What question did this study set out to answer?

The aim is to develop an AI-based hybrid model for accurate classification of Alzheimer's disease using medical imaging.

February 5, 2026Open Access

A Hybrid of ResNext101₃2x8d and Swin Transformer Networks with XAI for Alzheimer’s Disease Detection

Key Points

The aim is to develop an AI-based hybrid model for accurate classification of Alzheimer's disease using medical imaging.
Utilized a hybrid model consisting of ResNext101_32x8d and Swin Transformer networks.
Trained on 5120 MRI images with validation on 768 images and testing on 512 images.
Employed Grad-CAM and LIME for interpreting model predictions.
Implemented hyperparameter optimization and data augmentation techniques.
Achieved a testing accuracy of 98.83% with a loss rate of 0.1019.
Obtained precision, F1-score, and recall of 99.39%, 99.15%, and 98.91%, respectively.
Area under the ROC curve was 1.00, indicating perfect classification.

Abstract

Medical images obtained from advanced imaging devices play a crucial role in supporting disease diagnosis and detection. Nevertheless, acquiring such images is often costly and storage-intensive, and it is time-consuming to diagnose individuals. The use of artificial intelligence (AI) -based automated diagnostic systems provides potential solutions to address the limitations of cost and diagnostic time. In particular, deep learning and explainable AI (XAI) techniques provide a reliable and robust approach to classifying medical images. This paper presents a hybrid model comprising two networks, ResNext101₃2x8d and Swin Transformer to differentiate four categories of Alzheimer’s disease: no dementia, very mild dementia, mild dementia, and moderate dementia. The combination of the two networks is applied to imbalanced data, trained on 5120 MRI images, validated on 768 images, and tested on 512 other images. Grad-CAM and LIME techniques with a saliency map are employed to interpret the predictions of the model, providing transparent and clinically interpretable decision support. The proposed combination is realized through a TensorFlow framework, incorporating hyperparameter optimization and various data augmentation methods. The performance evaluation of the proposed model is conducted through several metrics, including the error matrix, precision recall (PR), receiver operating characteristic (ROC), accuracy, and loss curves. Experimental results reveal that the hybrid of ResNext101₃2x8d and Swin Transformer achieved a testing accuracy of 98. 83% with a corresponding loss rate of 0. 1019. Furthermore, for the combination “ResNext101₃2x8d + Swin Transformer”, the precision, F1-score, and recall were 99. 39%, 99. 15%, and 98. 91%, respectively, while the area under the ROC curve (AUC) was 1. 00, “100%”. The combination of proposed networks with XAI techniques establishes a unique contribution to advance medical AI systems and assist radiologists during Alzheimer’s disease screening of patients.

Read Full Paperexternally

Perguntar à IA

Bookmark

View Full Paper