A Standardized Pipeline for Colon Nuclei Identification and Counting Challenge
This work addresses computational pathology challenges like limited data and color variation for colorectal cancer analysis, but it is incremental as it integrates existing methods into a pipeline.
The authors tackled the CoNIC challenge for nuclear segmentation and classification in colorectal cancer histopathology by proposing a standardized pipeline with GAN-based data augmentation, stain normalization, and a HoVer-Net model with cost-sensitive loss, achieving 0.40665 mPQ+ (rank 49th) and 0.62199 r2 (rank 10th) in preliminary tests.
Nuclear segmentation and classification is an essential step for computational pathology. TIA lab from Warwick University organized a nuclear segmentation and classification challenge (CoNIC) for H&E stained histopathology images in colorectal cancer with two highly correlated tasks, nuclei segmentation and classification task and cellular composition task. There are a few obstacles we have to address in this challenge, 1) limited training samples, 2) color variation, 3) imbalanced annotations, 4) similar morphological appearance among classes. To deal with these challenges, we proposed a standardized pipeline for nuclear segmentation and classification by integrating several pluggable components. First, we built a GAN-based model to automatically generate pseudo images for data augmentation. Then we trained a self-supervised stain normalization model to solve the color variation problem. Next we constructed a baseline model HoVer-Net with cost-sensitive loss to encourage the model pay more attention on the minority classes. According to the results of the leaderboard, our proposed pipeline achieves 0.40665 mPQ+ (Rank 49th) and 0.62199 r2 (Rank 10th) in the preliminary test phase.