Robust Interactive Semantic Segmentation of Pathology Images with Minimal User Input

TL;DR

This paper introduces a minimal-input interactive segmentation method for pathology images that efficiently annotates tissue regions, reducing expert effort and outperforming existing models in accuracy and speed.

Contribution

The authors propose a novel interactive segmentation network that requires only simple user input and automatic guiding signal generation, improving robustness and efficiency in tissue region annotation.

Findings

Speeds up the annotation process significantly.

Outperforms existing automatic and interactive segmentation models.

Effective on breast cancer histology images.

Abstract

From the simple measurement of tissue attributes in pathology workflow to designing an explainable diagnostic/prognostic AI tool, access to accurate semantic segmentation of tissue regions in histology images is a prerequisite. However, delineating different tissue regions manually is a laborious, time-consuming and costly task that requires expert knowledge. On the other hand, the state-of-the-art automatic deep learning models for semantic segmentation require lots of annotated training data and there are only a limited number of tissue region annotated images publicly available. To obviate this issue in computational pathology projects and collect large-scale region annotations efficiently, we propose an efficient interactive segmentation network that requires minimum input from the user to accurately annotate different tissue types in the histology image. The user is only required to draw a simple squiggle inside each region of interest so it will be used as the guiding signal for the model. To deal with the complex appearance and amorph geometry of different tissue regions we introduce several automatic and minimalistic guiding signal generation techniques that help the model to become robust against the variation in the user input. By experimenting on a dataset of breast cancer images, we show that not only does our proposed method speed up the interactive annotation process, it can also outperform the existing automatic and interactive region segmentation models.