Cluster-Induced Mask Transformers for Effective Opportunistic Gastric Cancer Screening on Non-contrast CT Scans

TL;DR

This paper introduces a novel deep learning model called cluster-induced Mask Transformer for non-invasive gastric cancer detection on non-contrast CT scans, achieving high sensitivity and specificity, and comparable to traditional screening methods.

Contribution

The study presents a new multi-task deep learning model that encodes tumor prototypes using learnable clusters, improving gastric cancer detection accuracy on CT scans.

Findings

Achieves 85.0% sensitivity and 92.6% specificity on test set.

Outperforms radiologists in sensitivity, matching state-of-the-art screening tools.

Demonstrates potential as a non-invasive, cost-effective screening method.

Abstract

Gastric cancer is the third leading cause of cancer-related mortality worldwide, but no guideline-recommended screening test exists. Existing methods can be invasive, expensive, and lack sensitivity to identify early-stage gastric cancer. In this study, we explore the feasibility of using a deep learning approach on non-contrast CT scans for gastric cancer detection. We propose a novel cluster-induced Mask Transformer that jointly segments the tumor and classifies abnormality in a multi-task manner. Our model incorporates learnable clusters that encode the texture and shape prototypes of gastric cancer, utilizing self- and cross-attention to interact with convolutional features. In our experiments, the proposed method achieves a sensitivity of 85.0% and specificity of 92.6% for detecting gastric tumors on a hold-out test set consisting of 100 patients with cancer and 148 normal. In comparison, two radiologists have an average sensitivity of 73.5% and specificity of 84.3%. We also obtain a specificity of 97.7% on an external test set with 903 normal cases. Our approach performs comparably to established state-of-the-art gastric cancer screening tools like blood testing and endoscopy, while also being more sensitive in detecting early-stage cancer. This demonstrates the potential of our approach as a novel, non-invasive, low-cost, and accurate method for opportunistic gastric cancer screening.