Deep Learning-Based Feature Representation for AD/MCI Classification

By Heung-Il Suk, Dinggang Shen. 2013

457 citations recorded by the source corpus.

In recent years, there has been a great interest in computer-aided diagnosis of Alzheimer’s Disease (AD) and its prodromal stage, Mild Cognitive Impairment (MCI). Unlike the previous methods that consider simple low-level features such as gray matter tissue volumes from MRI, mean signal intensities from PET, in this paper, we propose a deep learning-based feature representation with a stacked auto-encoder. We believe that there exist latent complicated patterns, e.g., non-linear relations, inherent in the low-level features. Combining latent information with the original low-level features helps build a robust model for AD/MCI classification with high diagnostic accuracy. Using the ADNI dataset, we conducted experiments showing that the proposed method is 95.9%, 85.0%, and 75.8% accurate for AD, MCI, and MCI-converter diagnosis, respectively.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis (2017, background): “In fact, many studies in this paper have explicitly mentioned the lack of interpretability as a main limitation [14], [17], [21], [49], [62].”
A Deep Learning Approach for Automated Diagnosis and Multi-Class Classification of Alzheimer’s Disease Stages Using Resting-State fMRI and Residual Neural Networks (2019, methodology): “Neuroimaging data is acquired from Alzheimer ’ s disease Neuroimaging Initiative (ADNI) database [40] that has been used in various studies [13, 23] for AD classification.”
Alzheimer's disease diagnostics by adaptation of 3D convolutional network (2016, methodology): “[11] used a stacked autoencoder to separately extract features from MRI, PET, and cerebrospinal fluid (CSF) images; compared combinations of these features with due account of their clinical mini-mental state examination (MMSE) and AD assessment scale-cognitive (ADAScog) scores, and classified the A”
A deep learning framework for supporting the classification of breast lesions in ultrasound images (2017, background): “diagnosis for Alzheimers disease[46, 47, 48, 49] and mild cognitive impairment[47], 78”
Deep Learning in Medical Imaging: General Overview (2017, background): “Early reports of deep learning based CAD systems for breast cancer (86), lung cancer (87, 88) and Alzheimer’s disease (AD) (89-91) show promising results regarding their performance in detecting and staging the diseases.”
An Automatic Learning-Based Framework for Robust Nucleus Segmentation (2016, methodology): “Recently, CNN has been proven to be effective for object detection, segmentation, and classification in nature and medical image analysis [52]–[56].”
Using deep learning to investigate the neuroimaging correlates of psychiatric and neurological disorders: Methods and applications (2017, unknown): “Indeed, the performance of the classifiers has been consistently high, with several studies reporting accuracies above 95% for binary classifications between patients and controls (Deshpande et al., 2015; Hosseini-Asl et al., 2016; Payan and Montana, 2015; Sarraf and Tofighi, 2016; Suk and Shen, 201”
Deformable MR Prostate Segmentation via Deep Feature Learning and Sparse Patch Matching (2015, methodology): “To make the learned feature representation discriminative [33], [34], the supervised fine-tuning is often adopted by stacking another classification output layer on the top of the encoding part of the SSAE, as shown in red dashed box of Fig.”
Deep learning in bioinformatics (2016, unknown): “[124] studied Alzheimer’s disease classification using cerebrospinal fluid and brain images in the forms of MRI and PET scan and Soleymani et al.”
Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis (2014, unknown): “We argue that this joint feature representation discriminates our method from the previous multimodal methods (Hinrichs et al., 2011; Suk and Shen, 2013; Zhang et al., 2011), which first extracted features from each modality independently, and then combined them through kernel machines.”
Multimodal Neuroimaging Feature Learning With Multimodal Stacked Deep Polynomial Networks for Diagnosis of Alzheimer's Disease (2018, methodology): “SAE-MKL [39] ∗ 51 AD, 43 MCI-C, 56 MCI-NC, 52 NC MRI + PET + CSF The combination of SAE-based feature learning and MKL classification (SAE-MKL) algorithm DW-S2MTL [40] ∗ 51 AD, 43 MCI-C, 56 MCI-NC, 52 NC MRI + PET The deep sparse multi-task learning based feature selection (DW-S2MTL) algorithm”
Applications of Deep Learning and Reinforcement Learning to Biological Data (2017, methodology): “Several models were applied to detect Alzheimer’s Disease (AD) and Mild Cognitive Impairment (MCI) from MRI and PET scans including DA [117,118], DBM [120], RBM [121], and multimodal stacked deep polynomial network (MM-SDPN) [124].”
Brain MRI analysis for Alzheimer’s disease diagnosis using an ensemble system of deep convolutional neural networks (2018, methodology): “Suk et al. [23, 42, 78, 79] developed an autoencoder network-based model for AD diagnosis and used several complex SVM kernels for classification.”