CDNet: Causal Inference inspired Diversified Aggregation Convolution for Pathology Image Segmentation
Keywords: Causal inference, Feature aggregation, Nuclei segmentation, Pathology image
Abstract: Deep learning models have shown promising performance for Nuclei segmentation in the field of pathology image analysis. However, training a robust model from multiple domains remains a great challenge for Nuclei segmentation. Additionally, the shortcomings of background noise, highly overlapping between Nuclei, and blurred edges often lead to poor performance. To address these challenges, we propose a novel framework termed CDNet, 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 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 and GLySAC datasets yielded promising results, with mean intersection over union (mIoU) and Dice similarity coefficient (DSC) scores increasing by 3.59\% and 2.61\%, and 2.71\% and 2.04\%, respectively, outperforming other state-of-the-art methods.
Submission Number: 8
Loading