A Standardized Pipeline for Colon Nuclei Identification and Counting Challenge

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.

Nuclear Segmentation and Classification Model with Imbalanced Classes for CoNiC Challenge

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 based on the Lizard dataset. In this challenge, computer algorithms should be able to segment and recognize six types of nuclei, including Epithelial, Lymphocyte, Plasma, Eosinophil, Neutrophil, Connective tissue. This challenge introduces two highly correlated tasks, nuclei segmentation and classification task and prediction of cellular composition task. There are a few obstacles we have to address in this challenge, 1) imbalanced annotations with few training samples on minority classes, 2) color variation of the images from multiple centers or scanners, 3) limited training samples, 4) similar morphological appearance among classes. To deal with these challenges, we proposed a systematic pipeline for nuclear segmentation and classification. 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 33rd) and 0.62199 r2 (Rank 4th) in the preliminary test phase.