Cited by An adaptive weighted attention-enhanced deep convolutional neural network for classification of MRI images of Parkinson's disease

Brain connectivity for subtypes of parkinson’s disease using structural MRI DOI

Tanmayee Samantaray, Jitender Saini, Pramod Kumar Pal

et al.

Biomedical Physics & Engineering Express, Journal Year: 2024, Volume and Issue: 10(2), P. 025012 - 025012

Published: Jan. 15, 2024

Objective. Delineating Parkinson's disease (PD) into distinct subtypes is a major challenge. Most studies use clinical symptoms to label PD while our work uses an imaging-based data-mining approach subtype PD. Our study comprises two objectives - firstly, subtyping patients based on grey matter information from structural magnetic resonance imaging scans of human brains; secondly, comparative brain connectivity analysis derived the former step.Approach. Source-based-morphometry decomposition was performed 131 and 78 healthy controls PPMI dataset, derive at components (regions) with significance in high effect size. The loading coefficients significant were thresholded for arriving subtypes. Further, regional maps subtype-specific subjects separately parcellated employed construction association matrices using Pearson correlation. These binarized sparsity threshold leveraged network metrics.Main results. Two (namely A B) detected employing loadings satisfying selection criteria, third (AB) detected, common these components. Subtype highly weighted inferior, middle superior frontal gyri B temporal gyri. Network metrics analyses through permutation test revealed inter-subtype differences (p < 0.05) clustering coefficient, local efficiency, participation coefficient betweenness centrality. Moreover, hubs obtained centrality mean degree.Significance. MRI-based data-driven show lobes playing key role Graph theory-driven could untangle connections showing differential architecture. Replication initial results other datasets may be explored future. Clinical Relevance- Investigating provide treatment.

Language: Английский

Citations

Automated assessment of the substantia nigra on susceptibility map-weighted imaging using deep convolutional neural networks for diagnosis of Idiopathic Parkinson's disease DOI

Dong Hoon Shin, Hwan Heo, Soohwa Song

et al.

Parkinsonism & Related Disorders, Journal Year: 2021, Volume and Issue: 85, P. 84 - 90

Published: March 18, 2021

Language: Английский

Citations

Detecting Parkinson's Disease with Image Classification DOI

S. Kanagaraj,

M. Hema,

M. Nageswara Guptha

et al.

2022 IEEE 3rd Global Conference for Advancement in Technology (GCAT), Journal Year: 2022, Volume and Issue: unknown, P. 1 - 5

Published: Oct. 7, 2022

The non-curable neurological disorder that affects the motor system is known as Parkinson disease. When disease detected earlier, then it can diagnose, and we get a quick relief but not permanent. neurons segregate chemical called dopamine. That helps for transmitting signs to other in brain. dopamine flow starts fall, PD occurs. This makes patients to, resting tremors, bradykinesia rigidity problems. Here machine-learning dramatizations position patterns tag biomedical sciences. mainly attack so be analysed by Magnetic Resonance Imaging (MRI) scan, one detect predict In this paper, with MRI scan Parkinson's using CNN, VGG-16 model ResNET-50. ResNet-50 are compared find best based on accuracy.

Language: Английский

Citations

The performance of various machine learning methods for Parkinson’s disease recognition: a systematic review DOI

Nader Salari, Mohsen Kazeminia, Hesam Sagha

et al.

Current Psychology, Journal Year: 2022, Volume and Issue: 42(20), P. 16637 - 16660

Published: Feb. 27, 2022

Language: Английский

Citations

An adaptive weighted attention-enhanced deep convolutional neural network for classification of MRI images of Parkinson's disease DOI

Xinchun Cui,

Ningning Chen,

Chao Zhao

et al.

Journal of Neuroscience Methods, Journal Year: 2023, Volume and Issue: 394, P. 109884 - 109884

Published: May 17, 2023

Language: Английский

Citations