Intensity-based Segmentation of Tissue Images Using a U-Net with a Pretrained ResNet-34 Encoder: Application to Mueller Microscopy

TL;DR

This paper introduces a novel intensity-based U-Net model with a pretrained ResNet-34 encoder for automated tissue segmentation in Mueller microscopy, achieving high accuracy with limited training data.

Contribution

The study presents a new intensity-only input approach combined with transfer learning for efficient tissue segmentation in Mueller microscopy images.

Findings

Achieved 89.71% pixel accuracy on test data.

Attained 80.96% mean tissue Dice coefficient.

Effective transfer learning from ImageNet with limited data.

Abstract

Manual annotation of the images of thin tissue sections remains a time-consuming step in Mueller microscopy and limits its scalability. We present a novel automated approach using only the total intensity M11 element of the Mueller matrix as an input to a U-Net architecture with a pretrained ResNet-34 encoder. The network was trained to distinguish four classes in the images of murine uterine cervix sections: background, internal os, cervical tissue, and vaginal wall. With only 70 cervical tissue sections, the model achieved 89.71% pixel accuracy and 80.96% mean tissue Dice coefficient on the held-out test dataset. Transfer learning from ImageNet enables accurate segmentation despite limited size of training dataset typical of specialized biomedical imaging. This intensity-based framework requires minimal preprocessing and is readily extensible to other imaging modalities and tissue types, with publicly available graphical annotation tools for practical deployment.