A New Automatic Change Detection Frame-work Based on Region Growing and Weighted Local Mutual Information: Analysis of Breast Tumor Response to Chemotherapy in Serial MR Images

TL;DR

This paper introduces an automatic change detection framework for longitudinal breast MR images, combining intensity normalization, region extraction, and region growing with weighted local mutual information, outperforming some human experts.

Contribution

The paper presents a novel framework integrating hierarchical histogram matching, region extraction, and weighted local mutual information for improved change detection in breast MRI.

Findings

Framework outperforms human experts in some cases

Effective detection of lesion evolution in longitudinal images

Robust to noise and false changes

Abstract

The automatic analysis of subtle changes between longitudinal MR images is an important task as it is still a challenging issue in scope of the breast medical image processing. In this paper we propose an effective automatic change detection framework composed of two phases since previously used methods have features with low distinctive power. First, in the preprocessing phase an intensity normalization method is suggested based on Hierarchical Histogram Matching (HHM) that is more robust to noise than previous methods. To eliminate undesirable changes and extract the regions containing significant changes the proposed Extraction Region of Changes (EROC) method is applied based on intensity distribution and Hill-Climbing algorithm. Second, in the detection phase a region growing-based approach is suggested to differentiate significant changes from unreal ones. Due to using proposed Weighted Local Mutual Information (WLMI) method to extract high level features and also utilizing the principle of the local consistency of changes, the proposed approach enjoys reasonable performance. The experimental results on both simulated and real longitudinal Breast MR Images confirm the effectiveness of the proposed framework. Also, this framework outperforms the human expert in some cases which can detect many lesion evolutions that are missed by expert.