Application of Functional Magnetic Resonance Imaging in the Diagnosis of Parkinson’s Disease: A Histogram Analysis

Abstract

This study aimed to investigate the value of amplitude of low-frequency fluctuation (ALFF)-based histogram analysis in the diagnosis of Parkinson’s disease (PD) and to investigate the regions of the most important discriminative features and their contribution to classification discrimination. Patients with PD (n = 59) and healthy controls (HCs; n = 41) were identified and divided into a primary set (80 cases, including 48 patients with PD and 32 HCs) and a validation set (20 cases, including 11 patients with PD and nine HCs). The Automated Anatomical Labeling (AAL) 116 atlas was used to extract the histogram features of the regions of interest in the brain. Machine learning methods were used in the primary set for data dimensionality reduction, feature selection, model construction, and model performance evaluation. The model performance was further validated in the validation set. After feature data dimension reduction and feature selection, 23 of a total of 1,276 features were entered in the model. The brain regions of the selected features included the frontal, temporal, parietal, occipital, and limbic lobes, as well as the cerebellum and the thalamus. In the primary set, the area under the curve (AUC) of the model was 0.974, the sensitivity was 93.8%, the specificity was 90.6%, and the accuracy was 93.8%. In the validation set, the AUC, sensitivity, specificity, and accuracy were 0.980, 90.9%, 88.9%, and 90.0%, respectively. ALFF-based histogram analysis can be used to classify patients with PD and HCs and to effectively identify abnormal brain function regions in PD patients.

Effects of Exercise on Parkinson’s Disease: A Meta-Analysis of Brain Imaging Studies

“…It is well known that the cerebellum affects motor and cognitive functions through the cerebellar-thalamic-cortical circuit ( Pierce and Péron, 2020 ). Studies have shown that multiple areas of the cerebellum in patients with PD are atrophied, the subthalamic nucleus has lost its ability to regulate connections in the cerebellum, and there are extensive cerebellar-cortical network abnormalities ( Shi et al, 2021 ). In patients with PD, the volume of cerebellar gray matter decreases, the connections within the cerebellum and between the cerebellum and the sensory-motor network increase, the connections between the cerebellum and the caudate nucleus, thalamus, and amygdala increase, and the connections between the auxiliary motor area and the cingulate gyrus decrease ( Tuovinen et al, 2018 ).…”

Machine Learning for Detecting Parkinson’s Disease by Resting-State Functional Magnetic Resonance Imaging: A Multicenter Radiomics Analysis

“…All subjects underwent structural and functional MRI scanning on a 3-T Siemens Verio scanner. Data acquisition parameters can be found in previous studies ( Hu et al, 2015 ; Shi et al, 2021b ). The structural images were acquired with high-resolution three-dimensional T1-weighted sequences [slices = 128, repetition time (TR)/echo time (TE) = 2,530/3.43 ms, field of view (FOV) = 256 × 256 mm, slice thickness/gap = 1.33/0.5 mm, matrix = 256 × 192, voxel size = 1 × 1.33 × 1.83 mm 3 , and flip angle (FA) = 7].…”

“…It can detect the amplitude of spontaneous, low-frequency oscillations of blood oxygen level-dependent signals to reflect the regularity and physiological state of neuron autonomous activity in different brain regions ( Qian et al, 2020 ). This approach provides a reliable and sensitive measurement to characterize the spontaneous neural activity and has been widely used in PD ( Cao et al, 2020 ; Tian et al, 2020 ; Pang et al, 2021 ; Shi et al, 2021b ).…”

“…Subsequently, the machine learning methods are performed for data mining. Recently, rs-fMRI-based radiomics has been applied to explore neurological disease biomarkers for disease diagnosis and underlying mechanisms ( Sun et al, 2018 ; Mo et al, 2019 ; Wang Y. et al, 2020 ; Zhao et al, 2020 ), including PD ( Cao et al, 2020 ; Shi et al, 2021b ). However, the sample sizes of the above studies are limited and come from a single center, and the extracted features are the intensity histogram-based features.…”

Structural and Functional Asymmetry in Precentral and Postcentral Gyrus in Patients With Unilateral Chronic Shoulder Pain

“…For the functional analyses, we selected left precentral, right precentral, left postcentral, and right postcentral from the Automated Anatomical Labeling (AAL) atlas ( 29) as the seeds because AAL is a commonly used atlas in functional space (30)(31)(32)(33)(34). We performed Pearson's correlation between each seed region and the whole brain voxel.…”