{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T05:08:03Z","timestamp":1784092083015,"version":"3.55.0"},"reference-count":36,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T00:00:00Z","timestamp":1784073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Oncol."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Esophageal fistula is a life-threatening complication following treatment of esophageal squamous cell carcinoma (ESCC). Early identification of high-risk patients remains challenging due to the limited predictive value of conventional imaging markers. This study aimed to develop and validate a Grad-CAM\u2013guided deep learning\u2013radiomics framework for risk prediction and spatial biomarker discovery using pre-treatment CT.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this retrospective study, 73 ESCC patients treated between January 2019 and December 2022 were included, of whom 25 (34.2%) developed esophageal fistula within one year. A 3D convolutional neural network (3D-CNN) was trained using stratified five-fold cross-validation. Grad-CAM was applied to localize discriminative regions, guiding radiomics feature extraction from the bilateral lungs, thoracic spine, and esophageal tumor. Radscores were constructed using least absolute shrinkage and selection operator regression. Logistic regression analyses were performed to identify independent predictors.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The 3D-CNN demonstrated stable performance across folds, achieving mean accuracy, sensitivity, and AUC of 0.809, 0.873, and 0.848, respectively. Grad-CAM revealed prominent activation differences in the lungs and thoracic spine rather than the central mediastinum. Radiomics analysis confirmed significant textural differences in all three regions (P &amp;lt; 0.001), with higher Radscores observed in the fistula group. In conventional multivariable logistic regression, Lung Radscore (OR = 11.55, P = 0.038) and Esophageal Tumor Radscore (OR = 192.3, P = 0.040) were associated with esophageal fistula, whereas conventional CT parameters lost statistical significance. Firth penalized logistic regression yielded more conservative estimates, with Esophageal Tumor Radscore remaining significant and Lung Radscore showing a borderline association.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The Grad-CAM\u2013guided 3D-CNN radiomics framework identified tumor-related and extratumoral imaging patterns associated with esophageal fistula, providing exploratory spatial biomarkers that warrant further validation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1825313","type":"journal-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T04:43:09Z","timestamp":1784090589000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Spatial associations between esophageal lesions and surrounding tissues in esophageal fistula: a CAM-guided radiomics study"],"prefix":"10.3389","volume":"16","author":[{"given":"Ang","family":"Li","sequence":"first","affiliation":[{"name":"PET Center, Fujian Medical University Union Hospital","place":["Fuzhou, China"]},{"name":"Clinical Research Center for Radiology and Radiotherapy of Fujian Province (Digestive, Hematological and Breast Malignancies)","place":["Fuzhou, China"]},{"name":"Fujian Key Laboratory of Intelligent Imaging and Precision Radiotherapy for Tumors (Fujian Medical University)","place":["Fuzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lili","family":"Lin","sequence":"additional","affiliation":[{"name":"PET Center, Fujian Medical University Union Hospital","place":["Fuzhou, China"]},{"name":"Clinical Research Center for Radiology and Radiotherapy of Fujian Province (Digestive, Hematological and Breast Malignancies)","place":["Fuzhou, China"]},{"name":"Fujian Key Laboratory of Intelligent Imaging and Precision Radiotherapy for Tumors (Fujian Medical University)","place":["Fuzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zewen","family":"Han","sequence":"additional","affiliation":[{"name":"PET Center, Fujian Medical University Union Hospital","place":["Fuzhou, China"]},{"name":"Clinical Research Center for Radiology and Radiotherapy of Fujian Province (Digestive, Hematological and Breast Malignancies)","place":["Fuzhou, China"]},{"name":"Fujian Key Laboratory of Intelligent Imaging and Precision Radiotherapy for Tumors (Fujian Medical University)","place":["Fuzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianqiang","family":"Ye","sequence":"additional","affiliation":[{"name":"PET Center, Fujian Medical University Union Hospital","place":["Fuzhou, China"]},{"name":"Clinical Research Center for Radiology and Radiotherapy of Fujian Province (Digestive, Hematological and Breast Malignancies)","place":["Fuzhou, China"]},{"name":"Fujian Key Laboratory of Intelligent Imaging and Precision Radiotherapy for Tumors (Fujian Medical University)","place":["Fuzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junqing","family":"Lin","sequence":"additional","affiliation":[{"name":"Clinical Research Center for Radiology and Radiotherapy of Fujian Province (Digestive, Hematological and Breast Malignancies)","place":["Fuzhou, China"]},{"name":"Fujian Key Laboratory of Intelligent Imaging and Precision Radiotherapy for Tumors (Fujian Medical University)","place":["Fuzhou, China"]},{"name":"Department of Interventional Radiology, Fujian Medical University Union Hospital","place":["Fuzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Jiang","sequence":"additional","affiliation":[{"name":"PET Center, Fujian Medical University Union Hospital","place":["Fuzhou, China"]},{"name":"Clinical Research Center for Radiology and Radiotherapy of Fujian Province (Digestive, Hematological and Breast Malignancies)","place":["Fuzhou, China"]},{"name":"Fujian Key Laboratory of Intelligent Imaging and Precision Radiotherapy for Tumors (Fujian Medical University)","place":["Fuzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,15]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21834","article-title":"Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"74","author":"Bray","year":"2024","journal-title":"CA Cancer J Clin"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/j.anr.2024.04.004","article-title":"Frailty and health-related quality of life in elderly patients undergoing esophageal cancer surgery: a longitudinal study","volume":"18","author":"Chen","year":"2024","journal-title":"Asian Nurs Res (Korean Soc Nurs Sci)"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-074962","article-title":"Advances in diagnosis and management of cancer of the esophagus","volume":"385","author":"Deboever","year":"2024","journal-title":"BMJ"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1007\/s10388-024-01064-w","article-title":"Impact of quality of life on mortality risk in patients with esophageal cancer: a systematic review and meta-analysis","volume":"21","author":"Inoue","year":"2024","journal-title":"Esophagus"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/j.critrevonc.2024.104315","article-title":"Multi-disciplinary management of esophageal carcinoma: current practices and future directions","volume":"197","author":"Bandidwattanawong","year":"2024","journal-title":"Crit Rev Oncol Hematol"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1007\/s00432-023-05520-5","article-title":"Multi-omics and multi-VOIs to predict esophageal fistula in esophageal cancer patients treated with radiotherapy","volume":"150","author":"Guo","year":"2024","journal-title":"J Cancer Res Clin Oncol"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2021.02.031","article-title":"High incidence of esophageal fistula on patients with clinical T4b esophageal squamous cell carcinoma who received chemoradiotherapy: a retrospective analysis","volume":"158","author":"Chen","year":"2021","journal-title":"Radiother Oncol"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1186\/s13244-024-01754-0","article-title":"How to update esophageal masses imaging using literature review (MRI and CT features)","volume":"15","author":"Qu","year":"2024","journal-title":"Insights Imaging"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.240072","article-title":"Evaluating performance of a deep learning multilabel segmentation model to quantify acute and chronic brain lesions at MRI after stroke and predict prognosis","volume":"7","author":"Tang","year":"2025","journal-title":"Radiol Artif Intell"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1186\/s12880-024-01473-4","article-title":"Prediction of esophageal fistula in radiotherapy\/chemoradiotherapy for patients with advanced esophageal cancer by a clinical-deep learning radiomics model: prediction of esophageal fistula in radiotherapy\/chemoradiotherapy patients","volume":"24","author":"Zhang","year":"2024","journal-title":"BMC Med Imaging"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1186\/s40644-022-00490-2","article-title":"Quantitative CT analysis to predict esophageal fistula in patients with advanced esophageal cancer treated by chemotherapy or chemoradiotherapy","volume":"22","author":"Shi","year":"2022","journal-title":"Cancer Imaging"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1186\/s12903-023-03033-8","article-title":"Detecting representative characteristics of different genders using intraoral photographs: a deep learning model with interpretation of gradient-weighted class activation mapping","volume":"23","author":"Zhou","year":"2023","journal-title":"BMC Oral Health"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.105680","article-title":"A convolution neural network with multi-level convolutional and attention learning for classification of cancer grades and tissue structures in colon histopathological images","volume":"147","author":"Dabass","year":"2022","journal-title":"Comput Biol Med"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2023.3329231","article-title":"AD-CAM: enhancing interpretability of convolutional neural networks with a lightweight framework - from black box to glass box","volume":"28","author":"Iqbal","year":"2023","journal-title":"IEEE J Biomed Health Inform"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3089943","article-title":"LayerCAM: exploring hierarchical class activation maps for localization","volume":"30","author":"Jiang","year":"2021","journal-title":"IEEE Trans Image Process"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2025.109656","article-title":"ResViT FusionNet model: an explainable AI-driven approach for automated grading of diabetic retinopathy in retinal images","volume":"186","author":"Ikram","year":"2025","journal-title":"Comput Biol Med"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1002\/uog.27577","article-title":"Interaction between clinicians and artificial intelligence to detect fetal atrioventricular septal defects on ultrasound: how can we optimize collaborative performance","volume":"64","author":"Day","year":"2024","journal-title":"Ultrasound Obstet Gynecol"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1186\/s40658-024-00651-1","article-title":"Radiomics incorporating deep features for predicting Parkinson's disease in (123)I-Ioflupane SPECT","volume":"11","author":"Jiang","year":"2024","journal-title":"EJNMMI Phys"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.240541","article-title":"AI for multistructure incidental findings and mortality prediction at chest CT in lung cancer screening","volume":"312","author":"Marcinkiewicz","year":"2024","journal-title":"Radiology"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-024-10586-x","article-title":"Hematoma expansion prediction: still navigating the intersection of deep learning and radiomics","volume":"34","author":"Le","year":"2024","journal-title":"Eur Radiol"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1007\/s11517-023-02875-2","article-title":"A transfer learning approach on MRI-based radiomics signature for overall survival prediction of low-grade and high-grade gliomas","volume":"61","author":"Le","year":"2023","journal-title":"Med Biol Eng Comput"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.21037\/jtd-24-191","article-title":"Clinical-radiomics nomogram for the risk prediction of esophageal fistula in patients with esophageal squamous cell carcinoma treated with intensity-modulated radiation therapy or volumetric-modulated arc therapy","volume":"16","author":"Li","year":"2024","journal-title":"J Thorac Dis"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.21873\/anticanres.16074","article-title":"Evaluating neoadjuvant chemotherapy for lower esophageal squamous cell carcinoma by measuring esophageal wall thickness","volume":"42","author":"Sato","year":"2022","journal-title":"Anticancer Res"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1186\/s40001-024-01746-2","article-title":"Prediction of malignant esophageal fistula in esophageal cancer using a radiomics-clinical nomogram","volume":"29","author":"Zhu","year":"2024","journal-title":"Eur J Med Res"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1186\/s12967-023-04554-0","article-title":"Tissue fibrosis induced by radiotherapy: current understanding of the molecular mechanisms, diagnosis and therapeutic advances","volume":"21","author":"Yu","year":"2023","journal-title":"J Transl Med"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacbts.2018.01.014","article-title":"Radiation-induced endothelial vascular injury: a review of possible mechanisms","volume":"3","author":"Venkatesulu","year":"2018","journal-title":"JACC Basic Transl Sci"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.3390\/ph17040533","article-title":"Advances and challenges in targeting TGF-beta isoforms for therapeutic intervention of cancer: a mechanism-based perspective","volume":"17","author":"Danielpour","year":"2024","journal-title":"Pharmaceuticals (Basel)"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.3389\/fcvm.2020.00034","article-title":"Therapeutic targets for the treatment of cardiac fibrosis and cancer: focusing on TGF-beta signaling","volume":"7","author":"Parichatikanond","year":"2020","journal-title":"Front Cardiovasc Med"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1016\/j.lfs.2021.120115","article-title":"Effects of in-vitro modulation of TRPV1 activity on immune response of mice bearing metastatic breast carcinoma: enhanced inflammatory response may hinder therapeutic potentials of TRPV1 agonists","volume":"287","author":"Erin","year":"2021","journal-title":"Life Sci"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.3390\/cells10113053","article-title":"TRPV4 mechanotransduction in fibrosis","volume":"10","author":"Adapala","year":"2021","journal-title":"Cells"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1002\/deo2.260","article-title":"A rare cause of esophageal stenosis: compression due to a thoracic osteophyte","volume":"4","author":"Miida","year":"2024","journal-title":"DEN Open"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2022.102435","article-title":"Virtual disease landscape using mechanics-informed machine learning: application to esophageal disorders","volume":"134","author":"Halder","year":"2022","journal-title":"Artif Intell Med"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1007\/s11547-020-01318-4","article-title":"Radiomic analysis of the optic nerve at the first episode of acute optic neuritis: an indicator of optic nerve pathology and a predictor of visual recovery","volume":"126","author":"Cellina","year":"2021","journal-title":"Radiol Med"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1093\/jbmr\/zjae207","article-title":"Individuals with heterogenous trabecular bone texture by clinical magnetic resonance imaging have lower bone strength and stiffness by quantitative computed tomography-based finite element analysis","volume":"40","author":"Dash","year":"2025","journal-title":"J Bone Miner Res"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101838","article-title":"ELNet: automatic classification and segmentation for esophageal lesions using convolutional neural network","volume":"67","author":"Wu","year":"2021","journal-title":"Med Image Anal"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2024.1492399","article-title":"Multimodal data deep learning method for predicting symptomatic pneumonitis caused by lung cancer radiotherapy combined with immunotherapy","volume":"15","author":"Yang","year":"2024","journal-title":"Front Immunol"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1825313\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T04:43:18Z","timestamp":1784090598000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1825313\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,15]]},"references-count":36,"alternative-id":["10.3389\/fonc.2026.1825313"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1825313","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,15]]},"article-number":"1825313"}}