20 September 2021 in IEEE Journal of Biomedical and Health Informatics
With the development of deep learning and medical imaging technology, many researchers use convolutional neural network(CNN) to obtain deep-level features of medical image in order to better classify Alzheimer's disease (AD) and predict clinical scores. The principal component analysis network (PCANet) is a lightweight deep-learning network that mainly uses principal component analysis (PCA) to generate multilevel filter banks for the centralized learning of samples and then performs binarization and generates blockwise histograms to obtain image features. However, the dimensions of the extracted PCANet features reaching tens of thousands or even hundreds of thousands, and the formation of the multilevel filter banks is sample data dependent, reducing the flexibility of PCANet. In order to solve these problems, in this paper, we propose a data-independent network based on the idea of PCANet, called the nonnegative matrix factorization tensor decomposition network (NMF-TDNet). Specifically, we use nonnegative matrix factorization (NMF) instead of PCA to create multilevel filter banks for sample learning, then uses the learning results to build a higher-order tensor and perform tensor decomposition (TD) to achieve data dimensionality reduction, producing the final image features. Finally, our method use these features as the input of the support vector machine (SVM) for AD classification diagnosis and clinical score prediction. The performance of our method is extensively evaluated on the ADNI-1, ADNI-2 and OASIS datasets. The experimental results show that NMF-TDNet can achieve data dimensionality reduction and the NMF-TDNet features as input achieved superior performance than using PCANet features as input.
3 March 2023 in Journal of Biomedical Informatics
8 August 2022 in IET Image Processing
The early stage of Alzheimer's disease (AD) is called mild cognitive impairment (MCI). According to the final progression of the disease, it can be divided into progressive MCI (pMCI) and stable MCI (sMCI). Clinical treatment shows that early treatment of MCI stage can effectively delay the progression of the disease and even complete recovery. Therefore, accurate diagnosis of AD and its early stage play an important guiding role in the treatment and delay of AD progression. Previous studies have shown that the data of different modalities of AD can reflect different pathological changes. Therefore, the accuracy of combining multi‐modality data to classify AD is better than that of using single‐modality to classify AD. Based on this, an AD diagnosis method is proposed based on 3D discrete wavelet transform (3D‐DWT) and 3D moment invariants (3D‐MIs) features from multi‐modalities images. First, automatic anatomical landmark (AAL) atlas is used to identify the brain regions of interest (ROIs) from magnetic resonance image (MRI) and positron emission tomography (PET). Next, for each ROI, the 3D‐DWT and 3D‐MIs extract methods are used to extract features. Finally, a deep neural network with stacked autoencoders (SAE) is trained to detect AD. The experimental results show that, compared with the state‐of‐the‐art AD/MCI classification algorithms based on multi‐modality features, this method can significantly improve the classification performance of pMCI and sMCI classification tasks, which has an important guiding role in the early diagnosis of AD.
12 April 2025 in Expert Systems with Applications