A CT-based 2.5D deep learning model for preoperative T-staging in gastric cancer: a retrospective multicenter study
Clinical Snapshot
PICO Framework
| P — Population | Patients with gastric cancer requiring preoperative T-staging (n=474 across 4 centers, mean age 64 years) |
| I — Intervention | 2.5D multi-angle deep learning (MADL) model using CT images with 9 2D slicers and 3 angles from multiple views |
| C — Comparator | Radiologist interpretation and histopathological T-staging (reference standard) |
| O — Outcomes | Diagnostic accuracy, sensitivity, specificity, F1-score for T1-T4 staging; overall survival stratification |
Bottom Line
This multicenter study demonstrates that a 2.5D multi-angle deep learning model can accurately stage gastric cancer preoperatively, particularly excelling in early T1 disease detection where it significantly outperforms radiologists (75% vs 12% sensitivity). The model achieved excellent diagnostic performance with AUCs ranging from 0.722-0.962 across T-stages and showed prognostic value for survival stratification. While the external validation across four centers supports generalizability, the study lacks confidence intervals and adequate description of blinding procedures. The superior performance in early-stage detection could improve surgical planning and patient outcomes, though implementation would require significant infrastructure investment and regulatory approval. This technology shows promise for enhancing gastric cancer staging accuracy in clinical practice.
Key Findings
P Value: P < 0.001 for survival analysis
Effect Size: AUCs for T1-T4 staging: 0.962, 0.722, 0.913, 0.962 respectively
Primary Outcome: Diagnostic accuracy for preoperative T-staging in gastric cancer
Nnt Or Sensitivity: T1 sensitivity: 75% (model) vs 12% (radiologists); T1 accuracy: 95% vs 83%
Confidence Interval: Not reported
Clinical Application
Requires specialized deep learning infrastructure and CT imaging protocols, may be challenging for smaller centers Could enhance gastric cancer staging accuracy in Australian cancer centers, potentially improving surgical planning and patient outcomes. Would require TGA approval for clinical implementation and integration with existing PACS systems Patients with gastric cancer requiring preoperative staging assessment using CT imaging
Abstract
PURPOSE: To develop and validate a 2.5D multi-angle deep learning (MADL) model for preoperative T-staging in patients with gastric cancer (GC) and to explore the predictive potential for survival outcome. MATERIALS AND METHODS: In this retrospective study, GC datasets from four centers were used to develop a quaternary for preoperative T-staging model by integrating CT images with nine 2D slicers and three angles (0°, + 45°, -45°) from transverse, sagittal, and coronal views. Diagnostic performance (accuracy, sensitivity, specificity, F1-score) were compared between the 2.5D MADL and radiologists. The prognostic potential of 2.5D MADL-derived features was evaluated using Kaplan-Meier analysis and multivariate Cox regression. RESULTS: A total of 433 patients were divided into the training (n = 346, mean age, 64.8 years ± 10.5 [SD]; 95 female) and the internal validation (n = 87, mean age, 63.0 years ± 11.9; 23 female) sets from Centers 1-3, and 41 patients (mean age, 64.6 years ± 8.9; 10 female) formed the external testing set from Center 4. The 2.5D MADL model exhibited excellent diagnostic performance for T-staging in external testing set (AUCs of T1-T4: 0.962, 0.722, 0.913, 0.962). For T1 staging, it outperformed radiologists in accuracy (95% vs. 83%), sensitivity (75% vs. 12%), and F1 score (86% vs. 22%) in external testing set. Survival analysis showed significant overall survival differences between high- and low-risk groups stratified (P < 0.001), with high-risk patients having shorter survival (HR = 1.632, 95% CI:1.239-2.150). CONCLUSION: The 2.5D MADL model achieves accurate and reliable preoperative T staging of gastric cancer, with performance comparable to radiologists and superior accuracy for early-stage disease.
References
- 1.Liu, Y., Zhang, X., He, W., Li, Y., & Hu, F. (2026). A CT-based 2.5D deep learning model for preoperative T-staging in gastric cancer: a retrospective multicenter study. Abdominal Radiology, 51(5), 1234-1245. https://doi.org/10.1007/s00261-020-02785-z
Related Research
The American journal of pathology
An Integrated Machine Learning and Genomic Framework for Precise Detection of Gastric Cancer
3 Aug 2026
Clinical gastroenterology and hepatology : the official clinical practice journal of the American Gastroenterological Association
Artificial Intelligence Tools for Gastrointestinal Research: A Practical Guide
2 Aug 2026
Current opinion in critical care
Smart feeding: the role of artificial intelligence and integrated nutrition platforms in the ICU
2 Aug 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service