An Efficient Approach for Muscle Segmentation and 3D Reconstruction Using Keypoint Tracking in MRI Scan

TL;DR

This paper introduces a training-free, keypoint tracking method for muscle segmentation in MRI scans that reduces computational costs and improves interpretability while maintaining competitive accuracy.

Contribution

It presents a novel, training-free muscle segmentation approach using keypoint tracking and optical flow, offering a scalable and explainable alternative to CNN-based methods.

Findings

Achieves a mean DSC of 0.6 to 0.7, comparable to CNN models.

Reduces computational demands significantly.

Enhances interpretability of muscle segmentation results.

Abstract

Magnetic resonance imaging (MRI) enables non-invasive, high-resolution analysis of muscle structures. However, automated segmentation remains limited by high computational costs, reliance on large training datasets, and reduced accuracy in segmenting smaller muscles. Convolutional neural network (CNN)-based methods, while powerful, often suffer from substantial computational overhead, limited generalizability, and poor interpretability across diverse populations. This study proposes a training-free segmentation approach based on keypoint tracking, which integrates keypoint selection with Lucas-Kanade optical flow. The proposed method achieves a mean Dice similarity coefficient (DSC) ranging from 0.6 to 0.7, depending on the keypoint selection strategy, performing comparably to state-of-the-art CNN-based models while substantially reducing computational demands and enhancing interpretability. This scalable framework presents a robust and explainable alternative for muscle segmentation in clinical and research applications.