TA-Net: Topology-Aware Network for Gland Segmentation

TL;DR

TA-Net is a novel topology-aware deep learning model that improves gland segmentation accuracy in histopathology images, especially for densely clustered glands, by incorporating gland topology estimation into its multitask learning framework.

Contribution

The paper introduces TA-Net, a topology-aware network with a multitask architecture that jointly learns gland instance segmentation and topology estimation, enhancing segmentation of densely clustered glands.

Findings

Achieves state-of-the-art performance on GlaS and CRAG datasets.

Outperforms existing methods in densely clustered gland scenarios.

Improves generalization through topology-aware loss and multitask learning.

Abstract

Gland segmentation is a critical step to quantitatively assess the morphology of glands in histopathology image analysis. However, it is challenging to separate densely clustered glands accurately. Existing deep learning-based approaches attempted to use contour-based techniques to alleviate this issue but only achieved limited success. To address this challenge, we propose a novel topology-aware network (TA-Net) to accurately separate densely clustered and severely deformed glands. The proposed TA-Net has a multitask learning architecture and enhances the generalization of gland segmentation by learning shared representation from two tasks: instance segmentation and gland topology estimation. The proposed topology loss computes gland topology using gland skeletons and markers. It drives the network to generate segmentation results that comply with the true gland topology. We validate the proposed approach on the GlaS and CRAG datasets using three quantitative metrics, F1-score, object-level Dice coefficient, and object-level Hausdorff distance. Extensive experiments demonstrate that TA-Net achieves state-of-the-art performance on the two datasets. TA-Net outperforms other approaches in the presence of densely clustered glands.