A deep learning algorithm for white matter hyperintensity lesion detection and segmentation

• Published in: Neuroradiology Vol. 64; no. 4; pp. 727 - 734
• Main Authors: Zhang, Yajing, Duan, Yunyun, Wang, Xiaoyang, Zhuo, Zhizheng, Haller, Sven, Barkhof, Frederik, Liu, Yaou
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.04.2022; Springer Nature B.V
• Subjects: Abnormalities; Algorithms; Automation; Blood vessels; Brain - diagnostic imaging; Brain - pathology; Deep Learning; Delineation; Diagnostic Neuroradiology; Disease; Humans; Image processing; Image segmentation; Imaging; Lesions; Leukoaraiosis - pathology; Leukoencephalopathies - pathology; Machine learning; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Medical imaging; Medicine; Medicine & Public Health; Multiple sclerosis; Neurology; Neuroradiology; Neurosciences; Neurosurgery; Parameter sensitivity; Patients; Radiology; Substantia alba; White Matter - diagnostic imaging; White Matter - pathology; Workflow; Automated detection and segmentation; White matter hyperintensity; FLAIR; Multiple sclerosis; Multicentre
• ISSN: 0028-3940; 1432-1920; 1432-1920
• DOI: 10.1007/s00234-021-02820-w

Purpose White matter hyperintensity (WMHI) lesions on MR images are an important indication of various types of brain diseases that involve inflammation and blood vessel abnormalities. Automated quantification of the WMHI can be valuable for the clinical management of patients, but existing automated software is often developed for a single type of disease and may not be applicable for clinical scans with thick slices and different scanning protocols. The purpose of the study is to develop and validate an algorithm for automatic quantification of white matter hyperintensity suitable for heterogeneous MRI data with different disease types. Methods We developed and evaluated “DeepWML”, a deep learning method for fully automated white matter lesion (WML) segmentation of multicentre FLAIR images. We used MRI from 507 patients, including three distinct white matter diseases, obtained in 9 centres, with a wide range of scanners and acquisition protocols. The automated delineation tool was evaluated through quantitative parameters of Dice similarity, sensitivity and precision compared to manual delineation (gold standard). Results The overall median Dice similarity coefficient was 0.78 (range 0.64 ~ 0.86) across the three disease types and multiple centres. The median sensitivity and precision were 0.84 (range 0.67 ~ 0.94) and 0.81 (range 0.64 ~ 0.92), respectively. The tool’s performance increased with larger lesion volumes. Conclusion DeepWML was successfully applied to a wide spectrum of MRI data in the three white matter disease types, which has the potential to improve the practical workflow of white matter lesion delineation.