MSHT: Multi-stage Hybrid Transformer for the ROSE Image Analysis of Pancreatic Cancer

TL;DR

This paper introduces MSHT, a multi-stage hybrid Transformer model that combines CNN and Transformer features to improve the accuracy and interpretability of pancreatic cancer diagnosis from ROSE images, enabling automated analysis.

Contribution

The paper presents a novel multi-stage hybrid Transformer architecture that integrates CNN spatial features with Transformer global modeling for pancreatic cancer image analysis.

Findings

Achieved 95.68% classification accuracy on ROSE images.

Outperformed state-of-the-art models in accuracy and interpretability.

Demonstrated potential for automated clinical decision support.

Abstract

Pancreatic cancer is one of the most malignant cancers in the world, which deteriorates rapidly with very high mortality. The rapid on-site evaluation (ROSE) technique innovates the workflow by immediately analyzing the fast stained cytopathological images with on-site pathologists, which enables faster diagnosis in this time-pressured process. However, the wider expansion of ROSE diagnosis has been hindered by the lack of experienced pathologists. To overcome this problem, we propose a hybrid high-performance deep learning model to enable the automated workflow, thus freeing the occupation of the valuable time of pathologists. By firstly introducing the Transformer block into this field with our particular multi-stage hybrid design, the spatial features generated by the convolutional neural network (CNN) significantly enhance the Transformer global modeling. Turning multi-stage spatial features as global attention guidance, this design combines the robustness from the inductive bias of CNN with the sophisticated global modeling power of Transformer. A dataset of 4240 ROSE images is collected to evaluate the method in this unexplored field. The proposed multi-stage hybrid Transformer (MSHT) achieves 95.68% in classification accuracy, which is distinctively higher than the state-of-the-art models. Facing the need for interpretability, MSHT outperforms its counterparts with more accurate attention regions. The results demonstrate that the MSHT can distinguish cancer samples accurately at an unprecedented image scale, laying the foundation for deploying automatic decision systems and enabling the expansion of ROSE in clinical practice. The code and records are available at: https://github.com/sagizty/Multi-Stage-Hybrid-Transformer.