{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T23:15:17Z","timestamp":1787008517121,"version":"build-2736575974"},"reference-count":30,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T00:00:00Z","timestamp":1748995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"name":"National High-Level Hospital Clinical Research Funding","award":["2022-PUMCH-C-021"],"award-info":[{"award-number":["2022-PUMCH-C-021"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82173449"],"award-info":[{"award-number":["82173449"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005089","name":"Natural Science Foundation of Beijing","doi-asserted-by":"publisher","award":["7232114"],"award-info":[{"award-number":["7232114"]}],"id":[{"id":"10.13039\/501100005089","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005089","name":"Natural Science Foundation of Beijing","doi-asserted-by":"publisher","award":["L242106"],"award-info":[{"award-number":["L242106"]}],"id":[{"id":"10.13039\/501100005089","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,17]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Mycosis fungoides (MF) is the most common type of cutaneous T-cell lymphoma, and early-stage MF is difficult to differentiate from erythematous inflammatory disease. With the exception of biopsy, noninvasive information such as a patient\u2019s medical history and clinical and dermoscopic images is of great significance for early diagnosis of MF. However, there is a lack of diagnostic models based on convolutional neural networks that can use multimodal information.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>To develop an artificial intelligence (AI) deep learning model based on multimodal information, to verify its classification efficiency and to construct an AI-aided early diagnostic model of MF and inflammatory skin diseases for dermatologists.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This was a single-centre retrospective study based on multimodal information, including clinical information, clinical images and dermoscopic images. A total of 1157 cases of MF and inflammatory diseases were collected, including 2452 clinical images, 6550 dermoscopic images and corresponding clinical data. To assess the practicality of using AI models to help with clinical diagnoses, we carried out a comparative study involving three distinct groups: (i) dermatologists, (ii) the AI model and (iii) dermatologists + AI model. The dermatologist group comprised 23 dermatologists with a certain level of expertise and more than 10\u2005h of systematic dermoscopy training. We used RegNetY400MF as the backbone network to extract features from the dermoscopic and clinical images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The AI model demonstrated higher levels of total accuracy, precision, sensitivity and specificity in the classification of MF and other inflammatory skin diseases than participating dermatologists. A significant enhancement was noticed in the average accuracy, sensitivity and specificity for MF and inflammatory diseases in the \u2018dermatologist + AI\u2019 group, with values of 82.9%, 86.2% and 96.5%, respectively, compared with 71.5%, 74.6% and 94.1%, respectively, in the \u2018dermatologist-only\u2019 group. A more accurate diagnosis of each disease was also achieved by the multiclassification model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The results indicate that our AI model has a significantly strong discriminative ability to assist dermatologists with improving diagnostic accuracy in early-stage MF and common inflammatory skin diseases.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bjd\/ljaf212","type":"journal-article","created":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T07:47:59Z","timestamp":1749023279000},"page":"968-977","source":"Crossref","is-referenced-by-count":15,"title":["Early diagnosis model of mycosis fungoides and five inflammatory skin diseases based on a multimodal data-based convolutional neural network"],"prefix":"10.1093","volume":"193","author":[{"given":"Zhaorui","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Dermatology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, National Clinical Research Center for Dermatologic and Immunologic Diseases , Beijing ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yilan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Image Processing Center, School of Astronautics, Beihang University , Beijing ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Wang","sequence":"additional","affiliation":[{"name":"Image Processing Center, School of Astronautics, Beihang University , Beijing ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5681-2345","authenticated-orcid":false,"given":"Fengying","family":"Xie","sequence":"additional","affiliation":[{"name":"Image Processing Center, School of Astronautics, Beihang University , Beijing ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8219-2429","authenticated-orcid":false,"given":"Jie","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Dermatology, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, National Clinical Research Center for Dermatologic and Immunologic Diseases , Beijing ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,6,4]]},"reference":[{"key":"2025101708275573000_ljaf212-B1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.12968\/hmed.2021.0149","article-title":"Cutaneous T-cell lymphoma: diagnosing subtypes and the challenges","volume":"83","author":"Hague","year":"2022","journal-title":"Br J Hosp Med (Lond)"},{"key":"2025101708275573000_ljaf212-B2","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1016\/j.clindermatol.2019.01.004","article-title":"Mycosis fungoides: a great imitator","volume":"37","author":"Hodak","year":"2019","journal-title":"Clin Dermatol"},{"key":"2025101708275573000_ljaf212-B3","doi-asserted-by":"crossref","first-page":"17","DOI":"10.3390\/jcm10010017","article-title":"Morphologic features of cutaneous T-cell lymphomas using dermoscopy and high frequency ultrasound","volume":"10","author":"Wohlmuth-Wieser","year":"2020","journal-title":"J Clin Med"},{"key":"2025101708275573000_ljaf212-B4","doi-asserted-by":"crossref","first-page":"900","DOI":"10.1038\/s41591-020-0842-3","article-title":"A deep learning system for differential diagnosis of skin diseases","volume":"26","author":"Liu","year":"2020","journal-title":"Nat Med"},{"key":"2025101708275573000_ljaf212-B5","first-page":"244","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2023. Lecture Notes in Computer Science","author":"Zhang","year":"2023"},{"key":"2025101708275573000_ljaf212-B6","doi-asserted-by":"crossref","first-page":"102301","DOI":"10.1016\/j.media.2021.102301","article-title":"Dermoscopic image retrieval based on rotation-invariance deep hashing","volume":"77","author":"Zhang","year":"2022","journal-title":"Med Image Anal"},{"key":"2025101708275573000_ljaf212-B7","doi-asserted-by":"crossref","first-page":"7160","DOI":"10.1109\/ACCESS.2019.2962812","article-title":"Deep learning-based system for automatic melanoma detection","volume":"8","author":"Adegun","year":"2019","journal-title":"IEEE Access"},{"key":"2025101708275573000_ljaf212-B8","doi-asserted-by":"crossref","first-page":"107083","DOI":"10.1016\/j.compbiomed.2023.107083","article-title":"Deep learning in computational dermatopathology of melanoma: a technical systematic literature review","volume":"163","author":"Sauter","year":"2023","journal-title":"Comput Biol Med"},{"key":"2025101708275573000_ljaf212-B9","doi-asserted-by":"crossref","first-page":"104924","DOI":"10.1016\/j.compbiomed.2021.104924","article-title":"A convolutional neural network trained with dermoscopic images of psoriasis performed on par with 230 dermatologists","volume":"139","author":"Yang","year":"2021","journal-title":"Comput Biol Med"},{"key":"2025101708275573000_ljaf212-B10","doi-asserted-by":"crossref","first-page":"2268","DOI":"10.1111\/jdv.20031","article-title":"Human-multimodal deep learning collaboration in \u2018precise\u2019 diagnosis of lupus erythematosus subtypes and similar skin diseases","volume":"38","author":"Li","year":"2024","journal-title":"J Eur Acad Dermatol Venereol"},{"key":"2025101708275573000_ljaf212-B11","doi-asserted-by":"crossref","first-page":"108990","DOI":"10.1016\/j.patcog.2022.108990","article-title":"Co-attention fusion network for multimodal skin cancer diagnosis","volume":"133","author":"He","year":"2023","journal-title":"Pattern Recognit"},{"key":"2025101708275573000_ljaf212-B12","doi-asserted-by":"crossref","first-page":"102535","DOI":"10.1016\/j.media.2022.102535","article-title":"Adversarial multimodal fusion with attention mechanism for skin lesion classification using clinical and dermoscopic images","volume":"81","author":"Wang","year":"2022","journal-title":"Med Image Anal"},{"key":"2025101708275573000_ljaf212-B13","doi-asserted-by":"crossref","first-page":"106712","DOI":"10.1016\/j.compbiomed.2023.106712","article-title":"TFormer: a throughout fusion transformer for multi-modal skin lesion diagnosis","volume":"157","author":"Zhang","year":"2023","journal-title":"Comput Biol Med"},{"key":"2025101708275573000_ljaf212-B14","doi-asserted-by":"crossref","first-page":"107315","DOI":"10.1016\/j.cmpb.2022.107315","article-title":"Skin lesion classification based on two-modal images using a multi-scale fully-shared fusion network","volume":"229","author":"Yang","year":"2023","journal-title":"Comput Methods Programs Biomed"},{"key":"2025101708275573000_ljaf212-B15","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2018.2824327","article-title":"7-point checklist and skin lesion classification using multitask multimodal neural nets","author":"Kawahara","year":"2018","journal-title":"IEEE J Biomed Health Inform"},{"key":"2025101708275573000_ljaf212-B16","author":"Zoph"},{"key":"2025101708275573000_ljaf212-B17","author":"Kingma"},{"key":"2025101708275573000_ljaf212-B18","first-page":"770","volume-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"2025101708275573000_ljaf212-B19","first-page":"5987","volume-title":"Aggregated residual transformations for deep neural networks","author":"Xie","year":"2017"},{"key":"2025101708275573000_ljaf212-B20","first-page":"2261","volume-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"2025101708275573000_ljaf212-B21","first-page":"2818","volume-title":"Rethinking the inception architecture for computer vision","author":"Szegedy","year":"2016"},{"key":"2025101708275573000_ljaf212-B22","first-page":"6105","article-title":"EfficientNet: rethinking model scaling for convolutional neural networks","volume":"97","author":"Tan","year":"2019","journal-title":"PMLR"},{"key":"2025101708275573000_ljaf212-B23","first-page":"9992","volume-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"2025101708275573000_ljaf212-B24","first-page":"11966","volume-title":"A ConvNet for the 2020s","author":"Liu","year":"2022"},{"key":"2025101708275573000_ljaf212-B25","doi-asserted-by":"crossref","first-page":"617","DOI":"10.1111\/j.1468-3083.2012.04499.x","article-title":"Dermoscopy of early stage mycosis fungoides","volume":"27","author":"Lallas","year":"2013","journal-title":"J Eur Acad Dermatol Venereol"},{"key":"2025101708275573000_ljaf212-B26","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1111\/ijd.13860","article-title":"Dermoscopic characterization of cutaneous lymphomas: a pilot survey","volume":"57","author":"Ghahramani","year":"2018","journal-title":"Int J Dermatol"},{"key":"2025101708275573000_ljaf212-B27","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1111\/ced.13680","article-title":"Dermoscopic patterns of early-stage mycosis fungoides in a Chinese population","volume":"44","author":"Xu","year":"2019","journal-title":"Clin Exp Dermatol"},{"key":"2025101708275573000_ljaf212-B28","doi-asserted-by":"crossref","first-page":"843","DOI":"10.1111\/ijd.14925","article-title":"Dermoscopy in differential diagnosis of inflammatory dermatoses and mycosis fungoides","volume":"59","author":"Bilgic","year":"2020","journal-title":"Int J Dermatol"},{"key":"2025101708275573000_ljaf212-B29","doi-asserted-by":"crossref","first-page":"1091","DOI":"10.1007\/s13555-022-00716-y","article-title":"Parapsoriasis \u2013 a diagnosis with an identity crisis: a narrative review","volume":"12","author":"Chairatchaneeboon","year":"2022","journal-title":"Dermatol Ther (Heidelb)"},{"key":"2025101708275573000_ljaf212-B30","doi-asserted-by":"crossref","first-page":"102307","DOI":"10.1016\/j.media.2021.102307","article-title":"FusionM4Net: a multi-stage multi-modal learning algorithm for multi-label skin lesion classification","volume":"76","author":"Tang","year":"2022","journal-title":"Med Image Anal"}],"container-title":["British Journal of Dermatology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bjd\/advance-article-pdf\/doi\/10.1093\/bjd\/ljaf212\/63436723\/ljaf212.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bjd\/article-pdf\/193\/5\/968\/63436723\/ljaf212.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bjd\/article-pdf\/193\/5\/968\/63436723\/ljaf212.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T12:28:09Z","timestamp":1760704089000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bjd\/article\/193\/5\/968\/8156824"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,4]]},"references-count":30,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,6,4]]},"published-print":{"date-parts":[[2025,10,17]]}},"URL":"https:\/\/doi.org\/10.1093\/bjd\/ljaf212","relation":{},"ISSN":["0007-0963","1365-2133"],"issn-type":[{"value":"0007-0963","type":"print"},{"value":"1365-2133","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,11]]},"published":{"date-parts":[[2025,6,4]]}}}