An automatic interpretable deep learning pipeline for accurate Parkinson's disease diagnosis using quantitative susceptibility mapping and T1‐weighted images

Abstract

Parkinson's disease (PD) diagnosis based on magnetic resonance imaging (MRI) is still challenging clinically. Quantitative susceptibility maps (QSM) can potentially provide underlying pathophysiological information by detecting the iron distribution in deep gray matter (DGM) nuclei. We hypothesized that deep learning (DL) could be used to automatically segment all DGM nuclei and use relevant features for a better differentiation between PD and healthy controls (HC). In this study, we proposed a DL‐based pipeline for automatic PD diagnosis based on QSM and T1‐weighted (T1W) images. This consists of (1) a convolutional neural network model integrated with multiple attention mechanisms which simultaneously segments caudate nucleus, globus pallidus, putamen, red nucleus, and substantia nigra from QSM and T1W images, and (2) an SE‐ResNeXt50 model with an anatomical attention mechanism, which uses QSM data and the segmented nuclei to distinguish PD from HC. The mean dice values for segmentation of the five DGM nuclei are all >0.83 in the internal testing cohort, suggesting that the model could segment brain nuclei accurately. The proposed PD diagnosis model achieved area under the the receiver operating characteristic curve (AUCs) of 0.901 and 0.845 on independent internal and external testing cohorts, respectively. Gradient‐weighted class activation mapping (Grad‐CAM) heatmaps were used to identify contributing nuclei for PD diagnosis on patient level. In conclusion, the proposed approach can potentially be used as an automatic, explainable pipeline for PD diagnosis in a clinical setting.

Parkinson's disease and Parkinsonism syndromes: Evaluating iron deposition in the putamen using magnetic susceptibility MRI techniques - A systematic review and literature analysis

“…These methods include T2*-weighted (T2*-w) imaging, susceptibility-weighted imaging (SWI), quantitative susceptibility mapping (QSM), R2* mapping, and phase imaging [ [13] , [14] , [15] ]. These techniques are sensitive to iron accumulation in the brain and can be used to monitor the progression of diseases with neurodegeneration [ 16 ] such as multiple sclerosis (MS) [ 17 ], Parkinson's disease (PD) [ 18 , 19 ], Alzheimer's disease (AD) [ [20] , [21] , [22] ], Huntington's disease (HD) [ 23 ], amyotrophic lateral sclerosis [ 24 ], and Wilson's disease [ 25 ].…”

A more objective PD diagnostic model: integrating texture feature markers of cerebellar gray matter and white matter through machine learning

“…Given the lack of specific clinical presentations in the early stages of PD, and because the structural changes induced by PD are almost imperceptible to the naked eye on magnetic resonance imaging (MRI), developing an objective and accurate diagnostic method has become a focal point of research. Prior research had centered on the basal ganglia and cerebral cortex, but exploration of the cerebellum in PD patients has recently gained researchers' attention (Ko et al, 2017 ; Solana-Lavalle and Rosas-Romero, 2021 ; Pang et al, 2022 ; Wang et al, 2023 ). The cerebellum, as a brain region associated with motor functions, may reveal microstructural alterations related to PD through changes in its texture features.…”

Quantitative susceptibility mapping based basal ganglia segmentation via AGSeg: leveraging active gradient guiding mechanism in deep learning

“…Guan et al proposed a 3-D network to segment sub-cortical nuclei which adopts spatial and channel attention modules in both encoder and decoder stages to focus the network on target regions ( 25 ). Wang et al trained a 3D network with attention gates to segment basal ganglia and employed them for automatic PD detection ( 26 ). With the targeted adjustments and improvements of deep learning techniques on DGM segmentation tasks, the localization and segmentation of basal ganglia have been gradually developed.…”