{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T02:55:06Z","timestamp":1790564106699,"version":"4.1.0"},"reference-count":27,"publisher":"Baishideng Publishing Group Inc.","issue":"9","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["World J Radiol"],"abstract":"BACKGROUND<\/jats:p>\n Cervical cancer remains one of the leading causes of cancer-related mortality among women worldwide. Although californium-252 (252Cf) neutron brachytherapy has demonstrated favorable therapeutic efficacy for locally advanced cervical cancer, substantial inter-patient heterogeneity in treatment response still exists. Therefore, developing a reliable non-invasive predictive model before treatment is of considerable clinical importance.<\/jats:p>\n AIM<\/jats:p>\n To develop and validate a predictive model that integrates multiparametric magnetic resonance imaging (MRI) habitat atlas, radiomics, and deep learning features for the non-invasive and accurate prediction of treatment efficacy in cervical cancer patients receiving 252Cf neutron intracavitary brachytherapy combined with external beam radiotherapy.<\/jats:p>\n METHODS<\/jats:p>\n A total of 100 cervical cancer patients who underwent the aforementioned treatment at our institution from January 2020 to June 2025 were retrospectively enrolled. All patients underwent pretreatment multi-sequence MRI scans [T1-weighted imaging, T2-weighted imaging, dynamic contrast enhanced (DCE)-MRI, and diffusion weighted imaging (DWI)]. Based on DCE-MRI and DWI parameter maps, a k -means clustering algorithm was employed to delineate the tumor habitat atlas, partitioning the tumor into three functional subregions (H1: High vascularity\/high cellularity; H2: Low vascularity\/high cellularity; H3: Low vascularity\/low cellularity). Radiomics features were extracted from both the whole tumor region and each habitat subregion, while deep learning features were extracted using a pre-trained ResNet50 network. The aforementioned features, along with clinical-dosimetric parameters, were fused. Following feature selection via the least absolute shrinkage and selection operator, a fusion prediction model was constructed using a support vector machine. The dataset was split into a training set (n = 70) and a validation set (n = 30) at a 7:3 ratio for model evaluation.<\/jats:p>\n RESULTS<\/jats:p>\n Habitat analysis successfully identified three types of functional subregions, whose distribution was significantly associated with tumor heterogeneity. The fusion model (Model-Fusion) achieved an area under curve (AUC) of 0.892 (95% confidence interval: 0.821-0.963) and an accuracy of 0.867 in the validation set, significantly outperforming the model based solely on clinical features (AUC = 0.712), the whole-tumor radiomics model (AUC = 0.783), and the radiomics combined with deep learning model (AUC = 0.835) (all P < 0.05). Decision curve analysis demonstrated that the fusion model provided the highest clinical net benefit. The 3-year overall survival rate was significantly higher in the model-predicted high-benefit group (92.5%) compared to the low-benefit group (71.4%, P = 0.003).<\/jats:p>\n CONCLUSION<\/jats:p>\n This study integrates MRI habitat atlas analysis with deep learning and radiomics. The constructed multimodal fusion model can non-invasively and accurately predict the efficacy of 252Cf neutron therapy for cervical cancer, providing a promising approach for individualized precision radiotherapy decision-making.<\/jats:p>","DOI":"10.4329\/wjr.123597","type":"journal-article","created":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T09:41:13Z","timestamp":1786959673000},"source":"Crossref","is-referenced-by-count":0,"title":["Development and validation of a multimodal MRI habitat-based deep learning fusion model for predicting\n 252<\/sup>\n Cf neutron therapy response in cervical cancer"],"prefix":"10.4329","volume":"18","author":[{"given":"Shu-Peng","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhi-Guo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi-Jing","family":"Shan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miao","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Tong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Meng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"2060","published-online":{"date-parts":[[2026,9,28]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21660"},{"key":"B2","unstructured":"Hall EJ, Giaccia AJ. Radiobiology for the Radiologist. 8th ed. Philadelphia: Wolters Kluwer, 2019"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1038\/nrclinonc.2009.183"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1038\/nature12626"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.2147\/CMAR.S511796"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1038\/s41571-018-0114-z"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1038\/nm.4409"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0014-x"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1186\/s12957-022-02859-w"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2020191145"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1007\/s00261-022-03665-4"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1186\/s40644-022-00474-2"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.3390\/cancers14081858"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2020.00563"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1186\/s40644-025-00829-5"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-023-09990-6"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-51742-z"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-70055-9"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics14010005"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-61271-4"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2018172462"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1148\/89.2.337"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1093\/jrr\/rru059"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1016\/j.ctro.2020.04.001"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1016\/j.mri.2025.110542"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.3390\/cancers18010152"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1038\/s41571-022-00707-0"}],"container-title":["World Journal of Radiology"],"original-title":[],"link":[{"URL":"https:\/\/www.wjgnet.com\/1949-8470\/full\/v18\/i9\/123597.htm","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.wjgnet.com\/1949-8470\/full\/v18\/i9\/123597.htm","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T02:00:14Z","timestamp":1790560814000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.wjgnet.com\/1949-8470\/full\/v18\/i9\/123597.htm"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,28]]},"references-count":27,"journal-issue":{"issue":"9"},"alternative-id":["123597"],"URL":"https:\/\/doi.org\/10.4329\/wjr.123597","relation":{},"ISSN":["1949-8470"],"issn-type":[{"value":"1949-8470","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9,28]]}}}