Local Feature Extraction and Information Bottleneck-Based Segmentation of Brain Magnetic Resonance (MR) Images

Application of Clustering-Based Analysis in MRI Brain Tissue Segmentation

The segmentation of brain tissue by MRI not only contributes to the study of the function and anatomical structure of the brain, but it also offers a theoretical foundation for the diagnosis and treatment of brain illnesses. When discussing the anatomy of the brain in a clinical setting, the terms “white matter,” “gray matter,” and “cerebrospinal fluid” are the ones most frequently used (CSF). However, due to the fact that the human brain is highly complicated in its structure and that there are many different types of brain tissues, the human brain structure of each individual has its own set of distinctive qualities. Because of these several circumstances, the process of segmenting brain tissue will be challenging. In this article, several different clustering algorithms will be discussed, and their performance and effects will be compared to one another. The goal of this comparison is to determine which algorithm is most suited for segmenting MRI brain tissue. Based on the clustering method, the primary emphasis of this research is placed on the segmentation approach that is appropriate for medical brain imaging. The qualitative and quantitative findings of the experiment reveal that the FCM algorithm has more steady performance and better universality, but it is necessary to include the additional auxiliary conditions in order to achieve more ideal outcomes.

Semi–Automatic Corpus Callosum Segmentation and 3D Visualization Using Active Contour Methods

Accurate 3D computer models of the brain, and also of parts of its structure such as the corpus callosum (CC) are increasingly used in routine clinical diagnostics. This study presents comparative research to assess the utility and performance of three active contour methods (ACMs) for segmenting the CC from magnetic resonance (MR) images of the brain, namely: an edge-based active contour model using an inflation/deflation force with a damping coefficient (EM), the Selective Binary and Gaussian Filtering Regularized Level Set (SBGFRLS) method and the Distance Regularized Level Set Evolution (DRLSE) method. The pre-processing methods applied during research work were to improve the contrast, reduce noise and thus help segment the CC better. In this project, 3D CC models reconstructed based on the segmentations of cross-sections of MR images were also visualised. The results, as measured by quantitative tests of the similarity indice (SI) and overlap value (OV) are the best for the EM model (SI = 92%, OV = 82%) and are comparable to or better than those for other methods taken from a literature review. Furthermore, the properties of the EM model consisting in its ability to both expand and shrink at the same time allow segmentations to be better fitted in subsequent CC slices then in state-of-the art ACMs such as DRLSE or SBGFRLS. The CC contours from previous and subsequent iterations produced by the EM model can be used for initiation in subsequent or previous frames of MR images, which makes the segmentation process easier, particularly as the CC area can increase or decrease in subsequent MR image frames.

KL Divergence-Based Fuzzy Cluster Ensemble for Image Segmentation

Ensemble clustering combines different basic partitions of a dataset into a more stable and robust one. Thus, cluster ensemble plays a significant role in applications like image segmentation. However, existing ensemble methods have a few demerits, including the lack of diversity of basic partitions and the low accuracy caused by data noise. In this paper, to get over these difficulties, we propose an efficient fuzzy cluster ensemble method based on Kullback-Leibler divergence or simply, the KL divergence. The data are first classified with distinct fuzzy clustering methods. Then, the soft clustering results are aggregated by a fuzzy KL divergence-based objective function. Moreover, for image segmentation problems, we utilize the local spatial information in the cluster ensemble algorithm to suppress the effect of noise. Experiment results reveal that the proposed methods outperform many other methods in synthetic and real image-segmentation problems.