Using Multi-scale SwinTransformer-HTC with Data augmentation in CoNIC Challenge

TL;DR

This paper presents a multi-scale Swin Transformer with HTC and data augmentation techniques for automatic segmentation and classification of cells in histopathology images, aiming to improve efficiency in colorectal cancer diagnosis.

Contribution

The study introduces a novel multi-scale Swin Transformer combined with HTC and data augmentation for improved cell segmentation and classification in histopathology images.

Findings

Multi-scale features significantly improve recognition accuracy.

Data augmentation enhances model robustness.

Proposed method outperforms baseline models in the CoNIC challenge.

Abstract

Colorectal cancer is one of the most common cancers worldwide, so early pathological examination is very important. However, it is time-consuming and labor-intensive to identify the number and type of cells on H&E images in clinical. Therefore, automatic segmentation and classification task and counting the cellular composition of H&E images from pathological sections is proposed by CoNIC Challenge 2022. We proposed a multi-scale Swin transformer with HTC for this challenge, and also applied the known normalization methods to generate more augmentation data. Finally, our strategy showed that the multi-scale played a crucial role to identify different scale features and the augmentation arose the recognition of model.