An Explainable Deep Learning-Based Method For Schizophrenia Diagnosis Using Generative Data-Augmentation
This work addresses the challenge of accurate and trustworthy diagnosis for schizophrenia patients, though it is incremental as it builds on existing deep learning and data augmentation methods.
The study tackled the problem of automatic schizophrenia diagnosis from EEG recordings by using generative data augmentation to improve accuracy, achieving a 3.0% increase to 99.0% accuracy with a VAE-based approach and addressing interpretability with LIME.
In this study, we leverage a deep learning-based method for the automatic diagnosis of schizophrenia using EEG brain recordings. This approach utilizes generative data augmentation, a powerful technique that enhances the accuracy of the diagnosis. To enable the utilization of time-frequency features, spectrograms were extracted from the raw signals. After exploring several neural network architectural setups, a proper convolutional neural network (CNN) was used for the initial diagnosis. Subsequently, using Wasserstein GAN with Gradient Penalty (WGAN-GP) and Variational Autoencoder (VAE), two different synthetic datasets were generated in order to augment the initial dataset and address the over-fitting issue. The augmented dataset using VAE achieved a 3.0\% improvement in accuracy reaching up to 99.0\% and yielded a lower loss value as well as a faster convergence. Finally, we addressed the lack of trust in black-box models using the Local Interpretable Model-agnostic Explanations (LIME) algorithm to determine the most important superpixels (frequencies) in the diagnosis process.