A Geometric Flow Approach for Segmentation of Images with Inhomongeneous Intensity and Missing Boundaries

TL;DR

This paper introduces a novel geometric flow-based segmentation method that effectively handles intensity inhomogeneity and missing boundaries in MR images, improving accuracy over existing techniques.

Contribution

It proposes a new intensity correction method using a bias field estimate from fat fraction images and a semi-automatic segmentation approach with a geometric flow incorporating RKHS edge detection.

Findings

Achieved average dice scores of 92.5% for quadriceps muscles.

Significantly outperformed other state-of-the-art methods by at least 10%.

Demonstrated robustness in segmenting inhomogeneous MR images with missing boundaries.

Abstract

Image segmentation is a complex mathematical problem, especially for images that contain intensity inhomogeneity and tightly packed objects with missing boundaries in between. For instance, Magnetic Resonance (MR) muscle images often contain both of these issues, making muscle segmentation especially difficult. In this paper we propose a novel intensity correction and a semi-automatic active contour based segmentation approach. The approach uses a geometric flow that incorporates a reproducing kernel Hilbert space (RKHS) edge detector and a geodesic distance penalty term from a set of markers and anti-markers. We test the proposed scheme on MR muscle segmentation and compare with some state of the art methods. To help deal with the intensity inhomogeneity in this particular kind of image, a new approach to estimate the bias field using a fat fraction image, called Prior Bias-Corrected Fuzzy C-means (PBCFCM), is introduced. Numerical experiments show that the proposed scheme leads to significantly better results than compared ones. The average dice values of the proposed method are 92.5%, 85.3%, 85.3% for quadriceps, hamstrings and other muscle groups while other approaches are at least 10% worse.