Detection of subtle white matter lesions in MRI through texture feature extraction and boundary delineation using an embedded clustering strategy.
Kokhaur Ong, David M Young, Sarina Sulaiman, Siti Mariyam Shamsuddin, Norzaini Rose Mohd Zain, Hilwati Hashim, Kahhay Yuen, Stephan J Sanders, Weimiao Yu, Seepheng Hang
Author Information
Kokhaur Ong: Bioinformatics Institute, A*STAR, Singapore, Singapore.
David M Young: Institute of Molecular and Cell Biology, A*STAR, Singapore, Singapore.
Sarina Sulaiman: School of Computing, Faculty of Engineering, Universiti Teknologi Malaysia, Johor, Malaysia.
Siti Mariyam Shamsuddin: School of Computing, Faculty of Engineering, Universiti Teknologi Malaysia, Johor, Malaysia.
Norzaini Rose Mohd Zain: Department of Radiology, Hospital Kuala Lumpur, Kuala Lumpur, Malaysia.
Hilwati Hashim: Department of Radiology, Faculty of Medicine, Universiti Teknologi MARA, Sungai Buloh, Malaysia.
Kahhay Yuen: School of Pharmaceutical Sciences, Universiti Sains Malaysia, Penang, Malaysia.
Stephan J Sanders: Department of Psychiatry and Behavioral Sciences, UCSF Weill Institute for Neurosciences, University of California, San Francisco, USA.
Weimiao Yu: Bioinformatics Institute, A*STAR, Singapore, Singapore. yu_weimiao@bii.a-star.edu.sg.
Seepheng Hang: Department of Mathematical Sciences, Faculty of Science, Universiti Teknologi Malaysia, UTM Skudai, 81310, Johor, Malaysia. sphang@utm.my.
White matter lesions (WML) underlie multiple brain disorders, and automatic WML segmentation is crucial to evaluate the natural disease course and effectiveness of clinical interventions, including drug discovery. Although recent research has achieved tremendous progress in WML segmentation, accurate detection of subtle WML present early in the disease course remains particularly challenging. Here we propose an approach to automatic WML segmentation of mild WML loads using an intensity standardisation technique, gray level co-occurrence matrix (GLCM) embedded clustering technique, and random forest (RF) classifier to extract texture features and identify morphology specific to true WML. We precisely define their boundaries through a local outlier factor (LOF) algorithm that identifies edge pixels by local density deviation relative to its neighbors. The automated approach was validated on 32 human subjects, demonstrating strong agreement and correlation (excluding one outlier) with manual delineation by a neuroradiologist through Intra-Class Correlation (ICC = 0.881, 95% CI 0.769, 0.941) and Pearson correlation (r = 0.895, p-value < 0.001), respectively, and outperforming three leading algorithms (Trimmed Mean Outlier Detection, Lesion Prediction Algorithm, and SALEM-LS) in five of the six established key metrics defined in the MICCAI Grand Challenge. By facilitating more accurate segmentation of subtle WML, this approach may enable earlier diagnosis and intervention.
