Diffusion tensor imaging for the differential diagnosis of Parkinsonism by machine learning

Chih-Chien Tsai; Yao-Liang Chen; Chin-Song Lu; Jur-Shan Cheng; Yi-Hsin Weng; Sung-Han Lin; Yi-Ming Wu; Jiun-Jie Wang

doi:10.1016/j.bj.2022.05.006

Diffusion tensor imaging for the differential diagnosis of Parkinsonism by machine learning

Biomed J. 2023 Jun;46(3):100541. doi: 10.1016/j.bj.2022.05.006. Epub 2022 Jun 4.

Authors

Chih-Chien Tsai¹, Yao-Liang Chen², Chin-Song Lu³, Jur-Shan Cheng⁴, Yi-Hsin Weng⁵, Sung-Han Lin⁶, Yi-Ming Wu⁷, Jiun-Jie Wang⁸

Affiliations

¹ Healthy Aging Research Center, Chang Gung University, Taoyuan, Taiwan.
² Department of Diagnostic Radiology, Chang Gung Memorial Hospital, Keelung, Taiwan; Department of Medical Imaging and Intervention, Chang Gung Memorial Hospital, Linkou, Taoyuan, Taiwan.
³ Professor Lu Neurological Clinic, Taoyuan, Taiwan; Division of Movement Disorders, Department of Neurology, Chang Gung Memorial Hospital, Linkou, Taoyuan, Taiwan; Department of Neurology, Landseed International Hospital, Taoyuan, Taiwan.
⁴ Clinical Informatics and Medical Statistics Research Center, Chang Gung University, Taoyuan, Taiwan; Division of Hepatology, Department of Gastroenterology and Hepatology, Chang Gung Memorial Hospital, Taoyuan, Taiwan.
⁵ Division of Movement Disorders, Department of Neurology, Chang Gung Memorial Hospital, Linkou, Taoyuan, Taiwan; School of Medicine, Chang Gung University, Taoyuan, Taiwan; Neuroscience Research Center, Chang Gung Memorial Hospital, Linkou, Taoyuan, Taiwan.
⁶ Advanced Imaging Research Center, University of Texas Southwestern Medical Center, Dallas, TX, USA.
⁷ Department of Medical Imaging and Intervention, Chang Gung Memorial Hospital, Linkou, Taoyuan, Taiwan; Department of Medical Imaging and Radiological Sciences, Chang Gung University, Taoyuan, Taiwan.
⁸ Healthy Aging Research Center, Chang Gung University, Taoyuan, Taiwan; Department of Diagnostic Radiology, Chang Gung Memorial Hospital, Keelung, Taiwan; Neuroscience Research Center, Chang Gung Memorial Hospital, Linkou, Taoyuan, Taiwan; Department of Medical Imaging and Radiological Sciences, Chang Gung University, Taoyuan, Taiwan; Institute for Radiological Research, Chang Gung University/Chang Gung Memorial Hospital, Linkou, Taoyuan, Taiwan. Electronic address: jwang@mail.cgu.edu.tw.

Abstract

Background: There are currently no specific tests for either idiopathic Parkinson's disease or Parkinson-plus syndromes. The study aimed to investigate the diagnostic performance of features extracted from the whole brain using diffusion tensor imaging concerning parkinsonian disorders.

Methods: The retrospective data yielded 625 participants (average age: 61.4 ± 8.2, men/women: 313/312; healthy controls/idiopathic Parkinson's disease/multiple system atrophy/progressive supranuclear palsy: 219/286/51/69) between 2008 and 2017. Diffusion-weighted images were obtained using a 3T MR scanner. The 90th, 50th, and 10th percentiles of fractional anisotropy and mean/axial/radial diffusivity from each parcellated brain area were recorded. Statistical analysis was evaluated based on the features extracted from the whole brain, as determined using discriminant function analysis and support vector machine. 20% of the participants were used as an independent blind dataset with 5 times cross-verification. Diagnostic performance was evaluated by the sensitivity and the F1 score.

Results: Diagnoses were accurate for distinguishing idiopathic Parkinson's disease from healthy control and Parkinson-plus syndromes (87.4 ± 2.1% and 82.5 ± 3.9%, respectively). Diagnostic F1 scores varied for Parkinson-plus syndromes with 67.2 ± 3.8% for multiple system atrophy and 71.6 ± 3.5% for progressive supranuclear palsy. For early and late detection of idiopathic Parkinson's disease, the diagnostic performance was 79.2 ± 7.4% and 84.4 ± 6.9%, respectively. The diagnostic performance was 68.8 ± 11.0% and 52.5 ± 8.9% in early and late detection to distinguish different Parkinson-plus syndromes.

Conclusions: Features extracted from diffusion tensor imaging of the whole brain can provide objective evidence for the diagnosis of healthy control, idiopathic Parkinson's disease, and Parkinson-plus syndromes with fair to very good diagnostic performance.

Keywords: Differential diagnosis; Diffusion tensor imaging; Idiopathic Parkinson’s disease; Machine learning; Parkinson-plus syndromes.

MeSH terms

Aged
Diagnosis, Differential
Diffusion Tensor Imaging / methods
Female
Humans
Machine Learning
Male
Middle Aged
Multiple System Atrophy* / diagnostic imaging
Parkinson Disease* / diagnostic imaging
Parkinsonian Disorders* / diagnostic imaging
Retrospective Studies
Supranuclear Palsy, Progressive* / diagnostic imaging
Syndrome