CausalCellSegmenter: Causal Inference inspired Diversified Aggregation Convolution for Pathology Image Segmentation

TL;DR

This paper introduces CausalCellSegmenter, a novel pathology image segmentation framework combining causal inference and diversified aggregation convolution to improve robustness and accuracy across multiple domains.

Contribution

It proposes a new framework integrating Causal Inference Module and Diversified Aggregation Convolution for better cell nucleus segmentation.

Findings

Outperforms state-of-the-art methods on MoNuSeg-2018 dataset.

Achieves 3.6% higher mIoU and 2.65% higher DSC scores.

Effectively reduces false positives and improves edge clarity.

Abstract

Deep learning models have shown promising performance for cell nucleus segmentation in the field of pathology image analysis. However, training a robust model from multiple domains remains a great challenge for cell nucleus segmentation. Additionally, the shortcomings of background noise, highly overlapping between cell nucleus, and blurred edges often lead to poor performance. To address these challenges, we propose a novel framework termed CausalCellSegmenter, which combines Causal Inference Module (CIM) with Diversified Aggregation Convolution (DAC) techniques. The DAC module is designed which incorporates diverse downsampling features through a simple, parameter-free attention module (SimAM), aiming to overcome the problems of false-positive identification and edge blurring. Furthermore, we introduce CIM to leverage sample weighting by directly removing the spurious correlations between features for every input sample and concentrating more on the correlation between features and labels. Extensive experiments on the MoNuSeg-2018 dataset achieves promising results, outperforming other state-of-the-art methods, where the mIoU and DSC scores growing by 3.6% and 2.65%.