{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:51:41Z","timestamp":1792788701292,"version":"4.5.0"},"reference-count":36,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T00:00:00Z","timestamp":1791158400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004735","name":"Natural Science Foundation of Hunan Province","doi-asserted-by":"publisher","award":["2025JJ50596"],"award-info":[{"award-number":["2025JJ50596"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"publisher"}]},{"name":"High-Level Talent Support Program of Hunan Cancer Hospital","award":["20250805-1002"],"award-info":[{"award-number":["20250805-1002"]}],"id":[{"id":"https:\/\/ror.org\/025020z88","id-type":"ROR","asserted-by":"crossref"}]},{"name":"High-Level Talent Support Program of Hunan Cancer Hospital","award":["20250806-1002"],"award-info":[{"award-number":["20250806-1002"]}],"id":[{"id":"https:\/\/ror.org\/025020z88","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["www.plosdigitalhealth.org"],"crossmark-restriction":false},"short-container-title":["PLOS Digit Health"],"abstract":"<jats:p>\n                    Predicting response to induction chemotherapy (IC) and overall survival (OS) is critical for optimizing treatment in patients with locally advanced nasopharyngeal carcinoma (LANPC). This study aimed to develop and validate a multi-task deep learning model integrating pretreatment MRI and whole slide images (WSIs) to predict IC response and OS in LANPC. Pretreatment MRI and WSIs from 404 patients with LANPC were retrospectively collected to construct a multi-task model (MoEMIL) for the simultaneous prediction of early IC response and OS. In our cohort, no progressive disease cases were observed; therefore, the poor responder group consisted exclusively of patients with stable disease. MoEMIL employed multi-instance learning to process WSIs, PyRadiomics and a convolutional neural network (ResNet50) to extract MRI features, and fused multimodal features through a multi-gate mixture-of-experts architecture. Clustering-constrained attention multiple instance learning and gradient-weighted class activation mapping were applied for visualization and interpretation. MoEMIL effectively stratified patients into good and poor IC response groups, achieving areas under the curve of 0.917, 0.869, and 0.801 in the train, validation, and test sets, respectively. In the test set, MoEMIL significantly outperformed the deep learning radiomics model and TNM staging for both endpoints. Compared to the Pathomics model, MoEMIL achieved significant improvement for OS (\n                    <jats:italic>P<\/jats:italic>\n                    \u2009=\u20090.0049) and borderline improvement for IC response (\n                    <jats:italic>P<\/jats:italic>\n                    \u2009=\u20090.064). The model could stratify patients into high- and low-risk OS groups (\n                    <jats:italic>P\u2009&lt;<\/jats:italic>\n                    \u20090.05). MoEMIL might be an adjunctive tool for early induction chemotherapy response prediction and prognostic stratification in LANPC.\n                  <\/jats:p>","DOI":"10.1371\/journal.pdig.0001378","type":"journal-article","created":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T17:36:25Z","timestamp":1791221785000},"page":"e0001378","update-policy":"https:\/\/doi.org\/10.1371\/journal.pdig.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-task deep learning integrating pretreatment MRI and whole slide images predicts induction chemotherapy response and survival in locally advanced nasopharyngeal carcinoma"],"prefix":"10.1371","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9543-6389","authenticated-orcid":true,"given":"Jing","family":"Hou","sequence":"first","affiliation":[{"name":"Central South University","place":["Changsha, Hunan, People's Republic of China"],"department":["Department of Diagnostic Radiology, Hunan Cancer Hospital and the Affiliated Cancer Hospital of Xiangya School of Medicine"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaochun","family":"Yi","sequence":"additional","affiliation":[{"name":"Central South University","place":["Changsha, Hunan, People's Republic of China"],"department":["Department of Diagnostic Radiology, Hunan Cancer Hospital and the Affiliated Cancer Hospital of Xiangya School of Medicine"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Congrui","family":"Li","sequence":"additional","affiliation":[{"name":"Central South University","place":["Changsha, Hunan, People's Republic of China"],"department":["Department of Diagnostic Radiology, Hunan Cancer Hospital and the Affiliated Cancer Hospital of Xiangya School of Medicine"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junjian","family":"Li","sequence":"additional","affiliation":[{"name":"Central South University","place":["Changsha, People's Republic of China"],"department":["Hunan Provincial Key Laboratory on Bioinformatics, School of Computer Science and Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Cao","sequence":"additional","affiliation":[{"name":"Central South University","place":["Changsha, Hunan, People's Republic of China"],"department":["Department of Health Service Center, Hunan Cancer Hospital and the Affiliated Cancer Hospital of Xiangya School of Medicine"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Lu","sequence":"additional","affiliation":[{"name":"Central South University","place":["Changsha, Hunan, People's Republic of China"],"department":["Department of Diagnostic Radiology, Hunan Cancer Hospital and the Affiliated Cancer Hospital of Xiangya School of Medicine"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4502-1027","authenticated-orcid":true,"given":"Xiaoping","family":"Yu","sequence":"additional","affiliation":[{"name":"Central South University","place":["Changsha, Hunan, People's Republic of China"],"department":["Department of Diagnostic Radiology, Hunan Cancer Hospital and the Affiliated Cancer Hospital of Xiangya School of Medicine"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,10,5]]},"reference":[{"issue":"2","key":"pdig.0001378.ref001","doi-asserted-by":"crossref","DOI":"10.1016\/S2214-109X(19)30488-7","article-title":"Global burden of cancer attributable to infections in 2018: A worldwide incidence analysis","volume":"8","author":"C de Martel","year":"2020","journal-title":"Lancet Glob Health"},{"issue":"10192","key":"pdig.0001378.ref002","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/S0140-6736(19)30956-0","article-title":"Nasopharyngeal carcinoma","volume":"394","author":"Y-P Chen","year":"2019","journal-title":"Lancet"},{"issue":"7","key":"pdig.0001378.ref003","doi-asserted-by":"crossref","first-page":"873","DOI":"10.6004\/jnccn.2020.0031","article-title":"Head and neck cancers, version 2.2020, NCCN clinical practice guidelines in oncology","volume":"18","author":"DG Pfister","year":"2020","journal-title":"J Natl Compr Canc Netw"},{"issue":"7","key":"pdig.0001378.ref004","doi-asserted-by":"crossref","first-page":"913","DOI":"10.6004\/jnccn.2017.0121","article-title":"Validation of the 8th Edition of the UICC\/AJCC staging system for nasopharyngeal carcinoma from endemic areas in the intensity-modulated radiotherapy era","volume":"15","author":"L-L Tang","year":"2017","journal-title":"J Natl Compr Canc Netw"},{"key":"pdig.0001378.ref005","doi-asserted-by":"crossref","first-page":"24835","DOI":"10.1038\/srep24835","article-title":"The tumour response to induction chemotherapy has prognostic value for long-term survival outcomes after intensity-modulated radiation therapy in nasopharyngeal carcinoma","volume":"6","author":"H Peng","year":"2016","journal-title":"Sci Rep"},{"issue":"3","key":"pdig.0001378.ref006","doi-asserted-by":"crossref","first-page":"464","DOI":"10.1016\/j.ccell.2023.12.020","article-title":"Refining the 8th edition TNM classification for EBV related nasopharyngeal carcinoma","volume":"42","author":"X-J Du","year":"2024","journal-title":"Cancer Cell"},{"issue":"2","key":"pdig.0001378.ref007","doi-asserted-by":"crossref","first-page":"100206","DOI":"10.1016\/j.metrad.2026.100206","article-title":"Enhancing the prognosis of nasopharyngeal carcinoma using intra- and peritumoral radiomics","volume":"4","author":"S Khongwirotphan","year":"2026","journal-title":"Meta-Radiology"},{"issue":"2","key":"pdig.0001378.ref008","article-title":"A serial MRI-based deep learning model to predict survival in patients with locoregionally advanced nasopharyngeal carcinoma","volume":"7","author":"J Kou","year":"2025","journal-title":"Radiol Artif Intell"},{"key":"pdig.0001378.ref009","doi-asserted-by":"crossref","first-page":"111223","DOI":"10.1016\/j.radonc.2025.111223","article-title":"NPC-SurvAI: A fully automated deep learning framework for prognostic prediction and risk stratification in patients with nasopharyngeal carcinoma","volume":"214","author":"J You","year":"2026","journal-title":"Radiother Oncol"},{"issue":"1","key":"pdig.0001378.ref010","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1186\/s41747-023-00325-0","article-title":"Are deep models in radiomics performing better than generic models? A systematic review","volume":"7","author":"A Demircio\u011flu","year":"2023","journal-title":"Eur Radiol Exp"},{"issue":"21","key":"pdig.0001378.ref011","doi-asserted-by":"crossref","first-page":"3623","DOI":"10.3390\/cancers16213623","article-title":"Artificial intelligence in head and neck cancer diagnosis: A comprehensive review with emphasis on radiomics, histopathological, and molecular applications","volume":"16","author":"G Broggi","year":"2024","journal-title":"Cancers (Basel)"},{"key":"pdig.0001378.ref012","article-title":"BioCompNet: A deep learning workflow enabling automated body composition analysis toward precision management of cardiometabolic disorders","volume":"6","author":"J Wei","year":"2025","journal-title":"Cyborg Bionic Syst"},{"issue":"8","key":"pdig.0001378.ref013","doi-asserted-by":"crossref","first-page":"5121","DOI":"10.1007\/s00330-025-11396-5","article-title":"An interpretable machine learning model assists in predicting induction chemotherapy response and survival for locoregionally advanced nasopharyngeal carcinoma using MRI: A multicenter study","volume":"35","author":"H Liao","year":"2025","journal-title":"Eur Radiol"},{"issue":"1","key":"pdig.0001378.ref014","doi-asserted-by":"crossref","first-page":"537","DOI":"10.1007\/s00330-019-06211-x","article-title":"MRI-based radiomics nomogram may predict the response to induction chemotherapy and survival in locally advanced nasopharyngeal carcinoma","volume":"30","author":"L Zhao","year":"2020","journal-title":"Eur Radiol"},{"issue":"5","key":"pdig.0001378.ref015","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1093\/jnci\/djaa149","article-title":"A prognostic predictive system based on deep learning for locoregionally advanced nasopharyngeal carcinoma","volume":"113","author":"M Qiang","year":"2021","journal-title":"J Natl Cancer Inst"},{"key":"pdig.0001378.ref016","doi-asserted-by":"crossref","first-page":"109042","DOI":"10.1016\/j.compbiomed.2024.109042","article-title":"MBFusion: Multi-modal balanced fusion and multi-task learning for cancer diagnosis and prognosis","volume":"181","author":"Z Zhang","year":"2024","journal-title":"Comput Biol Med"},{"issue":"13","key":"pdig.0001378.ref017","doi-asserted-by":"crossref","first-page":"2527","DOI":"10.1158\/0008-5472.CAN-24-4190","article-title":"Multitask deep learning based on longitudinal CT images facilitates prediction of lymph node metastasis and survival in chemotherapy-treated gastric cancer","volume":"85","author":"B Qiu","year":"2025","journal-title":"Cancer Res"},{"issue":"5","key":"pdig.0001378.ref018","article-title":"Predicting peritoneal recurrence and disease-free survival from CT images in gastric cancer with multitask deep learning: A retrospective study","volume":"4","author":"Y Jiang","year":"2022","journal-title":"Lancet Digit Health"},{"issue":"1","key":"pdig.0001378.ref019","doi-asserted-by":"crossref","first-page":"1523","DOI":"10.1038\/s41467-025-56822-w","article-title":"Medical multimodal multitask foundation model for lung cancer screening","volume":"16","author":"C Niu","year":"2025","journal-title":"Nat Commun"},{"issue":"1","key":"pdig.0001378.ref020","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1186\/s12885-023-10817-2","article-title":"Development and validation of a radiopathomic model for predicting pathologic complete response to neoadjuvant chemotherapy in breast cancer patients","volume":"23","author":"J Zhang","year":"2023","journal-title":"BMC Cancer"},{"issue":"3","key":"pdig.0001378.ref021","article-title":"Development and validation of a multimodality model based on whole-slide imaging and biparametric MRI for predicting postoperative biochemical recurrence in prostate cancer","volume":"6","author":"C Hu","year":"2024","journal-title":"Radiol Imaging Cancer"},{"issue":"1","key":"pdig.0001378.ref022","article-title":"Development and validation of a radiopathomics model to predict pathological complete response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer: A multicentre observational study","volume":"4","author":"L Feng","year":"2022","journal-title":"Lancet Digit Health"},{"key":"pdig.0001378.ref023","doi-asserted-by":"crossref","first-page":"103561","DOI":"10.1016\/j.media.2025.103561","article-title":"M4: Multi-proxy multi-gate mixture of experts network for multiple instance learning in histopathology image analysis","volume":"103","author":"J Li","year":"2025","journal-title":"Med Image Anal"},{"key":"pdig.0001378.ref024","doi-asserted-by":"crossref","first-page":"110949","DOI":"10.1016\/j.radonc.2025.110949","article-title":"Deep learning radiopathomics based on pretreatment MRI and whole slide images for predicting overall survival in locally advanced nasopharyngeal carcinoma","volume":"209","author":"X Yi","year":"2025","journal-title":"Radiother Oncol"},{"issue":"2","key":"pdig.0001378.ref025","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1016\/j.ejca.2008.10.026","article-title":"New response evaluation criteria in solid tumours: Revised RECIST guideline (version 1.1)","volume":"45","author":"EA Eisenhauer","year":"2009","journal-title":"Eur J Cancer"},{"issue":"2","key":"pdig.0001378.ref026","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1148\/radiol.2020191145","article-title":"The image biomarker standardization initiative: Standardized quantitative radiomics for high-throughput image-based phenotyping","volume":"295","author":"A Zwanenburg","year":"2020","journal-title":"Radiology"},{"issue":"6","key":"pdig.0001378.ref027","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1038\/s41551-020-00682-w","article-title":"Data-efficient and weakly supervised computational pathology on whole-slide images","volume":"5","author":"MY Lu","year":"2021","journal-title":"Nat Biomed Eng"},{"issue":"11","key":"pdig.0001378.ref028","doi-asserted-by":"crossref","first-page":"3749","DOI":"10.1038\/s41591-025-03982-3","article-title":"A multimodal whole-slide foundation model for pathology","volume":"31","author":"T Ding","year":"2025","journal-title":"Nat Med"},{"key":"pdig.0001378.ref029","doi-asserted-by":"crossref","first-page":"102521","DOI":"10.1016\/j.media.2022.102521","article-title":"DARC: Deep adaptive regularized clustering for histopathological image classification","volume":"80","author":"J Li","year":"2022","journal-title":"Med Image Anal"},{"issue":"7","key":"pdig.0001378.ref030","doi-asserted-by":"crossref","first-page":"5095","DOI":"10.1109\/JBHI.2025.3552640","article-title":"CA2CL: Cluster-aware adversarial contrastive learning for pathological image analysis","volume":"29","author":"J Li","year":"2025","journal-title":"IEEE J Biomed Health Inform"},{"issue":"9","key":"pdig.0001378.ref031","doi-asserted-by":"crossref","first-page":"3126","DOI":"10.1109\/TPAMI.2020.2979450","article-title":"Bias in cross-entropy-based training of deep survival networks","volume":"43","author":"SG Zadeh","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"pdig.0001378.ref032","first-page":"618","article-title":"Grad-cam: Visual explanations from deep networks via gradient-based localization.","volume-title":"Proceedings of the IEEE international conference on computer vision","author":"RR Selvaraju","year":"2017"},{"issue":"7","key":"pdig.0001378.ref033","doi-asserted-by":"crossref","first-page":"1310","DOI":"10.3390\/medicina61071310","article-title":"Integrating radiomics and deep-learning for prognostic evaluation in nasopharyngeal carcinoma","volume":"61","author":"IM Pu\u0219ca\u0219","year":"2025","journal-title":"Medicina (Kaunas)"},{"key":"pdig.0001378.ref034","doi-asserted-by":"crossref","first-page":"105663","DOI":"10.1016\/j.ebiom.2025.105663","article-title":"Deep learning informed multimodal fusion of radiology and pathology to predict outcomes in HPV-associated oropharyngeal squamous cell carcinoma","volume":"114","author":"B Song","year":"2025","journal-title":"EBioMedicine"},{"key":"pdig.0001378.ref035","doi-asserted-by":"crossref","first-page":"106496","DOI":"10.1016\/j.compbiomed.2022.106496","article-title":"Multi-task deep learning for medical image computing and analysis: A review","volume":"153","author":"Y Zhao","year":"2023","journal-title":"Comput Biol Med"},{"key":"pdig.0001378.ref036","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1186\/s40880-016-0103-5","article-title":"A new prognostic histopathologic classification of nasopharyngeal carcinoma","volume":"35","author":"H-Y Wang","year":"2016","journal-title":"Chin J Cancer"}],"container-title":["PLOS Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001378","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T17:36:31Z","timestamp":1791221791000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001378"}},"subtitle":[],"editor":[{"given":"Feng","family":"Liu","sequence":"first","affiliation":[{"name":"Tianjin Medical University General Hospital","place":["CHINA"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,10,5]]},"references-count":36,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,10,5]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pdig.0001378","relation":{},"ISSN":["2767-3170"],"issn-type":[{"value":"2767-3170","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,5]]}}}