{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:30:17Z","timestamp":1740133817354,"version":"3.37.3"},"reference-count":48,"publisher":"BMJ","funder":[{"DOI":"10.13039\/501100010226","name":"Guangdong Provincial Department of Education","doi-asserted-by":"crossref","award":["2020ZDZX3043"],"award-info":[{"award-number":["2020ZDZX3043"]}],"id":[{"id":"10.13039\/501100010226","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Guangdong Provincial Key Laboratory","award":["2020B121201001","JCYJ20200109140820699"],"award-info":[{"award-number":["2020B121201001","JCYJ20200109140820699"]}]},{"name":"Stable Support Plan Program","award":["20200925174052004"],"award-info":[{"award-number":["20200925174052004"]}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["Br J Ophthalmol"],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>The crystalline lens is a transparent structure of the eye to focus light on the retina. It becomes muddy, hard and dense with increasing age, which makes the crystalline lens gradually lose its function. We aim to develop a nuclear age predictor to reflect the degeneration of the crystalline lens nucleus.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>First we trained and internally validated the nuclear age predictor with a deep-learning algorithm, using 12 904 anterior segment optical coherence tomography (AS-OCT) images from four diverse Asian and American cohorts: Zhongshan Ophthalmic Center with Machine0 (ZOM0), Tomey Corporation (TOMEY), University of California San Francisco and the Chinese University of Hong Kong. External testing was done on three independent datasets: Tokyo University (TU), ZOM1 and Shenzhen People\u2019s Hospital (SPH). We also demonstrate the possibility of detecting nuclear cataracts (NCs) from the nuclear age gap.<\/jats:p><\/jats:sec><jats:sec><jats:title>Findings<\/jats:title><jats:p>In the internal validation dataset, the nuclear age could be predicted with a mean absolute error (MAE) of 2.570 years (95% CI 1.886 to 2.863). Across the three external testing datasets, the algorithm achieved MAEs of 4.261 years (95% CI 3.391 to 5.094) in TU, 3.920 years (95% CI 3.332 to 4.637) in ZOM1-NonCata and 4.380 years (95% CI 3.730 to 5.061) in SPH-NonCata. The MAEs for NC eyes were 8.490 years (95% CI 7.219 to 9.766) in ZOM1-NC and 9.998 years (95% CI 5.673 to 14.642) in SPH-NC. The nuclear age gap outperformed both ophthalmologists in detecting NCs, with areas under the receiver operating characteristic curves of 0.853 years (95% CI 0.787 to 0.917) in ZOM1 and 0.909 years (95% CI 0.828 to 0.978) in SPH.<\/jats:p><\/jats:sec><jats:sec><jats:title>Interpretation<\/jats:title><jats:p>The nuclear age predictor shows good performance, validating the feasibility of using AS-OCT images as an effective screening tool for nucleus degeneration. Our work also demonstrates the potential use of the nuclear age gap to detect NCs.<\/jats:p><\/jats:sec>","DOI":"10.1136\/bjo-2023-323176","type":"journal-article","created":{"date-parts":[[2023,7,26]],"date-time":"2023-07-26T17:55:22Z","timestamp":1690394122000},"page":"bjo-2023-323176","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":0,"title":["Crystalline lens nuclear age prediction as a new biomarker of nucleus degeneration"],"prefix":"10.1136","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5417-9470","authenticated-orcid":false,"given":"Mengjie","family":"Guo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Risa","family":"Higashita","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingxi","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gilda Wing Ki","family":"Lai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1104-4194","authenticated-orcid":false,"given":"Anwell","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rei","family":"Sakata","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keiichiro","family":"Okamoto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanwu","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9702-5524","authenticated-orcid":false,"given":"Huazhu","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Makoto","family":"Aihara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiulan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5756-5414","authenticated-orcid":false,"given":"Jin","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shan","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher Kai-Shun","family":"Leung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"239","published-online":{"date-parts":[[2023,7,26]]},"reference":[{"key":"2023072610200722000_bjo-2023-323176v1.1","doi-asserted-by":"publisher","DOI":"10.1016\/S2214-109X(20)30488-5"},{"key":"2023072610200722000_bjo-2023-323176v1.2","doi-asserted-by":"publisher","DOI":"10.1136\/pgmj.2005.040857"},{"key":"2023072610200722000_bjo-2023-323176v1.3","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(05)17911-2"},{"key":"2023072610200722000_bjo-2023-323176v1.4","doi-asserted-by":"publisher","DOI":"10.1159\/000027475"},{"key":"2023072610200722000_bjo-2023-323176v1.5","doi-asserted-by":"publisher","DOI":"10.1159\/000316481"},{"key":"2023072610200722000_bjo-2023-323176v1.6","doi-asserted-by":"publisher","DOI":"10.1136\/bjo.2008.137653"},{"key":"2023072610200722000_bjo-2023-323176v1.7","doi-asserted-by":"crossref","first-page":"3821","DOI":"10.1364\/BOE.9.003821","article-title":"Volumetric macro-and micro-scale assessment of crystalline lens opacities in cataract patients using long-depth-range swept source optical coherence tomography","volume":"9","author":"Grulkowski","year":"2018","journal-title":"Biomed Opt Express"},{"key":"2023072610200722000_bjo-2023-323176v1.8","doi-asserted-by":"publisher","DOI":"10.1136\/bjophthalmol-2018-312661"},{"key":"2023072610200722000_bjo-2023-323176v1.9","doi-asserted-by":"crossref","first-page":"1930","DOI":"10.1109\/TMI.2017.2703147","article-title":"Segmentation and quantification for angle-closure glaucoma assessment in anterior segment OCT","volume":"36","author":"Fu","year":"2017","journal-title":"IEEE Trans Med Imaging"},{"key":"2023072610200722000_bjo-2023-323176v1.10","doi-asserted-by":"crossref","first-page":"101798","DOI":"10.1016\/j.media.2020.101798","article-title":"AGE challenge: angle closure glaucoma evaluation in anterior segment optical coherence tomography","volume":"66","author":"Fu","year":"2020","journal-title":"Med Image Anal"},{"key":"2023072610200722000_bjo-2023-323176v1.11","doi-asserted-by":"crossref","unstructured":"Zhang X , Xiao Z , Higashita R , et al . A novel deep learning method for nuclear cataract classification based on anterior segment optical coherence tomography images. 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC); Toronto, ON, Canada. doi:10.1109\/SMC42975.2020.9283218","DOI":"10.1109\/SMC42975.2020.9283218"},{"key":"2023072610200722000_bjo-2023-323176v1.12","doi-asserted-by":"crossref","first-page":"15014","DOI":"10.1038\/nrdp.2015.14","article-title":"Cataract","volume":"1","author":"Lam","year":"2015","journal-title":"Nat Rev Dis Primers"},{"key":"2023072610200722000_bjo-2023-323176v1.13","doi-asserted-by":"crossref","first-page":"141","DOI":"10.18240\/ijo.2022.01.21","article-title":"Prevalence of cataract and cataract surgery in urban and rural Chinese populations over 50 years old: a systematic review and meta-analysis","volume":"15","author":"Du","year":"2022","journal-title":"Int J Ophthalmol"},{"key":"2023072610200722000_bjo-2023-323176v1.14","doi-asserted-by":"publisher","DOI":"10.1136\/bjophthalmol-2013-303135"},{"key":"2023072610200722000_bjo-2023-323176v1.15","doi-asserted-by":"publisher","DOI":"10.1001\/archopht.1988.01060130356020"},{"key":"2023072610200722000_bjo-2023-323176v1.16","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcrs.2010.05.002"},{"key":"2023072610200722000_bjo-2023-323176v1.17","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"2023072610200722000_bjo-2023-323176v1.18","doi-asserted-by":"crossref","first-page":"562","DOI":"10.1038\/s43587-022-00245-5","article-title":"Detecting visually significant cataract using retinal photograph-based deep learning","volume":"2","author":"Tham","year":"2022","journal-title":"Nat Aging"},{"key":"2023072610200722000_bjo-2023-323176v1.19","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2015.2444389"},{"key":"2023072610200722000_bjo-2023-323176v1.20","doi-asserted-by":"crossref","unstructured":"Esteva A , Kuprel B , Novoa RA , et al . Corrigendum: dermatologist-level classification of skin cancer with deep neural networks. Nature 2017;546:686. doi:10.1038\/nature22985","DOI":"10.1038\/nature22985"},{"key":"2023072610200722000_bjo-2023-323176v1.21","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.17216"},{"key":"2023072610200722000_bjo-2023-323176v1.22","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.18152"},{"key":"2023072610200722000_bjo-2023-323176v1.23","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1038\/s41551-018-0195-0","article-title":"Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning","volume":"2","author":"Poplin","year":"2018","journal-title":"Nat Biomed Eng"},{"key":"2023072610200722000_bjo-2023-323176v1.24","doi-asserted-by":"crossref","first-page":"498","DOI":"10.1038\/s41551-020-00626-4","article-title":"A deep-learning system for the assessment of cardiovascular disease risk via the measurement of retinal-vessel calibre","volume":"5","author":"Cheung","year":"2021","journal-title":"Nat Biomed Eng"},{"key":"2023072610200722000_bjo-2023-323176v1.25","doi-asserted-by":"crossref","unstructured":"Jonsson BA , Bjornsdottir G , Thorgeirsson TE , et al . Brain age prediction using deep learning Uncovers associated sequence variants. Nat Commun 2019;10:5409. doi:10.1038\/s41467-019-13163-9","DOI":"10.1038\/s41467-019-13163-9"},{"key":"2023072610200722000_bjo-2023-323176v1.26","doi-asserted-by":"crossref","unstructured":"Shi W , Yan G , Li Y , et al . Fetal brain age estimation and anomaly detection using attention-based deep ensembles with uncertainty. Neuroimage 2020;223:117316. doi:10.1016\/j.neuroimage.2020.117316","DOI":"10.1016\/j.neuroimage.2020.117316"},{"key":"2023072610200722000_bjo-2023-323176v1.27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2010.01.005"},{"key":"2023072610200722000_bjo-2023-323176v1.28","doi-asserted-by":"publisher","DOI":"10.1136\/bjophthalmol-2021-319807"},{"key":"2023072610200722000_bjo-2023-323176v1.29","doi-asserted-by":"crossref","first-page":"946","DOI":"10.1038\/s42255-020-00270-x","article-title":"Three-dimensional facial-image analysis to predict heterogeneity of the human ageing rate and the impact of lifestyle","volume":"2","author":"Xia","year":"2020","journal-title":"Nat Metab"},{"key":"2023072610200722000_bjo-2023-323176v1.30","doi-asserted-by":"crossref","unstructured":"He K , Zhang X , Ren S , et al . Deep residual learning for image recognition. Sun J , ed. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Las Vegas, NV, USA. 2016 doi:10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"2023072610200722000_bjo-2023-323176v1.31","doi-asserted-by":"publisher","DOI":"10.3109\/02713683.2014.898774"},{"key":"2023072610200722000_bjo-2023-323176v1.32","doi-asserted-by":"crossref","unstructured":"Chen S , Zhang C , Dong M , et al . Using ranking-CNN for age estimation. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Honolulu, HI. 2017 doi:10.1109\/CVPR.2017.86","DOI":"10.1109\/CVPR.2017.86"},{"key":"2023072610200722000_bjo-2023-323176v1.33","unstructured":"Lee C-Y , Xie S , Gallagher P , et al ., eds. Deeply-supervised nets. Artificial intelligence and statistics. PMLR, 2015."},{"key":"2023072610200722000_bjo-2023-323176v1.34","unstructured":"Wang L , Lee C-Y , Tu Z , et al . Training deeper convolutional networks with deep supervision. arXiv Preprint arXiv:150502496 2015."},{"key":"2023072610200722000_bjo-2023-323176v1.35","doi-asserted-by":"crossref","unstructured":"Yang T-Y , Huang Y-H , Lin Y-Y , et al . SSR-Net: a compact soft Stagewise regression network for age estimation. Yang T-Y , Huang Y-H , Lin Y-Y , eds. Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18}; Stockholm, Sweden. California: IJCAI, 2018 doi:10.24963\/ijcai.2018\/150","DOI":"10.24963\/ijcai.2018\/150"},{"key":"2023072610200722000_bjo-2023-323176v1.36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"2023072610200722000_bjo-2023-323176v1.37","doi-asserted-by":"crossref","unstructured":"Selvaraju RR , Cogswell M , Das A , et al . Grad-Cam: visual explanations from deep networks via gradient-based localization. Batra D , ed. 2017 IEEE International Conference on Computer Vision (ICCV); Venice. 2017 doi:10.1109\/ICCV.2017.74","DOI":"10.1109\/ICCV.2017.74"},{"key":"2023072610200722000_bjo-2023-323176v1.38","doi-asserted-by":"crossref","first-page":"923","DOI":"10.1097\/00006324-199311000-00009","article-title":"Evaluation of lens opacities classification system III applied at the slit lamp","volume":"70","author":"Karbassi","year":"1993","journal-title":"Optom Vis Sci"},{"key":"2023072610200722000_bjo-2023-323176v1.39","doi-asserted-by":"publisher","DOI":"10.1016\/S0895-4356(99)00075-X"},{"key":"2023072610200722000_bjo-2023-323176v1.40","doi-asserted-by":"publisher","DOI":"10.1097\/01.ede.0000147512.81966.ba"},{"key":"2023072610200722000_bjo-2023-323176v1.41","doi-asserted-by":"crossref","unstructured":"Nygaard V , L\u00f8land A , Holden M , et al . Effects of mRNA amplification on gene expression ratios in cDNA experiments estimated by analysis of variance. BMC Genomics 2003;4:11. doi:10.1186\/1471-2164-4-11","DOI":"10.1186\/1471-2164-4-11"},{"key":"2023072610200722000_bjo-2023-323176v1.42","doi-asserted-by":"crossref","unstructured":"Xiao Z , Zhang X , Higashita R , et al . A 3D CNN-based multi-task learning for cataract screening and left and right eye classification on 3d AS-OCT images. ICIMH 2021; Macau China. New York, NY, USA, 2021 doi:10.1145\/3484377.3484378","DOI":"10.1145\/3484377.3484378"},{"key":"2023072610200722000_bjo-2023-323176v1.43","first-page":"956","article-title":"Massive increase in the stiffness of the human lens nucleus with age: the basis for presbyopia","volume":"10","author":"Heys","year":"2004","journal-title":"Mol Vis"},{"key":"2023072610200722000_bjo-2023-323176v1.44","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1016\/j.ebiom.2017.03.046","article-title":"Biological age predictors","volume":"21","author":"Jylh\u00e4v\u00e4","year":"2017","journal-title":"EBioMedicine"},{"key":"2023072610200722000_bjo-2023-323176v1.45","doi-asserted-by":"publisher","DOI":"10.1016\/j.molmed.2012.03.005"},{"key":"2023072610200722000_bjo-2023-323176v1.46","doi-asserted-by":"crossref","unstructured":"Islam S , Do MT , Frank BS , et al . \u0391-crystallin chaperone mimetic drugs inhibit lens \u0393-Crystallin aggregation: potential role for cataract prevention. J Biol Chem 2022;298:102417. doi:10.1016\/j.jbc.2022.102417","DOI":"10.1016\/j.jbc.2022.102417"},{"key":"2023072610200722000_bjo-2023-323176v1.47","doi-asserted-by":"publisher","DOI":"10.1111\/j.1755-3768.2012.02444.x"},{"key":"2023072610200722000_bjo-2023-323176v1.48","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1097\/ICU.0000000000000027","article-title":"New options for combined cataract and glaucoma surgery","volume":"25","author":"Budenz","year":"2014","journal-title":"Curr Opin Ophthalmol"}],"container-title":["British Journal of Ophthalmology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bjo-2023-323176","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,26]],"date-time":"2023-07-26T17:55:46Z","timestamp":1690394146000},"score":1,"resource":{"primary":{"URL":"https:\/\/bjo.bmj.com\/lookup\/doi\/10.1136\/bjo-2023-323176"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,26]]},"references-count":48,"alternative-id":["10.1136\/bjo-2023-323176"],"URL":"https:\/\/doi.org\/10.1136\/bjo-2023-323176","relation":{},"ISSN":["0007-1161","1468-2079"],"issn-type":[{"type":"print","value":"0007-1161"},{"type":"electronic","value":"1468-2079"}],"subject":[],"published":{"date-parts":[[2023,7,26]]}}}