Fuzzy Clustering Based Segmentation Of Vertebrae in T1-Weighted Spinal MR Images

TL;DR

This paper introduces a robust fuzzy C-means clustering method for segmenting vertebrae in T1-weighted spinal MRI images, addressing challenges like noise and artifacts to improve diagnostic accuracy.

Contribution

It develops an unsupervised fuzzy clustering approach that outperforms traditional methods like Otsu thresholding and K-means in spinal MRI segmentation.

Findings

Fuzzy C-means achieved higher Dice coefficients than Otsu and K-means.

The method demonstrated robustness against noise and artifacts.

Segmentation accuracy was validated with radiologist annotations.

Abstract

Image segmentation in the medical domain is a challenging field owing to poor resolution and limited contrast. The predominantly used conventional segmentation techniques and the thresholding methods suffer from limitations because of heavy dependence on user interactions. Uncertainties prevalent in an image cannot be captured by these techniques. The performance further deteriorates when the images are corrupted by noise, outliers and other artifacts. The objective of this paper is to develop an effective robust fuzzy C- means clustering for segmenting vertebral body from magnetic resonance image owing to its unsupervised form of learning. The motivation for this work is detection of spine geometry and proper localisation and labelling will enhance the diagnostic output of a physician. The method is compared with Otsu thresholding and K-means clustering to illustrate the robustness.The reference standard for validation was the annotated images from the radiologist, and the Dice coefficient and Hausdorff distance measures were used to evaluate the segmentation.