Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
August 14, 2026BMC Medical ImagingOpen Access

Advancing Parkinson’s detection from MRI: a deep learning comparison of classical and quantum architectures

View Full Paper
Ask AI
Bookmark
Share

Authors

JSJothiraj SelvarajFAFadiyah AlmutairiOAOmar Alhajlah

Discussion

Loading...

Member takes

Overview

Comparative neuroimaging evaluation reveals superior Parkinson's disease classification using quantum neural networks on MRI scans, highlighting potential for automated clinical diagnostic tools.

Key Points

  • Compare classical deep learning architectures (CNNs, Transformers) and quantum neural networks for the automated detection and classification of Parkinson's disease from brain MRI scans.
  • Implemented and evaluated CNN models (including ResNet50), Swin Transformers, and Quantum Neural Networks (QNN) to extract spatial features from brain MRI scans.
  • Assessed model generalizability and stability using an 80:20 data split with K-fold cross-validation.
  • Performed external validation on the independent Parkinson’s Progression Markers Initiative (PPMI) dataset.
  • Quantum Neural Networks achieved the highest classification performance, reaching a training accuracy of 0.9851 and a validation accuracy of 0.9731.
  • Swin Transformer achieved 0.9712 training and 0.9673 validation accuracy, while ResNet50 attained 0.9322 training and 0.9192 validation accuracy.
  • External validation on the PPMI dataset confirmed robust performance trends and generalizability across independent imaging data.

Cite This Study

Selvaraj et al. (2026) studied this question.

synapsesocial.com/papers/6a7ec775b70b84ec8b913e2ahttps://doi.org/10.1186/s12880-026-02639-y
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Quantum-enhanced deep learning for Parkinson’s disease classification2026
  2. 2AUTOMATED DETECTION OF PARKINSON’S DISEASE BASED ON HYBRID CNN AND QUANTUM MACHINE LEARNING TECHNIQUES IN MRI IMAGES2024 · 5 citations
  3. 3Bridging Accuracy and Interpretability: Explainable Deep Learning for Parkinson’s Disease Diagnosis from MRI2026
  4. 4A Comprehensive framework for Parkinson’s disease diagnosis using explainable artificial intelligence empowered machine learning techniques2024 · 39 citations
  5. 5Innovative Deep Learning Approach for Parkinson's Disease Prediction: Leveraging Convolutional Neural Networks for Early Detection2024 · 3 citations