# A semi-supervised segmentation method for microscopic hyperspectral pathological images based on multi-consistency learning

## TL;DR

This paper introduces a new semi-supervised method for segmenting high-resolution hyperspectral pathological images using multi-consistency learning to reduce the need for precise annotations.

## Contribution

The novel MCL-Net method combines pseudo-labeling and consistency regularization for semi-supervised segmentation of hyperspectral pathological images.

## Key findings

- MCL-Net improves segmentation accuracy by leveraging pseudo-labels and multi-decoder consistency.
- Experiments show the method is effective for hyperspectral pathological image segmentation with limited annotations.
- The proposed strategy enhances feature learning by promoting consistency among multiple decoders.

## Abstract

Pathological images are considered the gold standard for clinical diagnosis and cancer grading. Automatic segmentation of pathological images is a fundamental and crucial step in constructing powerful computer-aided diagnostic systems. Medical microscopic hyperspectral pathological images can provide additional spectral information, further distinguishing different chemical components of biological tissues, offering new insights for accurate segmentation of pathological images. However, hyperspectral pathological images have higher resolution and larger area, and their annotation requires more time and clinical experience. The lack of precise annotations limits the progress of research in pathological image segmentation. In this paper, we propose a novel semi-supervised segmentation method for microscopic hyperspectral pathological images based on multi-consistency learning (MCL-Net), which combines consistency regularization methods with pseudo-labeling techniques. The MCL-Net architecture employs a shared encoder and multiple independent decoders. We introduce a Soft-Hard pseudo-label generation strategy in MCL-Net to generate pseudo-labels that are closer to real labels for pathological images. Furthermore, we propose a multi-consistency learning strategy, treating pseudo-labels generated by the Soft-Hard process as real labels, by promoting consistency between predictions of different decoders, enabling the model to learn more sample features. Extensive experiments in this paper demonstrate the effectiveness of the proposed method, providing new insights for the segmentation of microscopic hyperspectral tissue pathology images.