the Add ROI function. Regarding execution, with a single button press, Instant3D runs TotalSegmentator and generates an STL mesh by default. Files are named consistently and saved in organized directories.\\u003c/p\\u003e\\u003cp\\u003e\\u003c/p\\u003e\\n\\u003ch3\\u003eAdvanced Options (Detailed Functions)\\u003c/h3\\u003e\\n\\u003cp\\u003eInstant3D has numerous advanced options, these include:\\u003c/p\\u003e\\u003cp\\u003e\\u003cul\\u003e\\u003cli\\u003e\\u003cp\\u003eBatch processing: Sequential processing of multiple input datasets.\\u003c/p\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cp\\u003eImaging modality: Toggle between CT and MRI modes.\\u003c/p\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cp\\u003eSegmentation task selection: Choose among available TotalSegmentator subtasks.\\u003c/p\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cp\\u003eMultiple ROI selection: Process several anatomical structures simultaneously.\\u003c/p\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cp\\u003ePlane specification: Select axial, coronal, or sagittal orientation.\\u003c/p\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cp\\u003eSlice order and flips: Reverse slice order, flip left/right, or flip up/down.\\u003c/p\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cp\\u003ePerformance settings: Force central processing unit execution or enable the \\u0026ldquo;Fast\\u0026rdquo; 3 mm model.\\u003c/p\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cp\\u003eMesh smoothing: Adjustable smoothing iterations (default\\u0026thinsp;=\\u0026thinsp;10).\\u003c/p\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cp\\u003eOutput options: Optionally export per-slice SVG masks (compatible with SegRef3D [\\u003cspan citationid=\\\"CR8\\\" class=\\\"CitationRef\\\"\\u003e8\\u003c/span\\u003e, \\u003cspan citationid=\\\"CR9\\\" class=\\\"CitationRef\\\"\\u003e9\\u003c/span\\u003e] [\\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003ehttps://github.com/SatoruMuro/SAM2GUIfor3Drecon\\u003c/span\\u003e\\u003cspan address=\\\"https://github.com/SatoruMuro/SAM2GUIfor3Drecon\\\" targettype=\\\"URL\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e]) and volumetric CSV files by enabling the corresponding checkboxes.\\u003c/p\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cp\\u003eROI/task search utility: Built-in searchable list for confirming supported ROIs and tasks.\\u003c/p\\u003e\\u003c/li\\u003e\\u003c/ul\\u003e\\u003c/p\\u003e\\u003cp\\u003eBy combining a streamlined default workflow with optional advanced adjustments, Instant3D ensures accessibility for non-technical users while providing flexibility for expert use. Furthermore, interoperability with SegRef3D extends functionality beyond automatic segmentation by enabling interactive refinement when necessary.\\u003c/p\\u003e\\n\\u003ch3\\u003eInstant3D Validation\\u003c/h3\\u003e\\n\\u003cp\\u003eInstant3D was tested on representative CT and MRI datasets, including publicly available example data from the 3D Slicer Sample Data module (\\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003ehttps://www.slicer.org\\u003c/span\\u003e\\u003cspan address=\\\"https://www.slicer.org\\\" targettype=\\\"URL\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e).\\u003c/p\\u003e\"},{\"header\":\"RESULTS\",\"content\":\"\\u003cdiv id=\\\"Sec8\\\" class=\\\"Section2\\\"\\u003e\\u003ch2\\u003eOutput Formats\\u003c/h2\\u003e\\u003cp\\u003eThe software generated three types of expected output formats: STL meshes, SVG masks, and CSV files. STL meshes comprised 3D models of selected ROIs produced with anatomical fidelity sufficient for visualization and downstream use (Fig.\\u0026nbsp;\\u003cspan refid=\\\"Fig2\\\" class=\\\"InternalRef\\\"\\u003e2\\u003c/span\\u003e). When enabled, per-slice segmentation masks were generated in SVG format. These files were confirmed to be directly editable in SegRef3D, allowing interactive refinement of automatically segmented boundaries (Fig.\\u0026nbsp;\\u003cspan refid=\\\"Fig3\\\" class=\\\"InternalRef\\\"\\u003e3\\u003c/span\\u003e). Optional volumetric data were exported as CSV files.\\u003c/p\\u003e\\u003cp\\u003e\\u003c/p\\u003e\\u003cp\\u003e\\u003c/p\\u003e\\u003c/div\\u003e\\n\\u003ch3\\u003eWorkflow Efficiency\\u003c/h3\\u003e\\n\\u003cp\\u003eUsing the default workflow, STL meshes could be generated immediately after data import and ROI selection once the segmentation was initiated with the Run button. Optional advanced settings\\u0026mdash;including batch processing, modality and task selection, and output toggles\\u0026mdash;functioned as intended, and provided additional flexibility without affecting stability.\\u003c/p\\u003e\\n\\u003ch3\\u003eFunctionality and Platform Validation\\u003c/h3\\u003e\\n\\u003cp\\u003eIn all cases, the program successfully executed TotalSegmentator through the GUI, producing segmentation results without requiring manual command-line interaction. The application consistently handled both DICOM folder inputs and pre-converted NIfTI or NRRD files.\\u003c/p\\u003e\\u003cp\\u003eRegarding platform validation, the executable distribution was confirmed to operate on Windows 10/11 systems, with TotalSegmentator installed in a standard Python environment. No additional dependencies were required beyond the backend installation.\\u003c/p\\u003e\"},{\"header\":\"DISCUSSION\",\"content\":\"\\u003cp\\u003eInstant3D provides an open-source, user-friendly GUI that bridges advanced automatic segmentation and practical application in research and education. By simplifying data import, ROI selection, and STL mesh generation through a streamlined workflow, the tool enables broader adoption of TotalSegmentator without requiring programming expertise. Optional outputs, including SVG masks and CSV volume data, extend its functionality and maintain interoperability with SegRef3D for interactive refinement.\\u003c/p\\u003e\\u003cp\\u003eExisting tools such as 3D Slicer are powerful for multimodal segmentation and surgical planning but typically require several modules and manual export steps, making STL generation cumbersome for non-technical users [\\u003cspan citationid=\\\"CR10\\\" class=\\\"CitationRef\\\"\\u003e10\\u003c/span\\u003e, \\u003cspan citationid=\\\"CR11\\\" class=\\\"CitationRef\\\"\\u003e11\\u003c/span\\u003e]. OsiriX/OsiriX MD offers similar capabilities but is limited to macOS and paid licensing [\\u003cspan citationid=\\\"CR10\\\" class=\\\"CitationRef\\\"\\u003e10\\u003c/span\\u003e]. Deep-learning frameworks including MONAI Label and recent 3D CNN architectures [\\u003cspan citationid=\\\"CR12\\\" class=\\\"CitationRef\\\"\\u003e12\\u003c/span\\u003e], as well as U-Net-based pipelines for 3D tumor modeling [\\u003cspan citationid=\\\"CR13\\\" class=\\\"CitationRef\\\"\\u003e13\\u003c/span\\u003e], achieve high accuracy but generally demand programming skills and GPU configuration. Broader 3D reconstruction surveys also note that most vision- or artificial intelligence-based methods require complex preprocessing and parameter tuning [\\u003cspan citationid=\\\"CR14\\\" class=\\\"CitationRef\\\"\\u003e14\\u003c/span\\u003e]. Instant3D integrates TotalSegmentator into a single open-source GUI with one-click STL export and SegRef3D interoperability [\\u003cspan citationid=\\\"CR8\\\" class=\\\"CitationRef\\\"\\u003e8\\u003c/span\\u003e, \\u003cspan citationid=\\\"CR9\\\" class=\\\"CitationRef\\\"\\u003e9\\u003c/span\\u003e], lowering technical barriers and enabling immediate, reproducible 3D reconstruction without command-line operations.\\u003c/p\\u003e\\u003cp\\u003eIn radiomics research, statistical and machine learning-based analyses of a wide variety of features extracted from medical images have been increasingly used to improve diagnostic accuracy, predict prognosis, and assess therapeutic outcomes [\\u003cspan citationid=\\\"CR15\\\" class=\\\"CitationRef\\\"\\u003e15\\u003c/span\\u003e, \\u003cspan citationid=\\\"CR16\\\" class=\\\"CitationRef\\\"\\u003e16\\u003c/span\\u003e]. Among these, radiomics analyses based on 3D surface or volumetric data of entire organs or lesions require precise segmentation as a critical preprocessing step, which has long been a major bottleneck in research [\\u003cspan citationid=\\\"CR17\\\" class=\\\"CitationRef\\\"\\u003e17\\u003c/span\\u003e, \\u003cspan citationid=\\\"CR18\\\" class=\\\"CitationRef\\\"\\u003e18\\u003c/span\\u003e]. Traditionally, manual contour tracing or semi-automated methods have been commonly employed, but these are time consuming and have reproducibility limitations. Instant3D substantially streamlines this process by enabling high-accuracy automatic segmentation using TotalSegmentator directly within a GUI and by providing immediate output in STL and CSV formats, including volumetric data [\\u003cspan citationid=\\\"CR4\\\" class=\\\"CitationRef\\\"\\u003e4\\u003c/span\\u003e, \\u003cspan citationid=\\\"CR6\\\" class=\\\"CitationRef\\\"\\u003e6\\u003c/span\\u003e]. Moreover, the ability to revise and share slice-based SVG masks in SegRef3D facilitates cross-institutional collaboration and data quality improvement [\\u003cspan citationid=\\\"CR8\\\" class=\\\"CitationRef\\\"\\u003e8\\u003c/span\\u003e, \\u003cspan citationid=\\\"CR9\\\" class=\\\"CitationRef\\\"\\u003e9\\u003c/span\\u003e]. Collectively, these features position Instant3D as a foundational tool for enhancing the reproducibility and scalability of 3D radiomics research.\\u003c/p\\u003e\\u003cp\\u003eThe primary strengths of Instant3D lie in its ease of use and batch processing capability. Previously, TotalSegmentator required command-line operation, which posed a steep learning curve for users without programming experience [\\u003cspan citationid=\\\"CR6\\\" class=\\\"CitationRef\\\"\\u003e6\\u003c/span\\u003e, \\u003cspan citationid=\\\"CR7\\\" class=\\\"CitationRef\\\"\\u003e7\\u003c/span\\u003e]. In contrast, Instant3D runs entirely through a GUI, allowing physicians, dentists, researchers, and students to perform high-quality segmentation and 3D reconstruction without any coding skills. Furthermore, its batch processing function reproduces the efficiency of command-line workflows within an intuitive GUI environment. Conventional DICOM viewers are designed to handle one patient\\u0026rsquo;s data at a time, focusing on detailed image reading. Even software equipped with 3D reconstruction tools typically process cases individually. Instant3D, however, enables organ-specific batch output of 3D meshes, contour data, and volumetric measurements from multiple CT datasets simultaneously. This functionality offers a major advantage for radiomics research, where extracting morphological information quantitatively from large image datasets is essential. Beyond radiomics, Instant3D can serve as a foundational tool for developing software for mixed reality or virtual reality/augmented reality-based surgical simulation and glasses-free 3D displays [\\u003cspan citationid=\\\"CR12\\\" class=\\\"CitationRef\\\"\\u003e12\\u003c/span\\u003e, \\u003cspan additionalcitationids=\\\"CR20 CR21 CR22\\\" citationid=\\\"CR19\\\" class=\\\"CitationRef\\\"\\u003e19\\u003c/span\\u003e\\u0026ndash;\\u003cspan citationid=\\\"CR23\\\" class=\\\"CitationRef\\\"\\u003e23\\u003c/span\\u003e], generating training data for machine-learning models, and creating 3D-printed models for surgical rehearsal [\\u003cspan citationid=\\\"CR23\\\" class=\\\"CitationRef\\\"\\u003e23\\u003c/span\\u003e]. In summary, Instant3D represents a flexible and accessible foundational platform bridging automated segmentation with diverse applications in research and development.\\u003c/p\\u003e\\u003cp\\u003eThis study has some limitations. First, the validation was confined to representative datasets and may therefore not encompass the full diversity of clinical imaging conditions. Second, a comparative performance analysis with other segmentation tools was not undertaken. Finally, the segmentable structure scope was constrained by the TotalSegmentator framework, and regulatory or clinical validations have not yet been performed.\\u003c/p\\u003e\"},{\"header\":\"CONCLUSIONS\",\"content\":\"\\u003cp\\u003eWe developed Instant3D, an open-source and user-friendly platform that combines intuitive usability with powerful batch processing capabilities. This tool enables broader adoption of TotalSegmentator without requiring programming expertise. Collectively, its features position it as a foundational tool for enhancing the reproducibility and scalability of 3D radiomics research. The 3D reconstructions generated by Instant3D are not just limited to visualization, they can serve as versatile resources for a range of applications, including radiomics and quantitative imaging research, machine-learning dataset generation, virtual or mixed reality-based model development, 3D printing for experimental prototyping or simulation, and visualization on glasses-free 3D displays. By lowering technical barriers while enabling scalable and data-driven analysis, Instant3D provides a seamless GUI, representing a practical bridge between automated segmentation and real-world research and development applications.\\u003c/p\\u003e\"},{\"header\":\"References\",\"content\":\"\\u003col\\u003e\\u003cli\\u003e\\u003cspan\\u003eIsensee F, Jaeger PF, Kohl SAA, Petersen J, Maier-Hein KH (2021) nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation. Nat Methods 18(2):203\\u0026ndash;211. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1038/s41592-020-01008-z\\u003c/span\\u003e\\u003cspan address=\\\"10.1038/s41592-020-01008-z\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e[EPub] 2020 Dec 7. PMID: 33288961\\u003c/span\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cspan\\u003eDiaz-Pinto A, Alle S, Nath V et al (2024) MONAI Label: A framework for AI-assisted interactive labeling of 3D medical images. Med Image Anal 95:103207. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1016/j.media.2024.103207\\u003c/span\\u003e\\u003cspan address=\\\"10.1016/j.media.2024.103207\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e[EPub]. PMID: 38776843\\u003c/span\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cspan\\u003eGao Y, Jiang Y, Peng Y, Yuan F, Zhang X, Wang J (2025) Medical image segmentation: A comprehensive review of deep learning-based methods. Tomography 11(5):52. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.3390/tomography11050052,\\u003c/span\\u003e\\u003cspan address=\\\"10.3390/tomography11050052,\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003ePMID: 40423254, PMCID: PMC12115501\\u003c/span\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cspan\\u003eSebro R, Mongan J (2023) TotalSegmentator: A gift to the biomedical imaging community. Radiol Artif Intell 5(5):e230235. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1148/ryai.230235,\\u003c/span\\u003e\\u003cspan address=\\\"10.1148/ryai.230235,\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003ePMID: 37795136, PMCID: PMC10546367\\u003c/span\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cspan\\u003eLindholz M, Ruppel R, Schulze-Weddige S et al (2025) Analyzing the TotalSegmentator for facial feature removal in head CT scans. \\u003cem\\u003eRadiography (Lond)\\u003c/em\\u003e ;31(1):372\\u0026ndash;8. doi: 10.1016/j.radi.2024.12.018 [EPub]. PMID: 39754865\\u003c/span\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cspan\\u003eWasserthal J, Breit HC, Meyer MT et al (2023) TotalSegmentator: Robust segmentation of 104 anatomic structures in CT images. Radiol Artif Intell 5(5):e230024. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1148/ryai.230024,\\u003c/span\\u003e\\u003cspan address=\\\"10.1148/ryai.230024,\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003ePMID: 37795137, PMCID: PMC10546353\\u003c/span\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cspan\\u003eReisert M, K\\u0026uuml;stner T, Walter A et al (2025) TotalSegmentator MRI: Robust sequence-independent segmentation of multiple anatomic structures in MRI. \\u003cem\\u003eRadiology\\u003c/em\\u003e ;314(2):e241613. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1148/radiol.241613\\u003c/span\\u003e\\u003cspan address=\\\"10.1148/radiol.241613\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e. PMID: 39964271\\u003c/span\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cspan\\u003eMuro S, Ibara T, Nimura A, Akita K (2025) Seg and ref: A newly developed toolset for artificial intelligence-powered segmentation and interactive refinement for labor-saving three-dimensional reconstruction. \\u003cem\\u003eMicroscopy (Oxf)\\u003c/em\\u003e. :dfaf015. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1093/jmicro/dfaf015\\u003c/span\\u003e\\u003cspan address=\\\"10.1093/jmicro/dfaf015\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e. Epub ahead of print. PMID: 40037547\\u003c/span\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cspan\\u003eMuro S, Ibara T, Nimura A, Akita K (2025) SegRef3D: A versatile open-source platform for artificial intelligence-assisted segmentation and three-dimensional reconstruction in morphological research. SSRN. www.ssrn.com/abstract=5547238. Published Sep 26, 2025. Accessed Nov 10. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.2139/ssrn.5547238\\u003c/span\\u003e\\u003cspan address=\\\"10.2139/ssrn.5547238\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cspan\\u003eVirz\\u0026igrave; A, Muller CO, Marret JB et al (2020) Comprehensive review of 3D segmentation software tools for MRI usable for pelvic surgery planning. J Digit Imaging 33(1):99\\u0026ndash;110. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1007/s10278-019-00239-7,\\u003c/span\\u003e\\u003cspan address=\\\"10.1007/s10278-019-00239-7,\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003ePMID: 31236743, PMCID: PMC7064712\\u003c/span\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cspan\\u003eKimura T, Takiguchi K, Tsukita S et al (2025) Development of anatomically accurate digital organ models for surgical simulation and training. PLoS ONE 20(4):e0320816. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1371/journal.pone.0320816,\\u003c/span\\u003e\\u003cspan address=\\\"10.1371/journal.pone.0320816,\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003ePMID: 40203219, PMCID: PMC11981654\\u003c/span\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cspan\\u003eIlesanmi AE, Ilesanmi TO, Ajayi BO (2024) Reviewing 3D convolutional neural network approaches for medical image segmentation. Heliyon 10(6):e27398. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1016/j.heliyon.2024.e27398,\\u003c/span\\u003e\\u003cspan address=\\\"10.1016/j.heliyon.2024.e27398,\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003ePMID: 38496891, PMCID: PMC10944240\\u003c/span\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cspan\\u003eWang K, Han Y, Ye Y et al (2025) Mixed reality infrastructure based on deep learning medical image segmentation and 3D visualization for bone tumors using DCU-Net. J Bone Oncol 50:100654. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1016/j.jbo.2024.100654,\\u003c/span\\u003e\\u003cspan address=\\\"10.1016/j.jbo.2024.100654,\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003ePMID: 39839577, PMCID: PMC11745962\\u003c/span\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cspan\\u003eZhou L, Wu G, Zuo Y, Chen X, Hu H (2024) A comprehensive review of vision-based 3D reconstruction methods. Sens (Basel) 24(7):2314. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.3390/s24072314,\\u003c/span\\u003e\\u003cspan address=\\\"10.3390/s24072314,\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003ePMID: 38610525, PMCID: PMC11014007\\u003c/span\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cspan\\u003eLambin P, Rios-Velazquez E, Leijenaar R et al (2012) Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer 48(4):441\\u0026ndash;446 PMID: 22257792, PMCID: PMC4533986\\u003c/span\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cspan\\u003eGillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278(2):563\\u0026ndash;567. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1148/radiol.2015151169,\\u003c/span\\u003e\\u003cspan address=\\\"10.1148/radiol.2015151169,\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003ePMID: 26579733, PMCID: PMC4734157\\u003c/span\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cspan\\u003eAerts H, Velazquez E, Leijenaar R et al (2014) Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. \\u003cem\\u003eNat Commun\\u003c/em\\u003e ;5(1):4006. doi: 400610.1038/ncomms5006, PMCID: PMC5784306\\u003c/span\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cspan\\u003eTraverso A, Wee L, Dekker A, Gillies R (2018) Repeatability and reproducibility of radiomic features: a systematic review. Int J Radiat Oncol Biol Phys 102(4):1143\\u0026ndash;1158. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1016/j.ijrobp.2018.05.053,\\u003c/span\\u003e\\u003cspan address=\\\"10.1016/j.ijrobp.2018.05.053,\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003ePMID: 30170872, PMCID: PMC6690209\\u003c/span\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cspan\\u003eMeidai K, Aihara T, Yamanaka N (2024) Enhancing liver surgery and transplantation: the role of 3D printing and virtual reality. Artif Intell Surg 4(3):180\\u0026ndash;186. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.20517/ais.2024.07\\u003c/span\\u003e\\u003cspan address=\\\"10.20517/ais.2024.07\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/span\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cspan\\u003eChen-Yoshikawa TF (2024) Evolution of three-dimensional computed tomography imaging in thoracic surgery. Cancers (Basel) 16(11):2161 : 10.3390/cancers16112161, PMID: 38893279, PMCID: PMC11172068\\u003c/span\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cspan\\u003eNaito S, Kajiwara M, Nakashima R, Sasaki T, Hasegawa S (2023) Application of extended reality (virtual reality and mixed reality) technology in laparoscopic liver resections. Cureus 15(9):e44520. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.7759/cureus.44520,\\u003c/span\\u003e\\u003cspan address=\\\"10.7759/cureus.44520,\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003ePMID: 37790042, PMCID: PMC10544840\\u003c/span\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cspan\\u003eSatoru M, Miyosawa K, Yamaguchi K et al (2025) Evaluation of glasses-free 3D anatomy learning materials through a randomized control study with a puzzle‐like method. Anat Sci Edu 18(7):684\\u0026ndash;696. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1002/ase.70063,\\u003c/span\\u003e\\u003cspan address=\\\"10.1002/ase.70063,\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003ePMID: 40452128, PMCID: PMC12222575\\u003c/span\\u003e\\u003c/li\\u003e\\u003cli\\u003e\\u003cspan\\u003eUeda H, Inami S, Moridaira H et al (2025) The usefulness and potential of high-fidelity three-dimensional models in spine surgery training: Cross-sectional empirical study. BMC Med Educ 25(1):387. \\u003cspan class=\\\"ExternalRef\\\"\\u003e\\u003cspan class=\\\"RefSource\\\"\\u003e10.1186/s12909-025-06936-y,\\u003c/span\\u003e\\u003cspan address=\\\"10.1186/s12909-025-06936-y,\\\" targettype=\\\"DOI\\\" class=\\\"RefTarget\\\"\\u003e\\u003c/span\\u003e\\u003c/span\\u003ePMID: 40089703, PMCID: PMC11910854\\u003c/span\\u003e\\u003c/li\\u003e\\u003c/ol\\u003e\"}],\"fulltextSource\":\"\",\"fullText\":\"\",\"funders\":[],\"hasAdminPriorityOnWorkflow\":false,\"hasManuscriptDocX\":true,\"hasOptedInToPreprint\":true,\"hasPassedJournalQc\":\"\",\"hasAnyPriority\":true,\"hideJournal\":true,\"highlight\":\"\",\"institution\":\"\",\"isAcceptedByJournal\":false,\"isAuthorSuppliedPdf\":false,\"isDeskRejected\":\"\",\"isHiddenFromSearch\":false,\"isInQc\":false,\"isInWorkflow\":false,\"isPdf\":false,\"isPdfUpToDate\":true,\"isWithdrawnOrRetracted\":false,\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"identity\":\"researchsquare\",\"isNatureJournal\":false,\"hasQc\":true,\"allowDirectSubmit\":true,\"externalIdentity\":\"\",\"sideBox\":\"\",\"snPcode\":\"\",\"submissionUrl\":\"/submission\",\"title\":\"Research Square\",\"twitterHandle\":\"researchsquare\",\"acdcEnabled\":true,\"dfaEnabled\":false,\"editorialSystem\":\"\",\"reportingPortfolio\":\"\",\"inReviewEnabled\":false,\"inReviewRevisionsEnabled\":true},\"keywords\":\"Automatic segmentation, 3D reconstruction, Medical imaging, Graphical user interface (GUI), Radiomics, 3D printing\",\"lastPublishedDoi\":\"10.21203/rs.3.rs-8150723/v1\",\"lastPublishedDoiUrl\":\"https://doi.org/10.21203/rs.3.rs-8150723/v1\",\"license\":{\"name\":\"CC BY 4.0\",\"url\":\"https://creativecommons.org/licenses/by/4.0/\"},\"manuscriptAbstract\":\"\\u003cp\\u003e\\u003cstrong\\u003eBackground: \\u003c/strong\\u003eAutomatic segmentation is indispensable in medical imaging, yet advanced tools often remain confined to experts due to command-line complexity. TotalSegmentator delivers accurate multi-organ segmentation, but lacks accessibility for clinicians and educators. To overcome this barrier, we developed Instant3D, an open-source graphical user interface (GUI) that makes high-quality 3D reconstruction straightforward and intuitive.\\u003c/p\\u003e\\n\\u003cp\\u003e\\u003cstrong\\u003eObjective: \\u003c/strong\\u003eThe purpose of this study was to introduce the Instant3D GUI and validate its performance.\\u003c/p\\u003e\\n\\u003cp\\u003e\\u003cstrong\\u003eMethods: \\u003c/strong\\u003eWe developed Instant3D in Python using PyQt6. It accepts DICOM, NIfTI, or NRRD input. Users select regions of interest through a suggestion-enabled interface, and the tool automatically runs TotalSegmentator. Outputs include STL meshes for 3D visualization, CSV files with volumetric data, and per-slice SVG masks. Crucially, these SVG files are interoperable with SegRef3D, enabling interactive correction and refinement of automated results—combining the strengths of artificial intelligence segmentation and user-driven adjustment. Batch processing is supported for large datasets. We validated Instant3D by testing it on representative computed tomography (CT) and magnetic resonance imaging (MRI) datasets, including publicly available example data from the 3D Slicer Sample Data module.\\u003c/p\\u003e\\n\\u003cp\\u003e\\u003cstrong\\u003eResults: \\u003c/strong\\u003eInstant3D reliably produced 3D models from CT and MRI scans. STL meshes preserved anatomical fidelity, SVG masks facilitated slice-level review and editing in SegRef3D, and CSV outputs provided quantitative volume data. The GUI eliminated the need for command-line knowledge, lowering the entry barrier for diverse users across research and education.\\u003c/p\\u003e\\n\\u003cp\\u003e\\u003cstrong\\u003eConclusions: \\u003c/strong\\u003eWe developed Instant3D, an open-source and user-friendly platform that democratizes advanced segmentation by combining automation with practical usability. It provides a seamless GUI, bridging advanced automatic segmentation with practical applications in research and development.\\u003c/p\\u003e\\n\\u003cp\\u003e\\u003cstrong\\u003eClinical Impact: \\u003c/strong\\u003eInstant3D 3D reconstructions extend beyond visualization, offering immediate value for radiomics-driven quantitative research, virtual reality-based surgical simulation, 3D printing for surgical planning and patient education, and glasses-free 3D display teaching tools.\\u003c/p\\u003e\",\"manuscriptTitle\":\"Instant3D: A User-Friendly GUI Integrating TotalSegmentator for Immediate Medical Image Segmentation and 3D Reconstruction\",\"msid\":\"\",\"msnumber\":\"\",\"nonDraftVersions\":[{\"code\":1,\"date\":\"2025-11-20 08:19:09\",\"doi\":\"10.21203/rs.3.rs-8150723/v1\",\"editorialEvents\":[{\"type\":\"communityComments\",\"content\":0}],\"status\":\"published\",\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"identity\":\"researchsquare\",\"isNatureJournal\":false,\"hasQc\":true,\"allowDirectSubmit\":true,\"externalIdentity\":\"\",\"sideBox\":\"\",\"snPcode\":\"\",\"submissionUrl\":\"/submission\",\"title\":\"Research Square\",\"twitterHandle\":\"researchsquare\",\"acdcEnabled\":true,\"dfaEnabled\":false,\"editorialSystem\":\"\",\"reportingPortfolio\":\"\",\"inReviewEnabled\":false,\"inReviewRevisionsEnabled\":true}}],\"origin\":\"\",\"ownerIdentity\":\"a6b2f1ad-5d20-417a-8e8a-cf1a47eeb553\",\"owner\":[],\"postedDate\":\"November 20th, 2025\",\"published\":true,\"recentEditorialEvents\":[],\"rejectedJournal\":[],\"revision\":\"\",\"amendment\":\"\",\"status\":\"posted\",\"subjectAreas\":[{\"id\":58220339,\"name\":\"Nuclear Medicine \\u0026 Medical Imaging\"}],\"tags\":[],\"updatedAt\":\"2025-11-20T08:19:09+00:00\",\"versionOfRecord\":[],\"versionCreatedAt\":\"2025-11-20 08:19:09\",\"video\":\"\",\"vorDoi\":\"\",\"vorDoiUrl\":\"\",\"workflowStages\":[]},\"version\":\"v1\",\"identity\":\"rs-8150723\",\"journalConfig\":\"researchsquare\"},\"__N_SSP\":true},\"page\":\"/article/[identity]/[[...version]]\",\"query\":{\"redirect\":\"/article/rs-8150723\",\"identity\":\"rs-8150723\",\"version\":[\"v1\"]},\"buildId\":\"XKTyCvWXoU3ODBz1xrDgd\",\"isFallback\":false,\"isExperimentalCompile\":false,\"dynamicIds\":[84888],\"gssp\":true,\"scriptLoader\":[]}","source_license":"CC-BY-4.0","license_restricted":false}