Automated segmentation of white matter fiber bundles using diffusion tensor imaging data and a new density based clustering algorithm

• Published in: Artificial intelligence in medicine Vol. 73; pp. 14 - 22
• Main Authors: Kamali, Tahereh, Stashuk, Daniel
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.10.2016
• Subjects: Algorithms; Bundles; Chameleon; Cluster Analysis; Clustering; Clusters; DBSCAN; Density; Density-based clustering algorithm; Diffusion Tensor Imaging; Fibers; Humans; Image segmentation; Internal Medicine; Mental Disorders - diagnostic imaging; Other; Spectral clustering; White Matter - diagnostic imaging; White matter fiber bundles segmentation; Density-based clustering algorithm; DBSCAN; White matter fiber bundles segmentation; Spectral clustering; Chameleon
• ISSN: 0933-3657; 1873-2860; 1873-2860
• DOI: 10.1016/j.artmed.2016.09.003

•A novel segmentation algorithm for white matter tissues using DTI data is proposed.•This segmentation method is based on a new clustering algorithm called NDEC.•NDEC does not require number of clusters as a priori.•The performance of NDEC is compared with other clustering algorithms.•NDEC obtained best performance using Johns Hopkins University DTI data. Robust and accurate segmentation of brain white matter (WM) fiber bundles assists in diagnosing and assessing progression or remission of neuropsychiatric diseases such as schizophrenia, autism and depression. Supervised segmentation methods are infeasible in most applications since generating gold standards is too costly. Hence, there is a growing interest in designing unsupervised methods. However, most conventional unsupervised methods require the number of clusters be known in advance which is not possible in most applications. The purpose of this study is to design an unsupervised segmentation algorithm for brain white matter fiber bundles which can automatically segment fiber bundles using intrinsic diffusion tensor imaging data information without considering any prior information or assumption about data distributions. Here, a new density based clustering algorithm called neighborhood distance entropy consistency (NDEC), is proposed which discovers natural clusters within data by simultaneously utilizing both local and global density information. The performance of NDEC is compared with other state of the art clustering algorithms including chameleon, spectral clustering, DBSCAN and k-means using Johns Hopkins University publicly available diffusion tensor imaging data. The performance of NDEC and other employed clustering algorithms were evaluated using dice ratio as an external evaluation criteria and density based clustering validation (DBCV) index as an internal evaluation metric. Across all employed clustering algorithms, NDEC obtained the highest average dice ratio (0.94) and DBCV value (0.71). NDEC can find clusters with arbitrary shapes and densities and consequently can be used for WM fiber bundle segmentation where there is no distinct boundary between various bundles. NDEC may also be used as an effective tool in other pattern recognition and medical diagnostic systems in which discovering natural clusters within data is a necessity.