{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T01:10:54Z","timestamp":1792113054378,"version":"4.4.0"},"reference-count":31,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T00:00:00Z","timestamp":1775520000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"The Clinical Research Center of Shanghai Tenth People\u2019s Hospital Affiliated of Tongji University, China","award":["YNCR2B010"],"award-info":[{"award-number":["YNCR2B010"]}]},{"award":["YNCR2B010"],"award-info":[{"award-number":["YNCR2B010"]}],"id":[{"id":"https:\/\/ror.org\/03vjkf643","id-type":"ROR","asserted-by":"publisher"}]},{"name":"Program for Research-oriented Physician of Shanghai Tenth People\u2019s Hospital, China","award":["2023YJXYSA011"],"award-info":[{"award-number":["2023YJXYSA011"]}]},{"name":"Ningbo Public Welfare Research Program Projects","award":["2024S058"],"award-info":[{"award-number":["2024S058"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JCM"],"abstract":"<jats:p>Objective: To develop and validate an artificial intelligence (AI) system for automated lens opacities classification system III (LOCS III)-based grading of all three major cataract subtypes using anterior segment optical coherence tomography (AS-OCT). Methods: This is a single-center cross-sectional study. AS-OCT images were collected and manually graded by ophthalmologists according to LOCS III. The dataset was randomly split into training, validation, and test sets. We propose a novel multi-granularity mask-guided network (MMNet) that jointly performs lens substructure segmentation and severity grading. The model\u2019s performance was assessed on an independent test set for automatic grading of cortical cataract (CC), nuclear cataract (NC), and posterior subcapsular cataract (PSC) and the grading performance of the proposed method against ophthalmologists was also evaluated. The model\u2019s interpretability was assessed via attention heatmaps and feature visualization. Results: The proposed MMNet exhibited high agreement with ground truth conducted through gold standard. The proportions of predictions with an absolute error &lt; 1.0 for three subtypes range from 83.02% to 89.94%. The model\u2019s grading accuracy for cataract subtypes was between 82.20 \u00b1 1.41% and 89.76 \u00b1 1.31% among the three subtypes, the Area Under the Curve (AUC) was between 0.954 (95% CI, 0.952\u20130.969; p &lt; 0.001) and 0.973 (95% CI, 0.964\u20130.985; p &lt; 0.001). The MMNet shows a satisfactory mean absolute error (MAE) of 0.14 \u00b1 0.35 in CC, 0.10 \u00b1 0.30 in NC, and 0.17 \u00b1 0.38 in PSC grading. It also achieved a fast grading speed of 0.0178 s\/image against manual grading. Conclusions: The proposed AI model presented advanced performance on AS-OCT images in automated LOCS III-based cataract grading for CC and NC, and also showed feasibility in PSC assessment.<\/jats:p>","DOI":"10.3390\/jcm15072798","type":"journal-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T13:14:19Z","timestamp":1775567659000},"page":"2798","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Multi-Granularity Mask-Guided Network: An Integrated AI Framework for Region-Level Segmentation and Grading of Cataract Subtypes on AS-OCT Images"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4222-6381","authenticated-orcid":false,"given":"Yiwen","family":"Hu","sequence":"first","affiliation":[{"name":"Department of Ophthalmology, Shanghai Tenth People\u2019s Hospital, Tongji University School of Medicine, Shanghai 200072, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bingyan","family":"Hao","sequence":"additional","affiliation":[{"name":"Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo 315000, China"},{"name":"Ningbo Key Laboratory of Biomedical Imaging Probe Materials and Technology, Ningbo 315000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1871-2887","authenticated-orcid":false,"given":"Yilin","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Shanghai Tenth People\u2019s Hospital, Tongji University School of Medicine, Shanghai 200072, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yitian","family":"Zhao","sequence":"additional","affiliation":[{"name":"Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo 315000, China"},{"name":"Ningbo Key Laboratory of Biomedical Imaging Probe Materials and Technology, Ningbo 315000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2327-582X","authenticated-orcid":false,"given":"Yuanyuan","family":"Gu","sequence":"additional","affiliation":[{"name":"Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo 315000, China"},{"name":"Ningbo Key Laboratory of Biomedical Imaging Probe Materials and Technology, Ningbo 315000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fang","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Shanghai Tenth People\u2019s Hospital, Tongji University School of Medicine, Shanghai 200072, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,7]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"e144","DOI":"10.1016\/S2214-109X(20)30489-7","article-title":"GBD 2019 Blindness and Vision Impairment Collaborators, & Vision Loss Expert Group of the Global Burden of Disease Study Causes of blindness and vision impairment in 2020 and trends over 30 years, and prevalence of avoidable blindness in relation to VISION 2020: The Right to Sight: An analysis for the Global Burden of Disease Study","volume":"9","author":"Steinmetz","year":"2021","journal-title":"Lancet Glob. Health"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1001\/archopht.1993.01090060119035","article-title":"The Lens Opacities Classification System III. The Longitudinal Study of Cataract Study Group","volume":"111","author":"Chylack","year":"1993","journal-title":"Arch. Ophthalmol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"790","DOI":"10.1136\/bjophthalmol-2020-318334","article-title":"Objective quantification of lens nuclear opacities using swept-source anterior segment optical coherence tomography","volume":"106","author":"Wang","year":"2022","journal-title":"Br. J. Ophthalmol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"107958","DOI":"10.1016\/j.cmpb.2023.107958","article-title":"Multi-style spatial attention module for cortical cataract classification in AS-OCT image with supervised contrastive learning","volume":"244","author":"Xiao","year":"2024","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"102499","DOI":"10.1016\/j.media.2022.102499","article-title":"Attention to region: Region-based integration-and-recalibration networks for nuclear cataract classification using AS-OCT images","volume":"80","author":"Zhang","year":"2022","journal-title":"Med. Image Anal."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"110069","DOI":"10.1016\/j.patcog.2023.110069","article-title":"Regional context-based recalibration network for cataract recognition in AS-OCT","volume":"147","author":"Zhang","year":"2024","journal-title":"Pattern Recognit."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Fern\u00e1ndez-Vigo, J.I., Burgos-Blasco, B., De-Pablo-G\u00f3mez-de-Lia\u00f1o, L., Almor\u00edn-Fern\u00e1ndez-Vigo, I., Arriola-Villalobos, P., Ruiz-Casas, D., Macarro-Merino, A., and Fern\u00e1ndez-Vigo, J.\u00c1. (2025). Clinical Applications of Anterior Segment Optical Coherence Tomography in Managing Phakic and Secondary Intraocular Lens Implants: A Comprehensive Review. Diagnostics, 15.","DOI":"10.3390\/diagnostics15182385"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"100900","DOI":"10.1016\/j.preteyeres.2020.100900","article-title":"Digital technology, tele-medicine and artificial intelligence in ophthalmology: A global perspective","volume":"82","author":"Li","year":"2021","journal-title":"Prog. Retin. Eye Res."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"100837","DOI":"10.1016\/j.xops.2025.100837","article-title":"Multi-Comparison of Different Ocular Imaging Modality-based Deep Learning Models for Visually Significant Cataract Detection","volume":"5","author":"Goh","year":"2025","journal-title":"Ophthalmol. Sci."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"104978","DOI":"10.1016\/j.cmpb.2019.07.006","article-title":"Automatic cataract grading methods based on deep learning","volume":"182","author":"Zhang","year":"2019","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"100147","DOI":"10.1016\/j.xops.2022.100147","article-title":"Deep Learning-Based Cataract Detection and Grading from Slit-Lamp and Retro-Illumination Photographs: Model Development and Validation Study","volume":"2","author":"Son","year":"2022","journal-title":"Ophthalmol. Sci."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1097\/j.jcrs.0000000000001598","article-title":"CATALYZE: A deep learning approach for cataract assessment and grading on SS-OCT images","volume":"51","author":"Panthier","year":"2025","journal-title":"J. Cataract. Refract. Surg."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"528","DOI":"10.1097\/j.jcrs.0000000000000790","article-title":"Lens Opacities Classification System III-based artificial intelligence program for automatic cataract grading","volume":"48","author":"Lu","year":"2022","journal-title":"J. Cataract. Refract. Surg."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"107141","DOI":"10.1016\/j.cmpb.2022.107141","article-title":"IEViT: An enhanced vision transformer architecture for chest X-ray image classification","volume":"226","author":"Okolo","year":"2022","journal-title":"Comput. Methods Progr. Biomed."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"245008","DOI":"10.1088\/1361-6560\/ad00fe","article-title":"SCA-Former: Transformer-like network based on stream-cross attention for medical image segmentation","volume":"68","author":"Gao","year":"2023","journal-title":"Phys. Med. Biol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"105836","DOI":"10.1016\/j.bspc.2023.105836","article-title":"A ranking-based multi-scale feature calibration network for nuclear cataract grading in AS-OCT images","volume":"90","author":"Gu","year":"2024","journal-title":"Biomed. Signal Process. Control."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"e1042","DOI":"10.3928\/1081597X-20250707-09","article-title":"Automated Quantification of Lens Cortex and Nuclear Opacity Based on Swept-Source Anterior Segment Optical Coherence Tomography","volume":"41","author":"Han","year":"2025","journal-title":"J. Refract. Surg."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Takinami, S., Ueno, Y., Mori, H., Morita, Y., Seita, J., and Oshika, T. (2026). Advancement of cataract classification with artificial intelligence using anterior segment optical coherence tomography images with self-supervised vision transformer. Jpn. J. Ophthalmol.","DOI":"10.1007\/s10384-025-01323-y"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. arXiv.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_20","first-page":"1","article-title":"ConvNets for automatic detection of polyglutamine SCAs from brain MRIs: State of the art applications","volume":"61","author":"Reetz","year":"2023","journal-title":"Med. Biol. Eng. Comput."},{"key":"ref_21","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An Image is Worth 16 \u00d7 16 Words: Transformers for Image Recognition at Scale (Version 2). arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"837","DOI":"10.2307\/2531595","article-title":"Comparing the areas under two or more correlated receiver operating characteristic curves: A nonparametric approach","volume":"44","author":"DeLong","year":"1988","journal-title":"Biometrics"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"760","DOI":"10.1097\/j.jcrs.0000000000001424","article-title":"All about traumatic cataracts: Narrative review","volume":"5","author":"Soleimani","year":"2024","journal-title":"J. Cataract. Refract. Surg."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"101134","DOI":"10.1016\/j.disamonth.2021.101134","article-title":"Diabetic cataracts","volume":"67","author":"Greenberg","year":"2021","journal-title":"Dis. Mon."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1016\/j.aopr.2024.06.003","article-title":"Complications of high myopia: An update from clinical manifestations to underlying mechanisms","volume":"4","author":"Du","year":"2024","journal-title":"Adv. Ophthalmol. Pract. Res."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1016\/j.ajo.2023.06.003","article-title":"Objective Quantification of Lens Opacity in Posterior Subcapsular Cataracts Using IOL Master 700 and CASIA-2","volume":"254","author":"Fan","year":"2023","journal-title":"Am. J. Ophthalmol."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2161","DOI":"10.2147\/OPTH.S308750","article-title":"\u201cChopper Shield\u201d Technique to Protect Corneal Endothelium During Phacoemulsification Surgery for Rock Hard Cataracts","volume":"15","author":"Mahajan","year":"2021","journal-title":"Clin. Ophthalmol."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1604","DOI":"10.1080\/02713683.2017.1343852","article-title":"Natural course of posterior subcapsular cataract over a short time period","volume":"42","author":"Neumayer","year":"2017","journal-title":"Curr. Eye Res."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Madan, C., Gupta, M., Basu, S., Gupta, P., and Arora, C. (2025). Lq-adapter: Vit-adapter with learnable queries for gallbladder cancer detection from ultrasound images. Proceedings of the 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, AZ, USA, 26 February\u20136 March 2025, IEEE.","DOI":"10.1109\/WACV61041.2025.00064"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Wang, N., Zeng, Z., and Qiu, X. (2023). SwinUnet with Multi-task Learning for Image Segmentation. Proceedings of the 2023 IEEE 6th International Conference on Information Systems and Computer Aided Education (ICISCAE), Dalian, China, 23\u201325 September 2023, IEEE.","DOI":"10.1109\/ICISCAE59047.2023.10393666"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1097\/ICU.0000000000000910","article-title":"Advances in drug therapy and delivery for cataract treatment","volume":"34","author":"Lee","year":"2023","journal-title":"Curr. Opin. Ophthalmol."}],"container-title":["Journal of Clinical Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2077-0383\/15\/7\/2798\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T13:19:47Z","timestamp":1775567987000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2077-0383\/15\/7\/2798"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,7]]},"references-count":31,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["jcm15072798"],"URL":"https:\/\/doi.org\/10.3390\/jcm15072798","relation":{},"ISSN":["2077-0383"],"issn-type":[{"value":"2077-0383","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,7]]}}}