Multi-Scale Hybrid Vision Transformer for Learning Gastric Histology: AI-Based Decision Support System for Gastric Cancer Treatment

TL;DR

This paper introduces a multi-scale hybrid Vision Transformer AI system that accurately classifies gastric cancer subtypes from histology slides, improving diagnostic sensitivity and efficiency in clinical settings.

Contribution

It presents a novel hybrid ViT model enabling fine-grained gastric cancer subclassification aligned with treatment guidance, enhancing AI-assisted pathology.

Findings

Achieved class-average sensitivity above 0.85 on 1,212 slides.

AI-assisted pathologists improved sensitivity by 12%.

Screening time reduced by 18%.

Abstract

Gastric endoscopic screening is an effective way to decide appropriate gastric cancer (GC) treatment at an early stage, reducing GC-associated mortality rate. Although artificial intelligence (AI) has brought a great promise to assist pathologist to screen digitalized whole slide images, existing AI systems are limited in fine-grained cancer subclassifications and have little usability in planning cancer treatment. We propose a practical AI system that enables five subclassifications of GC pathology, which can be directly matched to general GC treatment guidance. The AI system is designed to efficiently differentiate multi-classes of GC through multi-scale self-attention mechanism using 2-stage hybrid Vision Transformer (ViT) networks, by mimicking the way how human pathologists understand histology. The AI system demonstrates reliable diagnostic performance by achieving class-average sensitivity of above 0.85 on a total of 1,212 slides from multicentric cohort. Furthermore, AI-assisted pathologists show significantly improved diagnostic sensitivity by 12% in addition to 18% reduced screening time compared to human pathologists. Our results demonstrate that AI-assisted gastric endoscopic screening has a great potential for providing presumptive pathologic opinion and appropriate cancer treatment of gastric cancer in practical clinical settings.