{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T01:35:44Z","timestamp":1793669744703,"version":"4.5.1"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,11,16]],"date-time":"2022-11-16T00:00:00Z","timestamp":1668556800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,11,16]],"date-time":"2022-11-16T00:00:00Z","timestamp":1668556800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Uterine sarcomas have very poor prognoses and are sometimes difficult to distinguish from uterine leiomyomas on preoperative examinations. Herein, we investigated whether deep neural network (DNN) models can improve the accuracy of preoperative MRI-based diagnosis in patients with uterine sarcomas. Fifteen sequences of MRI for patients (uterine sarcoma group: n\u2009=\u200963; uterine leiomyoma: n\u2009=\u2009200) were used to train the models. Six radiologists (three specialists, three practitioners) interpreted the same images for validation. The most important individual sequences for diagnosis were axial T2-weighted imaging (T2WI), sagittal T2WI, and diffusion-weighted imaging. These sequences also represented the most accurate combination (accuracy: 91.3%), achieving diagnostic ability comparable to that of specialists (accuracy: 88.3%) and superior to that of practitioners (accuracy: 80.1%). Moreover, radiologists\u2019 diagnostic accuracy improved when provided with DNN results (specialists: 89.6%; practitioners: 92.3%). Our DNN models are valuable to improve diagnostic accuracy, especially in filling the gap of clinical skills between interpreters. This method can be a universal model for the use of deep learning in the diagnostic imaging of rare tumors.<\/jats:p>","DOI":"10.1038\/s41598-022-23064-5","type":"journal-article","created":{"date-parts":[[2022,11,16]],"date-time":"2022-11-16T11:05:57Z","timestamp":1668596757000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Development of a deep learning method for improving diagnostic accuracy for uterine sarcoma cases"],"prefix":"10.1038","volume":"12","author":[{"given":"Yusuke","family":"Toyohara","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kenbun","family":"Sone","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katsuhiko","family":"Noda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaname","family":"Yoshida","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ryo","family":"Kurokawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomoya","family":"Tanishima","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shimpei","family":"Kato","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shohei","family":"Inui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yudai","family":"Nakai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masanori","family":"Ishida","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wataru","family":"Gonoi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saki","family":"Tanimoto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Takahashi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Futaba","family":"Inoue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Asako","family":"Kukita","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yoshiko","family":"Kawata","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ayumi","family":"Taguchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akiko","family":"Furusawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuichiro","family":"Miyamoto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takehiro","family":"Tsukazaki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michihiro","family":"Tanikawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takayuki","family":"Iriyama","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mayuyo","family":"Mori-Uchino","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tetsushi","family":"Tsuruga","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katsutoshi","family":"Oda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Toshiharu","family":"Yasugi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kimihiro","family":"Takechi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Osamu","family":"Abe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yutaka","family":"Osuga","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,16]]},"reference":[{"key":"23064_CR1","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1016\/j.bpobgyn.2011.08.002","volume":"26","author":"T Van den Bosch","year":"2012","unstructured":"Van den Bosch, T., Coosemans, A., Morina, M., Timmerman, D. & Amant, F. Screening for uterine tumours. Best Pract. Res. Clin. Obstet. Gynaecol. 26, 257\u2013266 (2012).","journal-title":"Best Pract. Res. Clin. Obstet. Gynaecol."},{"key":"23064_CR2","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1007\/s00404-015-3993-6","volume":"294","author":"S Burghaus","year":"2016","unstructured":"Burghaus, S. et al. Outcome and prognosis in uterine sarcoma and malignant mixed Mullerian tumor. Arch. Gynecol. Obstet. 294, 343\u2013351 (2016).","journal-title":"Arch. Gynecol. Obstet."},{"key":"23064_CR3","doi-asserted-by":"publisher","first-page":"694","DOI":"10.3109\/0284186X.2012.689111","volume":"51","author":"CG Trop\u00e9","year":"2012","unstructured":"Trop\u00e9, C. G., Abeler, V. M. & Kristensen, G. B. Diagnosis and treatment of sarcoma of the uterus. A review. Acta Oncol. 51, 694\u2013705 (2012).","journal-title":"Acta Oncol."},{"key":"23064_CR4","doi-asserted-by":"publisher","first-page":"1134","DOI":"10.1136\/ijgc-2019-000355","volume":"29","author":"N Bizzarri","year":"2019","unstructured":"Bizzarri, N. et al. Secondary cytoreductive surgery in recurrent uterine leiomyosarcoma: A multi-institutional study. Int. J. Gynecol. Cancer 29, 1134\u20131140 (2019).","journal-title":"Int. J. Gynecol. Cancer"},{"key":"23064_CR5","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.critrevonc.2017.12.009","volume":"122","author":"IME Desar","year":"2018","unstructured":"Desar, I. M. E., Ottevanger, P. B., Benson, C. & van der Graaf, W. T. A. Systemic treatment in adult uterine sarcomas. Crit. Rev. Oncol. Hematol. 122, 10\u201320 (2018).","journal-title":"Crit. Rev. Oncol. Hematol."},{"key":"23064_CR6","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1148\/radiol.12120315","volume":"266","author":"E Sala","year":"2013","unstructured":"Sala, E., Rockall, A. G., Freeman, S. J., Mitchell, D. G. & Reinhold, C. The added role of MR imaging in treatment stratification of patients with gynecologic malignancies: What the radiologist needs to know. Radiology 266, 717\u2013740 (2013).","journal-title":"Radiology"},{"key":"23064_CR7","doi-asserted-by":"publisher","first-page":"31229","DOI":"10.1038\/srep31229","volume":"6","author":"H Liu","year":"2016","unstructured":"Liu, H. et al. Laparoscopic surgery on broken points for uterine sarcoma in the early stage decrease prognosis. Sci. Rep. 6, 31229 (2016).","journal-title":"Sci. Rep."},{"key":"23064_CR8","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1016\/j.ejca.2018.06.007","volume":"101","author":"M Bretthauer","year":"2018","unstructured":"Bretthauer, M. et al. Uterine morcellation and survival in uterine sarcomas. Eur. J. Cancer 101, 62\u201368 (2018).","journal-title":"Eur. J. Cancer"},{"key":"23064_CR9","doi-asserted-by":"publisher","first-page":"873","DOI":"10.1007\/s00247-016-3560-8","volume":"46","author":"EA Smith","year":"2016","unstructured":"Smith, E. A. & Dillman, J. R. Current role of body MRI in pediatric oncology. Pediatr. Radiol. 46, 873\u2013880 (2016).","journal-title":"Pediatr. Radiol."},{"key":"23064_CR10","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1016\/j.diii.2019.07.007","volume":"100","author":"S Sun","year":"2019","unstructured":"Sun, S. et al. How to differentiate uterine leiomyosarcoma from leiomyoma with imaging. Diagn. Interv. Imaging 100, 619\u2013634 (2019).","journal-title":"Diagn. Interv. Imaging"},{"key":"23064_CR11","doi-asserted-by":"publisher","first-page":"6125","DOI":"10.1007\/s00330-020-07678-9","volume":"31","author":"T Wang","year":"2021","unstructured":"Wang, T. et al. A combined radiomics and clinical variables model for prediction of malignancy in T2 hyperintense uterine mesenchymal tumors on MRI. Eur. Radiol. 31, 6125\u20136135 (2021).","journal-title":"Eur. Radiol."},{"key":"23064_CR12","doi-asserted-by":"publisher","first-page":"1228","DOI":"10.1111\/aogs.13008","volume":"95","author":"M Skorstad","year":"2016","unstructured":"Skorstad, M., Kent, A. & Lieng, M. Preoperative evaluation in women with uterine leiomyosarcoma. A nationwide cohort study. Acta Obstet. Gynecol. Scand. 95, 1228\u20131234 (2016).","journal-title":"Acta Obstet. Gynecol. Scand."},{"key":"23064_CR13","doi-asserted-by":"publisher","first-page":"e21766","DOI":"10.1097\/MD.0000000000021766","volume":"99","author":"L Wang","year":"2020","unstructured":"Wang, L., Li, S., Zhang, Z., Jia, J. & Shan, B. Prevalence and occult rates of uterine leiomyosarcoma. Medicine (Baltimore) 99, e21766 (2020).","journal-title":"Medicine (Baltimore)"},{"key":"23064_CR14","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1016\/j.jmig.2015.11.012","volume":"23","author":"PG Paul","year":"2016","unstructured":"Paul, P. G. et al. Uterine sarcomas in patients undergoing surgery for presumed leiomyomas: 10 years\u2019 experience. J. Minim. Invasive Gynecol. 23, 384\u2013389 (2016).","journal-title":"J. Minim. Invasive Gynecol."},{"key":"23064_CR15","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1007\/s00404-018-4949-4","volume":"299","author":"L van den Haak","year":"2019","unstructured":"van den Haak, L. et al. Incidence and groups at risk for unexpected uterine leiomyosarcoma: A Dutch nationwide cohort study. Arch. Gynecol. Obstet. 299, 159\u2013165 (2019).","journal-title":"Arch. Gynecol. Obstet."},{"key":"23064_CR16","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1007\/s11604-006-0106-2","volume":"25","author":"T Yamashiro","year":"2007","unstructured":"Yamashiro, T., Gibo, M., Utsunomiya, T. & Murayama, S. Huge uterine leiomyoma with adenomyotic cysts mimicking uterine sarcoma on MR imaging. Radiat. Med. 25, 127\u2013129 (2007).","journal-title":"Radiat. Med."},{"key":"23064_CR17","doi-asserted-by":"publisher","first-page":"570","DOI":"10.3348\/kjr.2017.18.4.570","volume":"18","author":"JG Lee","year":"2017","unstructured":"Lee, J. G. et al. Deep learning in medical imaging: General overview. Korean J. Radiol. 18, 570\u2013584 (2017).","journal-title":"Korean J. Radiol."},{"key":"23064_CR18","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O. et al. ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211\u2013252 (2015).","journal-title":"Int. J. Comput. Vis."},{"key":"23064_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. arXiv:1512.03385 (2015).","DOI":"10.1109\/CVPR.2016.90"},{"key":"23064_CR20","doi-asserted-by":"publisher","first-page":"2903","DOI":"10.1007\/s00330-016-4623-9","volume":"27","author":"Y Lakhman","year":"2017","unstructured":"Lakhman, Y. et al. Differentiation of uterine leiomyosarcoma from atypical leiomyoma: Diagnostic accuracy of qualitative MR imaging features and feasibility of texture analysis. Eur. Radiol. 27, 2903\u20132915 (2017).","journal-title":"Eur. Radiol."},{"key":"23064_CR21","doi-asserted-by":"publisher","first-page":"1172","DOI":"10.2214\/AJR.17.18605","volume":"210","author":"L Gerges","year":"2018","unstructured":"Gerges, L., Popiolek, D. & Rosenkrantz, A. B. Explorative investigation of whole-lesion histogram MRI metrics for differentiating uterine leiomyomas and leiomyosarcomas. AJR Am. J. Roentgenol. 210, 1172\u20131177 (2018).","journal-title":"AJR Am. J. Roentgenol."},{"key":"23064_CR22","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1016\/j.ejrad.2018.11.009","volume":"110","author":"M Malek","year":"2019","unstructured":"Malek, M. et al. A machine learning approach for distinguishing uterine sarcoma from leiomyomas based on perfusion weighted MRI parameters. Eur. J. Radiol. 110, 203\u2013211 (2019).","journal-title":"Eur. J. Radiol."},{"key":"23064_CR23","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.ejrad.2019.04.004","volume":"115","author":"H Xie","year":"2019","unstructured":"Xie, H. et al. Preliminary utilization of radiomics in differentiating uterine sarcoma from atypical leiomyoma: Comparison on diagnostic efficacy of MRI features and radiomic features. Eur. J. Radiol. 115, 39\u201345 (2019).","journal-title":"Eur. J. Radiol."},{"issue":"167","key":"23064_CR24","first-page":"e1","volume":"74","author":"M Nakagawa","year":"2019","unstructured":"Nakagawa, M. et al. A multiparametric MRI-based machine learning to distinguish between uterine sarcoma and benign leiomyoma: Comparison with 18 F-FDG PET\/CT. Clin. Radiol. 74(167), e1-167.e7 (2019).","journal-title":"Clin. Radiol."},{"key":"23064_CR25","doi-asserted-by":"publisher","first-page":"7404","DOI":"10.1038\/s41598-020-64285-w","volume":"10","author":"M Malek","year":"2020","unstructured":"Malek, M. et al. A diagnostic algorithm using multi-parametric MRI to differentiate benign from malignant myometrial tumors: Machine-learning method. Sci. Rep. 10, 7404 (2020).","journal-title":"Sci. Rep."},{"key":"23064_CR26","doi-asserted-by":"publisher","first-page":"2306","DOI":"10.1007\/s00330-013-2819-9","volume":"23","author":"I Thomassin-Naggara","year":"2013","unstructured":"Thomassin-Naggara, I. et al. How to differentiate benign from malignant myometrial tumours using MR imaging. Eur. Radiol. 23, 2306\u20132314 (2013).","journal-title":"Eur. Radiol."},{"key":"23064_CR27","doi-asserted-by":"publisher","first-page":"76","DOI":"10.14740\/wjon1031w","volume":"8","author":"BH Bacanakgil","year":"2017","unstructured":"Bacanakgil, B. H., Deveci, M., Karabuk, E. & Soyman, Z. Uterine smooth muscle tumor of uncertain malignant potential: Clinicopathologic-sonographic characteristics, follow-up and recurrence. World J. Oncol. 8, 76\u201380 (2017).","journal-title":"World J. Oncol."},{"key":"23064_CR28","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A. & Chen, L.-C. MobileNetV2: Inverted residuals and linear bottlenecks. arXiv:1801.04381 (2018).","DOI":"10.1109\/CVPR.2018.00474"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-23064-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-23064-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-23064-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,16]],"date-time":"2022-11-16T11:08:49Z","timestamp":1668596929000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-23064-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,16]]},"references-count":28,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["23064"],"URL":"https:\/\/doi.org\/10.1038\/s41598-022-23064-5","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,16]]},"assertion":[{"value":"24 March 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 October 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 November 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"K. Sone has a joint research agreement with Predicthy LLC. The remaining authors have no competing interests to disclose.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"19612"}}