Single Slice Thigh CT Muscle Group Segmentation with Domain Adaptation and Self-Training

TL;DR

This paper introduces a novel unsupervised domain adaptation method with self-training to accurately segment thigh muscle groups in single slice CT images by transferring knowledge from MR images, achieving high accuracy.

Contribution

It presents the first pipeline for domain adaptation from MR to CT for thigh muscle segmentation using CycleGAN and self-training techniques.

Findings

Achieved a mean Dice score of 0.888 across muscle groups.

Effectively transferred labels from MR to CT images.

Demonstrated robustness and effectiveness on 152 test images.

Abstract

Objective: Thigh muscle group segmentation is important for assessment of muscle anatomy, metabolic disease and aging. Many efforts have been put into quantifying muscle tissues with magnetic resonance (MR) imaging including manual annotation of individual muscles. However, leveraging publicly available annotations in MR images to achieve muscle group segmentation on single slice computed tomography (CT) thigh images is challenging. Method: We propose an unsupervised domain adaptation pipeline with self-training to transfer labels from 3D MR to single CT slice. First, we transform the image appearance from MR to CT with CycleGAN and feed the synthesized CT images to a segmenter simultaneously. Single CT slices are divided into hard and easy cohorts based on the entropy of pseudo labels inferenced by the segmenter. After refining easy cohort pseudo labels based on anatomical assumption, self-training with easy and hard splits is applied to fine tune the segmenter. Results: On 152 withheld single CT thigh images, the proposed pipeline achieved a mean Dice of 0.888(0.041) across all muscle groups including sartorius, hamstrings, quadriceps femoris and gracilis. muscles Conclusion: To our best knowledge, this is the first pipeline to achieve thigh imaging domain adaptation from MR to CT. The proposed pipeline is effective and robust in extracting muscle groups on 2D single slice CT thigh images.The container is available for public use at https://github.com/MASILab/DA_CT_muscle_seg