FrGNet: A fourier-guided weakly-supervised framework for nuclear instance segmentation

TL;DR

FrGNet is a novel weakly-supervised framework that leverages Fourier guidance and contrastive learning to improve nuclear instance segmentation accuracy with minimal annotation, outperforming state-of-the-art methods.

Contribution

The paper introduces a Fourier guidance module and a guide-based contrastive module for weakly-supervised nuclear segmentation, enhancing feature representation and segmentation performance.

Findings

Outperforms current SOTA methods under fully-supervised training.

Maintains high performance with minimal labeling in weakly-supervised settings.

Effectively generalizes to unseen data without additional labeling.

Abstract

Nuclear instance segmentation has played a critical role in pathology image analysis. The main challenges arise from the difficulty in accurately segmenting instances and the high cost of precise mask-level annotations for fully-supervised training.In this work, we propose a fourier guidance framework for solving the weakly-supervised nuclear instance segmentation problem. In this framework, we construct a fourier guidance module to fuse the priori information into the training process of the model, which facilitates the model to capture the relevant features of the nuclear. Meanwhile, in order to further improve the model's ability to represent the features of nuclear, we propose the guide-based instance level contrastive module. This module makes full use of the framework's own properties and guide information to effectively enhance the representation features of nuclear. We show on two public datasets that our model can outperform current SOTA methods under fully-supervised design, and in weakly-supervised experiments, with only a small amount of labeling our model still maintains close to the performance under full supervision.In addition, we also perform generalization experiments on a private dataset, and without any labeling, our model is able to segment nuclear images that have not been seen during training quite effectively. As open science, all codes and pre-trained models are available at https://github.com/LQY404/FrGNet.