analiza aiqbench
The paper proposes a hybrid CNN-transformer model for classifying Alzheimer's, Parkinson's, and healthy brain MRIs, and its most useful result is a warning about generalization. Accuracy falls from 98% on a single Kaggle split to about 59% on ADNI test images when the data sources differ and patients are kept separate. Readers evaluating medical imaging models should weigh the cross-dataset and patient-level results more heavily than the headline single-dataset accuracy.
HybridDualPathNet: Cross-Fusion Attention of EfficientNetV2 and Swin Transformer for Brain MRI Classification of Alzheimer's and Parkinson's Disease
arXiv:2610.17251v1 Announce Type: cross Abstract: Separating Alzheimer's Disease (AD), Parkinson's Disease (PD), and Healthy Controls (HC) using structural MRI remains challenging because disease signatures overlap and model performance can be strongly affected by data partitioning. We present HybridDualPathNet, a hybrid architecture combining EfficientNetV2-S for local features and Swin-Tiny for global context through a Cross-Fusion Attention (CFA) module. We evaluate the model in two experiments. First, on the Kaggle APD-3-Class dataset using an image-level split, the model achieves 98.25% accuracy. Second, on a combined Kaggle and Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset containing 17,859 slices, we use a per-source split with patient-wise separation for ADNI subjects. In this setting, the model achieves 73.37% standard accuracy and a macro AUC of 0.880. Source-stratified evaluation reveals a substantial domain gap, with 91.2% accuracy on Kaggle test images and 59.2% on ADNI test images. Temperature scaling reduces expected calibration error from 0.130 to 0.015, while split-conformal prediction achieves 89.5% coverage. Saliency analyses using Grad-CAM++, Integrated Gradients, and occlusion indicate that model activations concentrate on brain tissue. These results highlight the importance of patient-level separation, cross-dataset evaluation, and uncertainty estimation when assessing MRI classification systems. The findings also show that strong performance on a single dataset does not necessarily translate to reliable generalization across imaging cohorts.
Abstract:Separating Alzheimer's Disease (AD), Parkinson's Disease (PD), and Healthy Controls (HC) using structural MRI remains challenging because disease signatures overlap and model performance can be strongly affected by data partitioning. We present HybridDualPathNet, a hybrid architecture combining EfficientNetV2-S for local features and Swin-Tiny for global context through a Cross-Fusion Attention (CFA) module. We evaluate the model in two experiments. First, on the Kaggle APD-3-Class dataset using an image-level split, the model achieves 98.25% accuracy. Second, on a combined Kaggle and Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset containing 17,859 slices, we use a per-source split with patient-wise separation for ADNI subjects. In this setting, the model achieves 73.37% standard accuracy and a macro AUC of 0.880. Source-stratified evaluation reveals a substantial domain gap, with 91.2% accuracy on Kaggle test images and 59.2% on ADNI test images. Temperature scaling reduces expected calibration error from 0.130 to 0.015, while split-conformal prediction achieves 89.5% coverage. Saliency analyses using Grad-CAM++, Integrated Gradients, and occlusion indicate that model activations concentrate on brain tissue. These results highlight the importance of patient-level separation, cross-dataset evaluation, and uncertainty estimation when assessing MRI classification systems. The findings also show that strong performance on a single dataset does not necessarily translate to reliable generalization across imaging cohorts.
Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Software Engineering (cs.SE)
arXiv:2610.17251 [cs.CV]
(or arXiv:2610.17251v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2610.17251 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 309 cuvinte
Subiecte conexe
Exploring Diffusion Transformers for Cross-Modal Augmentation in Multimodal Brain State Decoding
arXiv · 12 sept. 2026
DiffAttn: Diffusion-Based Drivers' Visual Attention Prediction with LLM-Enhanced Semantic Reasoning
arXiv · 17 iun. 2026
Multi-Context Fusion Transformer for Pedestrian Crossing Intention Prediction in Urban Environments
arXiv · 25 aug. 2026
Beyond Parallel Tracking: Interactive Multi-Feature Fusion Drives Semantic Reconstruction from Non-invasive Brain Recordings
arXiv · 21 iul. 2026