Tensorizing GAN with High-Order Pooling for Alzheimer's Disease Assessment

TL;DR

This paper introduces THS-GAN, a novel deep learning model that leverages tensorization, high-order pooling, and semi-supervised learning to improve Alzheimer's Disease diagnosis from MRI images, demonstrating superior performance on ADNI data.

Contribution

The paper presents the first tensor-train, high-order pooling, and semi-supervised GAN model specifically designed for MRI-based AD classification, integrating structural brain information.

Findings

THS-GAN outperforms existing methods on ADNI dataset

Tensor-train and high-order pooling improve classification accuracy

Generated samples are plausible for semi-supervised learning

Abstract

It is of great significance to apply deep learning for the early diagnosis of Alzheimer's Disease (AD). In this work, a novel tensorizing GAN with high-order pooling is proposed to assess Mild Cognitive Impairment (MCI) and AD. By tensorizing a three-player cooperative game based framework, the proposed model can benefit from the structural information of the brain. By incorporating the high-order pooling scheme into the classifier, the proposed model can make full use of the second-order statistics of the holistic Magnetic Resonance Imaging (MRI) images. To the best of our knowledge, the proposed Tensor-train, High-pooling and Semi-supervised learning based GAN (THS-GAN) is the first work to deal with classification on MRI images for AD diagnosis. Extensive experimental results on Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset are reported to demonstrate that the proposed THS-GAN achieves superior performance compared with existing methods, and to show that both tensor-train and high-order pooling can enhance classification performance. The visualization of generated samples also shows that the proposed model can generate plausible samples for semi-supervised learning purpose.