Distance Transform Guided Mixup for Alzheimer's Detection
This incremental method aims to improve early Alzheimer's diagnosis for medical applications by enhancing data augmentation in single-domain generalization.
The study tackled Alzheimer's detection by extending mixup with distance transforms on MRI scans to address class imbalance and limited diversity, resulting in improved generalization performance across ADNI and AIBL datasets.
Alzheimer's detection efforts aim to develop accurate models for early disease diagnosis. Significant advances have been achieved with convolutional neural networks and vision transformer based approaches. However, medical datasets suffer heavily from class imbalance, variations in imaging protocols, and limited dataset diversity, which hinder model generalization. To overcome these challenges, this study focuses on single-domain generalization by extending the well-known mixup method. The key idea is to compute the distance transform of MRI scans, separate them spatially into multiple layers and then combine layers stemming from distinct samples to produce augmented images. The proposed approach generates diverse data while preserving the brain's structure. Experimental results show generalization performance improvement across both ADNI and AIBL datasets.