Muscle-Driven prognostication in gastric cancer: A multicenter deep learning framework integrating Iliopsoas and erector spinae radiomics for 5-Year survival prediction

Abstract

This study developed a 5-year survival prediction model for gastric cancer patients by combining radiomics and deep learning, focusing on CT-based 2D and 3D features of the iliopsoas and erector spinae muscles. Retrospective data from 705 patients across two centers were analyzed, with clinical variables assessed via Cox regression and radiomic features extracted using deep learning. The 2D model outperformed the 3D approach, leading to feature fusion across five dimensions, optimized via logistic regression. Results showed no significant association between clinical baseline characteristics and survival, but the 2D model demonstrated strong prognostic performance (AUC ~ 0.8), with attention heatmaps emphasizing spinal muscle regions. The 3D model underperformed due to irrelevant data. The final integrated model achieved stable predictive accuracy, confirming the link between muscle mass and survival. This approach advances precision medicine by enabling personalized prognosis and exploring 3D imaging feasibility, offering insights for gastric cancer research.

Keywords: Deep learning; Gastric cancer; Radical gastrectomy; Sarcopenia.

Fig. 1

Flowchart of patient enrollment. Of 603 initially screened gastrectomy patients, 511 completed 5-year follow-up (32 withdrew, 57 lost to follow-up, 3 unrelated deaths).

Fig. 2

Flow chart of muscle segmentation. The pipeline processes abdominal CT images through three stages: (1) original/abdominal window phases, (2) automated segmentation using a U-NET model (TotalSegmentation), and (3) generation of three muscle subgroups (bilateral psoas, erector spinae, and combined muscles). Six standardized input datasets (3 muscle groups × 2 CT phases) were produced for subsequent analysis.

Fig. 3

Radiomics workflow for 5-year survival prediction after gastrectomy. The pipeline consists of three main stages: (1) preprocessing of clinical and imaging data, (2) multi-modal 2D neural network screening (14 architectures tested) with feature fusion, and (3) predictive model evaluation using 11 machine learning classifiers. The optimal 2D-based fusion strategy demonstrated superior performance over 3D approaches in external validation (n = 194).

Fig. 4

Performance evaluation of optimal 2D neural networks across five imaging modalities. (A-E) The receiver operating characteristic (ROC) and decision curve analysis (DCA) results demonstrate the predictive performance of selected models: a.Muscle fusion: ResNet18 for both non-enhanced (A) and enhanced (B) modalities (AUC > 0.6). b.Iliopsoas: MNASNet0_5 (C, non-enhanced) and ResNet152 (D, enhanced). c.Erector spinae: ResNet50 (E, enhanced only; original phase models excluded due to accuracy ≈ 0.5). d.Each modality is presented in three subplots: (1) ROC curves with AUC and 95% CI, (2) training set DCA, and (3) test set DCA. Model selection was based on strict criteria excluding underperforming models (AUC < 0.5) and prioritizing those with consistent train-test performance and low overfitting risk.

Fig. 5

Performance comparison of 3D neural networks using ROC curves. The evaluation of DenseNet121 and DenseNet201 models on abdominal CT scans showed limited classification capability, with AUC values below 0.5 for both models. While 3D architectures can capture spatial information effectively, these results suggest they may not be optimal for this particular task. The ROC curves (left: DenseNet121; right: DenseNet201) with 95% confidence intervals demonstrate this performance limitation, leading to their exclusion from the final model integration.

Fig. 6

Performance comparison of machine learning classifiers after multimodal feature fusion. The evaluation of 11 classifiers on fused neural network features showed logistic regression (LR) and support vector machine (SVM) as top performers. (A-B) ROC curves demonstrate classification accuracy of LR and SVM models. (C-F) DCA curves validate clinical utility in both training and test sets. (G) Boxplot summarizes cross-validated accuracy across all classifiers. The final selection of LR as optimal classifier was based on its balanced performance and practical stability in clinical application scenarios.

Fig. 7

2D attention heatmaps based on neural networks. Models consistently focused on paravertebral muscles during classification, shown for (A) erector spinae, (B) iliopsoas, and (C) combined muscle groups.

Fig. 8

Visualization of attention heatmaps for correctly and incorrectly predicted cases. (A) Heatmaps from correctly predicted cases demonstrate model focus on clinically relevant muscle areas. (B) Heatmaps from misclassified cases show scattered or non-informative attention regions.