Comparative validation of AI and non-AI methods in MRI volumetry to diagnose Parkinsonian syndromes

Abstract

Automated segmentation and volumetry of brain magnetic resonance imaging (MRI) scans are essential for the diagnosis of Parkinson’s disease (PD) and Parkinson’s plus syndromes (P-plus). To enhance the diagnostic performance, we adopt deep learning (DL) models in brain MRI segmentation and compared their performance with the gold-standard non-DL method. We collected brain MRI scans of healthy controls ($$n=105$$ n = 105 ) and patients with PD ($$n=105$$ n = 105 ), multiple systemic atrophy ($$n=132$$ n = 132 ), and progressive supranuclear palsy ($$n=69$$ n = 69 ) at Samsung Medical Center from January 2017 to December 2020. Using the gold-standard non-DL model, FreeSurfer (FS), we segmented six brain structures: midbrain, pons, caudate, putamen, pallidum, and third ventricle, and considered them as annotated data for DL models, the representative convolutional neural network (CNN) and vision transformer (ViT)-based models. Dice scores and the area under the curve (AUC) for differentiating normal, PD, and P-plus cases were calculated to determine the measure to which FS performance can be reproduced as-is while increasing speed by the DL approaches. The segmentation times of CNN and ViT for the six brain structures per patient were 51.26 ± 2.50 and 1101.82 ± 22.31 s, respectively, being 14 to 300 times faster than FS (15,735 ± 1.07 s). Dice scores of both DL models were sufficiently high (> 0.85) so their AUCs for disease classification were not inferior to that of FS. For classification of normal vs. P-plus and PD vs. P-plus (except multiple systemic atrophy - Parkinsonian type) based on all brain parts, the DL models and FS showed AUCs above 0.8, demonstrating the clinical value of DL models in addition to FS. DL significantly reduces the analysis time without compromising the performance of brain segmentation and differential diagnosis. Our findings may contribute to the adoption of DL brain MRI segmentation in clinical settings and advance brain research.

Assessing cortical features in early stage ASD children

“…Specifically, motion correction was performed prior to averaging when using different source volumes in order to compensate for small variations in motion between volumes. In addition, intensity normalisation was applied to the original volume and the intensities of all voxels were scaled to the mean value of the white matter ( 23 ). After correcting the movements and normalising the data, FS removed the skull to isolate the brain from extracranial or non-brain tissue in a process known as skull stripping ( 24 ).…”