Voxel-based morphometry and minimum redundancy maximum relevance method for classification of Parkinson's disease and controls from T1-weighted MRI

Rana, Bharti; Juneja, Akanksha; Saxena, Mohit; Gudwani, Sunita; Kumaran, Senthil; Agrawal, R. K.; Behari, Madhuri

doi:10.1145/3009977.3009998

Cited by 1 publication

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, the volume of the right lateral ventricle also differed between the two groups. In brief, the expansion of the lateral ventricle likely reflects atrophy of the basal ganglia ( Kocaman et al, 2019 ), which has been reported in several previous ML and group-level researches in patients with PD ( Rana et al, 2015a , 2016 ; Solana-Lavalle and Rosas-Romero, 2021 ; Song et al, 2021 ). As an indirect sign, the enlargement of the lateral ventricle may provide vital reference information for the macroscopic structural changes of the PD brain.…”

Section: Discussionmentioning

confidence: 80%

“…As a part of the striatum, the caudate nucleus is primarily involved in emotion regulation, reward processing, decision-making, and executive functioning ( Owens-Walton et al, 2018 ). Many previous ML studies have found its atrophy in patients with PD ( Long et al, 2012 ; Rana et al, 2015a , 2016 ; Adeli et al, 2016 ; Liu et al, 2018 ; Song et al, 2021 ). The asymmetry of brain structure is related to various aspects of language function, visual spatial tasks, attention, and emotion, and it changes with aging ( Sarica et al, 2018 ).…”

Section: Discussionmentioning

confidence: 94%

“…Similar to our study, some previous studies also found the superiority of employing multiple features in the ML studies. For example, Rana et al (2016) and Cigdem and Demirel (2018) revealed that modeling after fusing GM and WM features achieved higher accuracy than using a single feature, with an improvement of up to about 15 and 30% in accuracy, respectively. By using multiple structural features (GM, WM, CSF, CT, surface area, and the correlation index of CT and surface area), Peng et al (2017) adopted filter- and wrapper-based feature selection method and the support vector machine classifier and obtained the highest accuracy of 85.78%.…”

Section: Discussionmentioning

confidence: 99%

“…The insula (including ACIS, AAIC, and MI) is a hub region of the salience network and is mainly involved with a variety of brain functions including perception, emotion, and cognition ( Huang et al, 2020 ). A number of ML studies have reported abnormalities of the insula in patients with PD ( Babu et al, 2014 ; Rana et al, 2015a , 2016 ; Adeli et al, 2016 ; Peng et al, 2017 ; Park et al, 2020 ). SCEF is a part of the supplementary motor area, which is primarily related to the production of autonomous, complex, and continuous movement ( Jubault et al, 2011 ).…”

Section: Discussionmentioning

confidence: 99%

See 3 more Smart Citations

Machine Learning Models for Diagnosis of Parkinson’s Disease Using Multiple Structural Magnetic Resonance Imaging Features

Yang

Jia

et al. 2022

Front. Aging Neurosci.

View full text Add to dashboard Cite

PurposeThis study aimed to develop machine learning models for the diagnosis of Parkinson’s disease (PD) using multiple structural magnetic resonance imaging (MRI) features and validate their performance.MethodsBrain structural MRI scans of 60 patients with PD and 56 normal controls (NCs) were enrolled as development dataset and 69 patients with PD and 71 NCs from Parkinson’s Progression Markers Initiative (PPMI) dataset as independent test dataset. First, multiple structural MRI features were extracted from cerebellar, subcortical, and cortical regions of the brain. Then, the Pearson’s correlation test and least absolute shrinkage and selection operator (LASSO) regression were used to select the most discriminating features. Finally, using logistic regression (LR) classifier with the 5-fold cross-validation scheme in the development dataset, the cerebellar, subcortical, cortical, and a combined model based on all features were constructed separately. The diagnostic performance and clinical net benefit of each model were evaluated with the receiver operating characteristic (ROC) analysis and the decision curve analysis (DCA) in both datasets.ResultsAfter feature selection, 5 cerebellar (absolute value of left lobule crus II cortical thickness (CT) and right lobule IV volume, relative value of right lobule VIIIA CT and lobule VI/VIIIA gray matter volume), 3 subcortical (asymmetry index of caudate volume, relative value of left caudate volume, and absolute value of right lateral ventricle), and 4 cortical features (local gyrification index of right anterior circular insular sulcus and anterior agranular insula complex, local fractal dimension of right middle insular area, and CT of left supplementary and cingulate eye field) were selected as the most distinguishing features. The area under the curve (AUC) values of the cerebellar, subcortical, cortical, and combined models were 0.679, 0.555, 0.767, and 0.781, respectively, for the development dataset and 0.646, 0.632, 0.690, and 0.756, respectively, for the independent test dataset, respectively. The combined model showed higher performance than the other models (Delong’s test, all p-values < 0.05). All models showed good calibration, and the DCA demonstrated that the combined model has a higher net benefit than other models.ConclusionThe combined model showed favorable diagnostic performance and clinical net benefit and had the potential to be used as a non-invasive method for the diagnosis of PD.

show abstract