MGTUNet: An new UNet for colon nuclei instance segmentation and quantification

TL;DR

This paper introduces MGTUNet, a novel UNet-based model that simultaneously performs nuclei instance segmentation, classification, and component regression in colon tissue images, achieving state-of-the-art accuracy.

Contribution

The paper presents MGTUNet, a new UNet variant with enhanced features like Mish activation, group normalization, and a ranger optimizer for improved end-to-end nuclei analysis.

Findings

Achieved PQ of 0.6254 and mPQ of 0.6359, outperforming existing models.

Demonstrated effective simultaneous segmentation, classification, and regression tasks.

Validated state-of-the-art performance on colon histopathological image datasets.

Abstract

Colorectal cancer (CRC) is among the top three malignant tumor types in terms of morbidity and mortality. Histopathological images are the gold standard for diagnosing colon cancer. Cellular nuclei instance segmentation and classification, and nuclear component regression tasks can aid in the analysis of the tumor microenvironment in colon tissue. Traditional methods are still unable to handle both types of tasks end-to-end at the same time, and have poor prediction accuracy and high application costs. This paper proposes a new UNet model for handling nuclei based on the UNet framework, called MGTUNet, which uses Mish, Group normalization and transposed convolution layer to improve the segmentation model, and a ranger optimizer to adjust the SmoothL1Loss values. Secondly, it uses different channels to segment and classify different types of nucleus, ultimately completing the nuclei instance segmentation and classification task, and the nuclei component regression task simultaneously. Finally, we did extensive comparison experiments using eight segmentation models. By comparing the three evaluation metrics and the parameter sizes of the models, MGTUNet obtained 0.6254 on PQ, 0.6359 on mPQ, and 0.8695 on R2. Thus, the experiments demonstrated that MGTUNet is now a state-of-the-art method for quantifying histopathological images of colon cancer.