Predicting Prognosis for Gastric Cancer Patients Receiving Neoadjuvant Treatment With Body Composition-Based Deep Learning

Clinical Snapshot

Key Findings

• P Value: Significant survival differences between risk groups (specific p-value not provided)

• Effect Size: AUC 0.890 in test set for combined model

• Primary Outcome: Overall survival prediction using combined clinical, radiomics, and deep learning features

• Nnt Or Sensitivity: C-index 0.819 in test set indicating good discrimination for survival prediction

• Confidence Interval: Not reported in abstract

Clinical Application

Requires specialized imaging analysis software and machine learning infrastructure, limiting immediate clinical implementation Relevant to Australian gastric cancer management; could inform PBS funding decisions for neoadjuvant therapy and align with Cancer Australia guidelines for personalized treatment approaches Gastric cancer patients considered for neoadjuvant treatment with available CT imaging

Abstract

BACKGROUND: This study sought to develop an innovative body composition (BC)-based deep learning (DL) model to precisely evaluate survival in gastric cancer (GC) patients undergoing neoadjuvant treatment (NT). MATERIALS AND METHODS: This retrospective study included GC patients undergoing NT from two centers. CT images both pre-NT and post-NT were preprocessed, focusing on the automatic segmentation of subcutaneous fat, visceral fat, and skeletal muscle regions using TotalSegmentator. Delta Radiomics features were extracted using Pyradiomics. After feature fusion and selection, the optimal model is Naive Bayes (Rad model). A hybrid DL model was developed by combining ResNet18 and Transformer networks for feature extraction. The Clinic_Rad_DL model was constructed by combining clinical features, radiomic signatures, and DL signatures. The ExtraTree classifier was used for the Clinic_Rad_DL model, while a separate Cox regression model was developed for survival analysis using the same features. RESULTS: A total of 356 patients (mean age, 59 ± 10 years; 264 males [74.2%]) were enrolled and divided into training, validation, and test sets in a 7:2:1 ratio. The DL model outperformed the Rad model. The Clinic_Rad_DL model outperformed both Rad model and DL model, with AUC of 0.915, 0.890, and 0.890 in training, validation, and test sets, respectively. The Cox proportional hazards model showed C-index of 0.806, 0.803, and 0.819, effectively stratifying patients into high- and low-risk groups with significant survival differences. CONCLUSION: The study developed and validated a BC-based DL model to predict survival in GC patients undergoing NT, offering potential for personalized treatment strategies in clinical practice.

References

1. 1.Zhang, Y., Tong, T., Hou, B., Yu, T., Su, P., Yu, J., & Huang, Y. (2026). Predicting prognosis for gastric cancer patients receiving neoadjuvant treatment with body composition-based deep learning. Cancer Medicine. https://doi.org/10.1002/cam4.71886