Bilinear pooling and metric learning network for early Alzheimer's disease identification with FDG-PET images

TL;DR

This paper introduces BMNet, a novel neural network that leverages bilinear pooling and metric learning to improve early Alzheimer's disease classification using FDG-PET images, addressing challenges with hard samples and inter-region features.

Contribution

The study proposes a new bilinear pooling and metric learning network (BMNet) that enhances feature extraction and classification accuracy for early Alzheimer's detection from FDG-PET images.

Findings

Improved classification metrics with bilinear pooling and metric loss modules.

Enhanced specificity and NPV in EMCI vs LMCI classification.

Validated effectiveness on 998 FDG-PET images from ADNI.

Abstract

FDG-PET reveals altered brain metabolism in individuals with mild cognitive impairment (MCI) and Alzheimer's disease (AD). Some biomarkers derived from FDG-PET by computer-aided-diagnosis (CAD) technologies have been proved that they can accurately diagnosis normal control (NC), MCI, and AD. However, the studies of identification of early MCI (EMCI) and late MCI (LMCI) with FDG-PET images are still insufficient. Compared with studies based on fMRI and DTI images, the researches of the inter-region representation features in FDG-PET images are insufficient. Moreover, considering the variability in different individuals, some hard samples which are very similar with both two classes limit the classification performance. To tackle these problems, in this paper, we propose a novel bilinear pooling and metric learning network (BMNet), which can extract the inter-region representation features and distinguish hard samples by constructing embedding space. To validate the proposed method, we collect 998 FDG-PET images from ADNI. Following the common preprocessing steps, 90 features are extracted from each FDG-PET image according to the automatic anatomical landmark (AAL) template and then sent into the proposed network. Extensive 5-fold cross-validation experiments are performed for multiple two-class classifications. Experiments show that most metrics are improved after adding the bilinear pooling module and metric losses to the Baseline model respectively. Specifically, in the classification task between EMCI and LMCI, the specificity improves 6.38% after adding the triple metric loss, and the negative predictive value (NPV) improves 3.45% after using the bilinear pooling module.