Abstract:
The establishment of an unbiased protocol for the automated volumetric measure ment of iron-rich regions in the substantia nigra (SN) is clinically important for diag nosing neurodegenerative diseases exhibiting midbrain atrophy, such as progressive
supranuclear palsy (PSP). This study aimed to automatically quantify the volume and
surface properties of the iron-rich 3D regions in the SN using the quantitative MRI R2
* map. Three hundred and sixty-seven slices of R2
* map and susceptibility-weighted
imaging (SWI) at 3-T MRI from healthy control (HC) individuals and Parkinson's dis ease (PD) patients were used to train customized U-net++ convolutional neural net work based on expert-segmented masks. Age- and sex-matched participants were
selected from HC, PD, and PSP groups to automate the volumetric determination of
iron-rich areas in the SN. Dice similarity coefficient values between expert segmented and detected masks from the proposed network were 0:91 0:07 for R2
*
maps and 0:89 0:08 for SWI. Reductions in iron-rich SN volume from the R2
* map
(SWI) were observed in PSP with area under the receiver operating characteristic
curve values of 0.96 (0.89) and 0.98 (0.92) compared with HC and PD, respectively.
The mean curvature of the PSP showed SN deformation along the side closer to the
red nucleus. We demonstrated the automated volumetric measurement of iron-rich
regions in the SN using deep learning can quantify the SN atrophy in PSP compared
with PD and HC.
