{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T19:09:57Z","timestamp":1788808197431,"version":"build-2803163510"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Yanda Meng's King Abdullah University of Science and Technology (KAUST) Baseline Research","award":["BAS\/1\/1121-01-01"],"award-info":[{"award-number":["BAS\/1\/1121-01-01"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Med. Imaging"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1109\/tmi.2026.3710844","type":"journal-article","created":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T19:44:36Z","timestamp":1783453476000},"page":"4846-4860","source":"Crossref","is-referenced-by-count":0,"title":["DiffGeo-AOR: Diffusion-Optimized Medical Grading via Geometric Priors Enhanced Autoregressive Ordinal Regression"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6526-0928","authenticated-orcid":false,"given":"Qinkai","family":"Yu","sequence":"first","affiliation":[{"name":"King Abdullah University of Science and Technology (KAUST)","place":["Thuwal, Saudi Arabia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8264-9297","authenticated-orcid":false,"given":"He","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Liverpool","place":["Liverpool, U.K."],"department":["Eye and Vision Department"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8926-7833","authenticated-orcid":false,"given":"Yanyu","family":"Xu","sequence":"additional","affiliation":[{"name":"Shandong University","place":["Shandong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Wang","sequence":"additional","affiliation":[{"name":"National University of Singapore","place":["Queenstown, Singapore"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4357-4592","authenticated-orcid":false,"given":"Yitian","family":"Zhao","sequence":"additional","affiliation":[{"name":"Ningbo Cixi Institute of Biomedical Engineering. Chinese Academy of Sciences","place":["Cixi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9702-5524","authenticated-orcid":false,"given":"Huazhu","family":"Fu","sequence":"additional","affiliation":[{"name":"Institute of High-Performance Computing, Agency for Science, Technology and Research","place":["Connexis, Singapore"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0115-0724","authenticated-orcid":false,"given":"Xujiong","family":"Ye","sequence":"additional","affiliation":[{"name":"University of Exeter","place":["Exeter, U.K."],"department":["Computer Science Department"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3731-9168","authenticated-orcid":false,"given":"Aline","family":"Villavicencio","sequence":"additional","affiliation":[{"name":"University of Exeter","place":["Exeter, U.K."],"department":["Computer Science Department"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7566-1626","authenticated-orcid":false,"given":"Gregory Y. H.","family":"Lip","sequence":"additional","affiliation":[{"name":"University of Liverpool","place":["Liverpool, U.K."]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7873-0922","authenticated-orcid":false,"given":"Yalin","family":"Zheng","sequence":"additional","affiliation":[{"name":"University of Liverpool","place":["Liverpool, U.K."],"department":["Eye and Vision Department"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7344-2174","authenticated-orcid":false,"given":"Yanda","family":"Meng","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology (KAUST)","place":["Thuwal, Saudi Arabia"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.17216"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1001\/archopht.123.11.1570"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32239-7_6"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1016\/j.patrec.2020.11.008","article-title":"Rank consistent ordinal regression for neural networks with application to age estimation","volume":"140","author":"Cao","year":"2020","journal-title":"Pattern Recognit. Lett."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10044-023-01181-9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01368"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0003"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2559"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00283"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72378-0_62"},{"key":"ref11","first-page":"1691","article-title":"Generative pretraining from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref12","article-title":"Pix2seq: A language modeling framework for object detection","author":"Chen","year":"2021","journal-title":"arXiv:2109.10852"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32848"},{"key":"ref14","article-title":"An image is worth $16\\times 16$\n words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00539"},{"key":"ref16","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06555-x"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1797"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-05182-0_44"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44795-4_13"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.532"},{"key":"ref24","first-page":"1","article-title":"Order learning and its application to age estimation","volume-title":"Proc. 8th Int. Conf. Learn. Represent. (ICLR)","author":"Lim"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01820"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01216"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_1"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0786"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01448"},{"issue":"8","key":"ref31","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref32","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref33","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref34","article-title":"Qwen technical report","volume-title":"arXiv:2309.16609","author":"Bai","year":"2023"},{"key":"ref35","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2936410"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104167"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref41","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Tarvainen"},{"key":"ref42","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","volume":"33","author":"Ho"},{"key":"ref43","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv:2010.02502"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43987-2_10"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.06.011"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43904-9_42"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1177\/193229680900300315"},{"key":"ref48","article-title":"FairVision: Equitable deep learning for eye disease screening via fair identity scaling","author":"Luo","year":"2023","journal-title":"arXiv:2310.02492"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32570"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-13919-2"},{"key":"ref54","first-page":"1802","article-title":"Exploring the landscape of spatial robustness","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Engstrom"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102141"}],"container-title":["IEEE Transactions on Medical Imaging"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/42\/11676284\/11598822.pdf?arnumber=11598822","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T19:04:36Z","timestamp":1788807876000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11598822\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":55,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tmi.2026.3710844","relation":{},"ISSN":["1558-254X","0278-0062"],"issn-type":[{"value":"1558-254X","type":"electronic"},{"value":"0278-0062","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]}}}