Improved Automatic Segmentation of White Matter Hyperintensities in MRI Based on Multilevel Lesion Features

• Published in: Neuroinformatics (Totowa, N.J.) Vol. 15; no. 3; pp. 231 - 245
• Main Authors: Rincón, M., Díaz-López, E., Selnes, P., Vegge, K., Altmann, M., Fladby, T., Bjørnerud, A.
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.07.2017; Springer Nature B.V
• Subjects: Adult; Aged; Algorithms; Attention deficit hyperactivity disorder; Bioinformatics; Biomedical and Life Sciences; Biomedicine; Brain Infarction - diagnostic imaging; Cerebrovascular system; Cognitive Dysfunction - diagnostic imaging; Computational Biology/Bioinformatics; Computer Appl. in Life Sciences; Female; Geriatrics; Humans; Image Interpretation, Computer-Assisted; Image processing; Magnetic Resonance Imaging; Male; Middle Aged; Nerve Fibers, Myelinated - pathology; Neurodegenerative diseases; Neurology; Neurosciences; Older people; Original Article; Segmentation; Substantia alba; Vascular diseases; White Matter - diagnostic imaging; White matter lesions; White matter hyperintensities; Amorphous object segmentation; Automated WMH detection; Similarity index; Object-oriented analysis; WM modelling
• ISSN: 1539-2791; 1559-0089; 1559-0089
• DOI: 10.1007/s12021-017-9328-y

Brain white matter hyperintensities (WMHs) are linked to increased risk of cerebrovascular and neurodegenerative diseases among the elderly. Consequently, detection and characterization of WMHs are of significant clinical importance. We propose a novel approach for WMH segmentation from multi-contrast MRI where both voxel-based and lesion-based information are used to improve overall performance in both volume-oriented and object-oriented metrics. Our segmentation method (AMOS-2D) consists of four stages following a “generate-and-test” approach: pre-processing, Gaussian white matter (WM) modelling, hierarchical multi-threshold WMH segmentation and object-based WMH filtering using support vector machines. Data from 28 subjects was used in this study covering a wide range of lesion loads. Volumetric T1-weighted images and 2D fluid attenuated inversion recovery (FLAIR) images were used as basis for the WM model and lesion masks defined manually in each subject by experts were used for training and evaluating the proposed method. The method obtained an average agreement (in terms of the Dice similarity coefficient, DSC) with experts equivalent to inter-expert agreement both in terms of WMH number (DSC = 0.637 vs. 0.651) and volume (DSC = 0.743 vs. 0.781). It allowed higher accuracy in detecting WMH compared to alternative methods tested and was further found to be insensitive to WMH lesion burden. Good agreement with expert annotations combined with stable performance largely independent of lesion burden suggests that AMOS-2D will be a valuable tool for fully automated WMH segmentation in patients with cerebrovascular and neurodegenerative pathologies.