{"paper_id":"39d7724a-3432-468f-a855-d9c95b0c34c8","body_text":"Abstract\nBackground\nMagnetic resonance imaging (MRI) has been increasingly applied in the classification of adenomyosis; however, due to the lack of a standardized gold standard for lesion classification, it remains challenging to make an early diagnosis and initiate timely treatment. This study aimed to develop a deep learning (DL)-based classification system for adenomyosis and systematically compare the performance of five most frequently researched classification criteria.\nMethods\nUsing standardized protocols (slice thickness: 3–4 mm, TR/TE: 3000–5000/80–100 ms), T2-weighted images (T2WI) from 6,768 MRI scans acquired at 1.5T and 3T scanners (Siemens, GE, and Philips) were analyzed. Images were independently labeled by three expert radiologists with at least 10 years of experience according to five classification systems (Hulka, Kishi, Bazot, Kobayashi, and Gong), with interobserver agreement (κ = 0.82–0.91). The VGG11 model was evaluated in terms of accuracy, precision, recall, and F1-score with 95% confidence intervals (CIs).\nResults\nThe model achieved over 90% accuracy on all criteria. The Bazot 3-class system showed the best performance (accuracy: 0.9778 [95% CI: 0.972–0.983], F1-score: 0.9723). K-fold cross-validation showed stable convergence within 200 epochs. Confusion matrix analysis revealed an exceptional generalization capability, even for the extreme class imbalances (at the sample ratio of 86:1). The Gong 6-class system achieved lower performance (accuracy: 0.9214 [95% CI: 0.912–0.931]) due to data imbalance.\nConclusions\nOur DL system provided accurate, automated adenomyosis classification. The systematic comparison revealed significant performance differences among various criteria, and the Bazot system was optimal for DL applications, which endowed clinicians with the enhanced diagnostic capabilities for adenomyosis evaluation through MRI.\nResearch highlights\nThe VGG11-based deep learning model achieved exceptional diagnostic accuracy (over 90% on all criteria), establishing a new benchmark for the MRI-based detection of adenomyosis.\nThis study provided the first comprehensive evaluation of the five most frequently researched adenomyosis classification systems using deep learning, revealing significant performance differences that inform the selection of the optimal clinical protocol.\nThe demonstrated accuracy and consistency of our automated system addressed critical standardization gaps in adenomyosis diagnosis, providing an objective tool for clinicians to reduce diagnostic variability and improve treatment planning.\nAbbreviations\n- DL:\n-\nDeep Learning\n- MRI:\n-\nMagnetic resonance imaging\n- T2WI:\n-\nT2-weighted images\n- TVUS:\n-\nTransvaginal ultrasound\n- CNN:\n-\nConvolutional neural network\n- JZ:\n-\nJunctional zone\nFunding\nThis work was supported by National Key R&D Plan for Intergovernmental Cooperation, the Ministry of Science and Technology of China (Grant No.2022YFE0133100), Foundation of State Key Laboratory of Ultrasound in Medicine and Engineering (Grant No. 2024KFKT016), Sichuan Provincial Natural Science Foundation Project (26NSFSC0004), Nanchong Municipal Bureau of Science and Technology Project (25YYJCYJ0077), Sichuan Medical Science & Technology Innovation Research Association (Grant No. 2026YCYM002), the Sichuan Medical and Health Care Promotion Institute Scientific Research Project (Grant No. KY2025QN0053) and the Project of North Sichuan Medical College Youth Program (Grant No. CBY23-QNA19, CBY23-ZDA12, CBY23-QNA11).\nAuthor information\nAuthors and Affiliations\nCorresponding author\nEthics declarations\nEthics approval and consent to participate\nWe ensured that the work described has been carried out in accordance with The Code of Ethics of the World Medical Association (Declaration of Helsinki). This retrospective cohort study received ethical approval from the Institutional Review Board of the Affiliated Nanchong Central Hospital, North Sichuan Medical College (Approval No. 2021/104), with waiver of informed consent owing to the anonymized nature of the data.\nDeclaration of generative AI and AI-assisted technologies in the writing process\nDuring the preparation of this work, the authors used DeepSeek-V3 (DeepSeek AI) to improve the language fluency and readability of the manuscript. All AI-generated content was carefully reviewed, edited, and approved by the authors, who assume full responsibility for the final published work. The authors carefully reviewed and edited all content generated by this tool and assume full responsibility for the final published work.\nConsent for publication\nNot applicable.\nDisclosure\nThe author declares no known competing financial interests or personal relationships that could influence the content reported in this study.\nCompeting interests\nThe authors declare no competing interests.\nAdditional information\nPublisher’s note\nSpringer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.\nSupplementary Information\nBelow is the link to the electronic supplementary material.\nRights and permissions\nOpen Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.\nAbout this article\nCite this article\nTang, Y., Tian, Hd., Chen, Xm. et al. VGG11-based deep learning for automated MRI classification of adenomyosis: a systematic comparison of five classification criteria. BMC Med Imaging (2026). https://doi.org/10.1186/s12880-026-02633-4\nReceived:\nAccepted:\nPublished:\nDOI: https://doi.org/10.1186/s12880-026-02633-4","source_license":"CC0","license_restricted":false}