Morphological feature visualization of Alzheimer's disease via Multidirectional Perception GAN

TL;DR

This paper introduces MP-GAN, a novel generative model that visualizes morphological features of Alzheimer's disease in MR images, aiding early diagnosis by highlighting subtle lesions across different disease stages.

Contribution

The paper proposes a multidirectional perception mechanism within a GAN to effectively visualize AD-related morphological features and lesions in MR images, outperforming existing methods.

Findings

MP-GAN achieves superior visualization performance on ADNI dataset.

The visualized lesions align well with clinical observations.

The model effectively delineates subtle brain lesions across AD stages.

Abstract

The diagnosis of early stages of Alzheimer's disease (AD) is essential for timely treatment to slow further deterioration. Visualizing the morphological features for the early stages of AD is of great clinical value. In this work, a novel Multidirectional Perception Generative Adversarial Network (MP-GAN) is proposed to visualize the morphological features indicating the severity of AD for patients of different stages. Specifically, by introducing a novel multidirectional mapping mechanism into the model, the proposed MP-GAN can capture the salient global features efficiently. Thus, by utilizing the class-discriminative map from the generator, the proposed model can clearly delineate the subtle lesions via MR image transformations between the source domain and the pre-defined target domain. Besides, by integrating the adversarial loss, classification loss, cycle consistency loss and \emph{L}1 penalty, a single generator in MP-GAN can learn the class-discriminative maps for multiple-classes. Extensive experimental results on Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset demonstrate that MP-GAN achieves superior performance compared with the existing methods. The lesions visualized by MP-GAN are also consistent with what clinicians observe.