Enhancing interpretability of AI with radiomics-based deep neural network: proof of concept in the classification of Parkinsonian syndromes with 18F-FDG PET imaging
Open Access
- 11 September 2025
- journal article
- research article
- Published by Springer Nature in European Journal of Nuclear Medicine and Molecular Imaging
- Vol. 53 (3) , 1962-1979
Abstract
Objective: Interpretability and reproducibility remain major challenges in applying deep neural network (DNN) to neuroimaging-based diagnosis. This study proposes a radiomics-guided dual-channel deep neural network (RDDNN) to improve feature transparency and enhance clinical understanding in the classification of Parkinsonian syndromes. Methods: In this bi-centric study, we analysed two independent cohorts comprising 1,275 patients with idiopathic Parkinson’s disease (IPD), multiple system atrophy (MSA), and progressive supranuclear palsy (PSP), alongside 223 healthy controls from Huashan Hospital and 90 patients with IPD, MSA, and PSP (34IPD, 17MSA, 39PSP) from the University Hospital Munich. It is a re-analysis of well-studied Chinese and German cohorts of 18 F-fluorodeoxyglucose Positron emission tomography (FDG-PET) imaging of parkinsonian patients and the FDG scans were of 10-min static acquisition at 60 min post FDG injection and normalized against whole brain activity. The RDDNN model combines local features extracted via dilated convolutional networks and global features derived from Transformer-based self-attention networks. Model performance was evaluated using classification metrics and compared to radiomics and DNN approaches. The model’s outputs were also compared with nuclear medicine specialists’ visual assessments to assess interpretability and time efficiency. Furthermore, SHapley Additive Explanations (SHAP), Layer-wise Class Activation Mapping (Layer-CAM), and Rollout Attention Map (RAM) were employed to evaluate which features played the most critical roles in the model’s final classification decisions after supervised training, and to examine how both networks spatially corresponded to known brain connectivity regions. Results: In the internal blind-test cohort, the RDDNN achieved high accuracy (AUC = 0.99, accuracy = 0.98). SHAP and correlation analyses jointly indicated complementary information across channels, some of which were clinically interpretable. In the external cohort, the model maintained robust performance (AUC = 0.94, accuracy = 0.81), with consistent feature patterns across populations. The model significantly reduced evaluation time compared to nuclear medicine specialists’ readings ( p < 0.001), and the heatmaps showed disease-specific activation in anatomically relevant regions for IPD, MSA, and PSP. Conclusion: The RDDNN framework provides a clinically interpretable and reproducible DNN solution for classifying Parkinsonian disorders. By integrating radiomics and attention-based modeling, it enhances lesion localization, supports clinical decision-making, and offers performance comparable to human specialists—while substantially improving diagnostic efficiency.Keywords
Funding Information
- University of Bern
This publication has 62 references indexed in Scilit:
- Visual reading for [18F]Florzolotau Tau PET scans in progressive supranuclear palsyEuropean Journal of Nuclear Medicine and Molecular Imaging, 2024
- Dopamine Pathway and Parkinson's Risk Variants Are Associated with Levodopa‐Induced DyskinesiaMovement Disorders, 2024
- Using machine learning to improve the diagnostic accuracy of the modified Duke/ESC 2015 criteria in patients with suspected prosthetic valve endocarditis – a proof of concept studyEuropean Journal of Nuclear Medicine and Molecular Imaging, 2024
- International consensus on clinical use of presynaptic dopaminergic positron emission tomography imaging in parkinsonismEuropean Journal of Nuclear Medicine and Molecular Imaging, 2023
- Decoding the dopamine transporter imaging for the differential diagnosis of parkinsonism using deep learningEuropean Journal of Nuclear Medicine and Molecular Imaging, 2022
- Using radiomics-based modelling to predict individual progression from mild cognitive impairment to Alzheimer’s diseaseEuropean Journal of Nuclear Medicine and Molecular Imaging, 2022
- Multivariate radiomics models based on 18F-FDG hybrid PET/MRI for distinguishing between Parkinson’s disease and multiple system atrophyEuropean Journal of Nuclear Medicine and Molecular Imaging, 2021
- Clinical diagnosis of progressive supranuclear palsy: The movement disorder society criteriaMovement Disorders, 2017
- MDS clinical diagnostic criteria for Parkinson's diseaseMovement Disorders, 2015
- EANM procedure guidelines for PET brain imaging using [18F]FDG, version 2European Journal of Nuclear Medicine and Molecular Imaging, 2009