A Cascaded Segmentation-Classification Deep Learning Framework for Preoperative Prediction of Occult Peritoneal Metastasis and Early Recurrence in Advanced Gastric Cancer.
Authors
Affiliations (8)
Affiliations (8)
- Department of Radiology, Fujian Medical University Union Hospital, Fuzhou 350001, China (T.Z., P.C., T.L., X.C., F.Y., X.L., L.W.).
- Department of Radiology, the Third People's Hospital of Jining, Jining 272000, China (T.W.).
- Department of Radiology, Fujian Medical University Affiliated Fuzhou First Hospital, Fuzhou 350000, China (S.L.).
- Department of Radiology, the 907th Hospital of the PLA Joint Logistics Support Force, 353000, Nanping, Fujian, China (X.Y.).
- Fujian Medical University, Fuzhou 350000, China (L.Z., Y.L.).
- School of Electrical and Computer Engineering, University of Oklahoma, Norman, OK 73019 (B.Z.).
- Department of Radiotherapy, Fujian Medical University Union Hospital, Fuzhou 350001, China (J.S.).
- Department of Radiology, Fujian Medical University Union Hospital, Fuzhou 350001, China (T.Z., P.C., T.L., X.C., F.Y., X.L., L.W.). Electronic address: [email protected].
Abstract
To develop a cascaded deep learning (DL) framework integrating tumor segmentation with metastatic risk stratification for preoperative prediction of occult peritoneal metastasis (OPM) in advanced gastric cancer (GC), and validate its generalizability for early peritoneal recurrence (PR) prediction. This multicenter study enrolled 765 patients with advanced GC from three institutions. We developed a two-stage framework as follows: (1) V-Net-based tumor segmentation on CT; (2) DL-based metastatic risk classification using segmented tumor regions. Clinicopathological predictors were integrated with deep learning probabilities to construct a combined model. Validation cohorts comprised: Internal validation (Test1 for OPM, n=168; Test2 for early PR, n=212) and External validation (Test3 for early PR, n=57 from two independent centers). Multivariable analysis identified Borrmann type (OR=1.314, 95% CI: 1.239-1.394), CA125 ≥35U/mL (OR=1.301, 95% CI: 1.127-1.499), and CT-N+ stage (OR=1.259, 95% CI: 1.124-1.415) as independent OPM predictors. The combined model demonstrated robust performance for both OPM and early PR prediction: achieving AUCs of 0.938 (Train) and 0.916 (Test1) for OPM with improvements over clinical (∆AUC +0.039-+0.107) and DL-only models (∆AUC +0.044-+0.104), while attaining AUC 0.820-0.825 for early PR (Test2 and Test3) with balanced sensitivity (79.7-88.9%) and specificity (72.4-73.3%). Decision curve analysis confirmed net clinical benefit across clinical thresholds. This CT-based cascaded framework enables reliable preoperative risk stratification for OPM and early PR in advanced GC, potentially refining indications for personalized therapeutic pathways.