Habitat informed 3D deep learning predicts immunochemotherapy response in esophageal squamous cell carcinoma.
Authors
Affiliations (8)
Affiliations (8)
- Department of Digital Medicine, College of Biomedical Engineering and Medical Imaging, Army Medical University (Third Military Medical University), Chongqing, China.
- Yu-Yue Pathology Research Center, Jinfeng Laboratory, Chongqing, China.
- Department of Cardiothoracic Surgery of Jiangbei Campus, The First Affiliated Hospital of Army Medical University, Chongqing, China.
- Department of Thoracic Surgery, Southwest Hospital, Army Medical University (Third Military Medical University), Chongqing, China.
- Daping Hospital & Army Medical Center of PLA, Army Medical University, Chongqing, China.
- Radiobiology of Cancer Key Laboratory of Chongqing Education Commission of China, Chongqing, China.
- Department of Cardiac Surgery, Southwest Hospital, Army Medical University (Third Military Medical University), Chongqing, China.
- Department of Thoracic Surgery, Daping Hospital, Army Medical University (Third Military Medical University), Chongqing, China.
Abstract
Immunochemotherapy (ICT) is a critical treatment for locally advanced esophageal squamous cell carcinoma (LA-ESCC), yet predicting individual response remains challenging. We developed a three-channel 3D deep learning framework integrating tumor habitat analysis for predicting ICT response. In this multicenter retrospective study of 277 patients, voxel-level clustering of pretreatment CT images segmented tumors into habitat subregions reflecting microenvironmental heterogeneity. A ResNet-50 model incorporating habitat maps, cropped tumor images, and ROI masks achieved an AUC of 0.927 (95% CI, 0.850-0.951) in the independent external test cohort, compared with 0.869 for habitat radiomics (DeLong <i>p</i> = 0.343). SHapley Additive exPlanations analysis identified texture features, particularly gray-level co-occurrence matrix correlation in habitat 3, as the primary contributors. This framework provides a noninvasive approach for predicting ICT response in LA-ESCC.