{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T18:59:33Z","timestamp":1790189973411,"version":"4.1.0"},"reference-count":20,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"37","license":[{"start":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T00:00:00Z","timestamp":1757635200000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,12]]},"abstract":"<jats:p>\n                    T2 weighted magnetic resonance imaging has become a commonly used noninvasive examination method for the diagnosis of Polymyositis (PM). The data regarding the comparison of deep learning and radiomics in the diagnosis of PM is still lacking. This study investigates the feasibility of 3D convolutional neural network (CNN) in the prediction of PM, with comparison to radiomics. A total of 120 patients (with 60 PM) were from center A, and 30 (with 15 PM) were from B, and 46 (with 23 PM) were from C. The data from center A was used as training data, and data from B as validation data, and data from C as external test data. The magnetic resonance radiomics features of rectus femoris were obtained for all cases. The maximum correlation minimum redundancy and least absolute shrinkage and selection operator regression were used before establishing a radiomics score model. A 3D CNN classification model was trained with \u201cmonai\u201d based on 150 data with labels. A 3D Unet segmentation model was also trained with \u201cmonai\u201d based on 196 original data and their segmentation of rectus femoris. The accuracy on the external test data was compared between 2 methods by using the paired chi-square test. PM and non-PM cases did not differ in age or gender (\n                    <jats:italic toggle=\"yes\">P<\/jats:italic>\n                    \u2005&gt;\u2005.05). The 3D CNN classification model achieved accuracy of 97% in validation data. The sensitivity, specificity, accuracy and positive predictive value of the 3D CNN classification model in the external test data were 96% (22\/23), 91% (21\/23), 93% (43\/46), and 92% (22\/24), respectively. The radiomics score achieved accuracy of 90% in the validation data. The sensitivity, specificity, accuracy, and positive predictive value of the radiomics score in the external test data were 70% (16\/23), 65% (15\/23), 67% (31\/46), and 67% (16\/24), respectively, significantly lower than that of CNN model (\n                    <jats:italic toggle=\"yes\">P<\/jats:italic>\n                    \u2005=\u2005.035). The 3D segmentation model for rectus femoris on T2 weighted magnetic resonance images was obtained with dice similarity coefficient of 0.71. 3D CNN model is not inferior to radiomics score in the prediction of PM. The combination of deep learning and radiomics is recommended for the evaluation of PM in future clinical practice.\n                  <\/jats:p>","DOI":"10.1097\/md.0000000000044496","type":"journal-article","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T21:01:18Z","timestamp":1757970078000},"page":"e44496","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":0,"title":["The comparison of deep learning and radiomics in the prediction of polymyositis"],"prefix":"10.1097","volume":"104","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9740-499X","authenticated-orcid":false,"given":"Gang","family":"Wu","sequence":"first","affiliation":[{"name":"Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Basen","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7926-214X","authenticated-orcid":false,"given":"Ting","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Radiology, The Central Hospital of Wuhan, Tongji Medical College Affiliated to Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liangjin","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Radiology, Hubei No. 3 People\u2019s Hospital of Jianghan University, Wuhan, China."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","reference":[{"key":"R1-20260923","doi-asserted-by":"crossref","first-page":"537","DOI":"10.1097\/BOR.0000000000000837","article-title":"Polymyositis: does it really exist as a distinct clinical subset?","volume":"33","author":"Leclair","year":"2021","journal-title":"Curr Opin Rheumatol"},{"key":"R2-20260923","doi-asserted-by":"crossref","first-page":"1041","DOI":"10.1007\/s12098-023-04896-z","article-title":"Idiopathic inflammatory myopathies.","volume":"91","author":"Balan","year":"2023","journal-title":"Indian J Pediatr"},{"key":"R3-20260923","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1038\/s41572-021-00321-x","article-title":"Idiopathic inflammatory myopathies.","volume":"7","author":"Lundberg","year":"2021","journal-title":"Nat Rev Dis Primers"},{"key":"R4-20260923","first-page":"S241","article-title":"Evolving classification and role of muscle biopsy in diagnosis of inflammatory myopathies.","volume":"65","author":"Swain","year":"2022","journal-title":"Indian J Pathol Microbiol"},{"key":"R5-20260923","doi-asserted-by":"crossref","first-page":"368","DOI":"10.3390\/tomography10030029","article-title":"Intravoxel incoherent motion diffusion-weighted MRI, fat quantification, and electromyography: correlation in polymyositis and dermatomyositis.","volume":"10","author":"Kim","year":"2024","journal-title":"Tomography"},{"key":"R6-20260923","doi-asserted-by":"crossref","first-page":"2684","DOI":"10.1093\/rheumatology\/keae125","article-title":"Magnetic resonance imaging patterns revealing muscle pathology and clinical features in idiopathic inflammatory myopathies.","volume":"63","author":"Shimoyama","year":"2024","journal-title":"Rheumatology (Oxford)"},{"key":"R7-20260923","doi-asserted-by":"crossref","first-page":"9821","DOI":"10.1038\/s41598-021-89311-3","article-title":"Texture analysis of muscle MRI: machine learning-based classifications in idiopathic inflammatory myopathies.","volume":"11","author":"Nagawa","year":"2021","journal-title":"Sci Rep"},{"key":"R8-20260923","doi-asserted-by":"crossref","first-page":"e003271","DOI":"10.1136\/rmdopen-2023-003271","article-title":"Intramuscular lesions in musculoskeletal MRI as a favourable prognostic sign in patients with anti-MDA5 antibody-positive dermatomyositis.","volume":"9","author":"Oto","year":"2023","journal-title":"RMD Open"},{"key":"R9-20260923","doi-asserted-by":"crossref","first-page":"632","DOI":"10.1177\/02841851241244507","article-title":"Value of radiomics-based automatic grading of muscle edema in polymyositis\/dermatomyositis based on MRI fat-suppressed T2-weighted images.","volume":"65","author":"Zhang","year":"2024","journal-title":"Acta Radiol"},{"key":"R10-20260923","doi-asserted-by":"crossref","first-page":"3186","DOI":"10.1007\/s00415-024-12191-w","article-title":"Quantitative whole-body muscle MRI in idiopathic inflammatory myopathies including polymyositis with mitochondrial pathology: indications for a disease spectrum.","volume":"271","author":"Zierer","year":"2024","journal-title":"J Neurol"},{"key":"R11-20260923","doi-asserted-by":"crossref","first-page":"2350","DOI":"10.1007\/s00330-022-09254-9","article-title":"Assessment of idiopathic inflammatory myopathy using a deep learning method for muscle T2 mapping segmentation.","volume":"33","author":"Wang","year":"2023","journal-title":"Eur Radiol"},{"key":"R12-20260923","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1016\/j.meatsci.2018.03.020","article-title":"Predicting pork loin intramuscular fat using computer vision system.","volume":"143","author":"Liu","year":"2018","journal-title":"Meat Sci"},{"key":"R13-20260923","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1186\/s12880-023-01056-9","article-title":"Identification of radiomic biomarkers in a set of four skeletal muscle groups on Dixon MRI of the NAKO MR study.","volume":"23","author":"Fischer","year":"2023","journal-title":"BMC Med Imaging"},{"key":"R14-20260923","doi-asserted-by":"crossref","first-page":"2103","DOI":"10.1002\/mp.13451","article-title":"Automated pectoral muscle identification on MLO-view mammograms: comparison of deep neural network to conventional computer vision.","volume":"46","author":"Ma","year":"2019","journal-title":"Med Phys"},{"key":"R15-20260923","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1186\/s42490-019-0026-8","article-title":"An automatic nuclei segmentation method based on deep convolutional neural networks for histopathology images.","volume":"1","author":"Jung","year":"2019","journal-title":"BMC Biomed Eng"},{"key":"R16-20260923","doi-asserted-by":"crossref","first-page":"333","DOI":"10.21037\/atm-22-534","article-title":"A convolutional neural network-based COVID-19 detection method using chest CT images.","volume":"10","author":"Cao","year":"2022","journal-title":"Ann Transl Med"},{"key":"R17-20260923","doi-asserted-by":"crossref","first-page":"809","DOI":"10.1097\/SCS.0000000000009105","article-title":"Radiomics and artificial intelligence study of masseter muscle segmentation in patients with hemifacial microsomia.","volume":"34","author":"Han","year":"2023","journal-title":"J Craniofac Surg"},{"key":"R18-20260923","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1002\/mus.26827","article-title":"Semi-automated volumetry of MRI serves as a biomarker in neuromuscular patients.","volume":"61","author":"M\u00fcller","year":"2020","journal-title":"Muscle Nerve"},{"key":"R19-20260923","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/j.semcancer.2023.07.003","article-title":"Artificial intelligence-based radiomics in bone tumors: technical advances and clinical application.","volume":"95","author":"Meng","year":"2023","journal-title":"Semin Cancer Biol"},{"key":"R20-20260923","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1016\/j.rcl.2021.11.011","article-title":"Bone and soft tissue tumors: horizons in radiomics and artificial intelligence.","volume":"60","author":"Richardson","year":"2022","journal-title":"Radiol Clin North Am"}],"container-title":["Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.ovid.com\/10.1097\/MD.0000000000044496","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T18:01:30Z","timestamp":1790186490000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ovid.com\/10.1097\/MD.0000000000044496"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,12]]},"references-count":20,"journal-issue":{"issue":"37","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.1097\/md.0000000000044496","relation":{},"ISSN":["1536-5964","0025-7974"],"issn-type":[{"value":"1536-5964","type":"electronic"},{"value":"0025-7974","type":"print"}],"subject":[],"published":{"date-parts":[[2025,9,12]]},"assertion":[{"value":"2025-06-27","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-26","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}