CausalCellSegmenter: Causal Inference inspired Diversified Aggregation Convolution for Pathology Image Segmentation
This work addresses the problem of accurate cell segmentation in pathology images for medical diagnosis, representing an incremental improvement over existing methods.
The paper tackles the challenge of robust cell nucleus segmentation across multiple domains by proposing CausalCellSegmenter, which combines causal inference and diversified aggregation convolution to address issues like background noise and overlapping cells, achieving a 3.6% improvement in mIoU and 2.65% in DSC on the MoNuSeg-2018 dataset.
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%.