Predicting Alzheimer’s Disease Using LSTM

Hong, Xin; Lin, Rong; Yang, Chenhui; Zeng, Nianyin; Cai, Chunting; Gou, Jianping; Yang, Jianping

doi:10.1109/access.2019.2919385

Cited by 104 publications

(57 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They obtained an accuracy rate of 95.9% over these MCI stages. Hong et al [37] predicted Alzheimer's disease using long short-term memory (LSTM) because it was able to connect the patient's previous information to the current task. They process the time series data in three layers, such as pre-fully connected, cells, and post-fully connected layers.…”

Section: Deep Learning-based Techniquementioning

confidence: 99%

A Deep Siamese Convolution Neural Network for Multi-Class Classification of Alzheimer Disease

et al. 2020

View full text Add to dashboard Cite

Alzheimer’s disease (AD) may cause damage to the memory cells permanently, which results in the form of dementia. The diagnosis of Alzheimer’s disease at an early stage is a problematic task for researchers. For this, machine learning and deep convolutional neural network (CNN) based approaches are readily available to solve various problems related to brain image data analysis. In clinical research, magnetic resonance imaging (MRI) is used to diagnose AD. For accurate classification of dementia stages, we need highly discriminative features obtained from MRI images. Recently advanced deep CNN-based models successfully proved their accuracy. However, due to a smaller number of image samples available in the datasets, there exist problems of over-fitting hindering the performance of deep learning approaches. In this research, we developed a Siamese convolutional neural network (SCNN) model inspired by VGG-16 (also called Oxford Net) to classify dementia stages. In our approach, we extend the insufficient and imbalanced data by using augmentation approaches. Experiments are performed on a publicly available dataset open access series of imaging studies (OASIS), by using the proposed approach, an excellent test accuracy of 99.05% is achieved for the classification of dementia stages. We compared our model with the state-of-the-art models and discovered that the proposed model outperformed the state-of-the-art models in terms of performance, efficiency, and accuracy.

show abstract

Section: Deep Learning-based Techniquementioning

confidence: 99%

A Deep Siamese Convolution Neural Network for Multi-Class Classification of Alzheimer Disease

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Deep learning is a powerful tool for solving numerous complex problems in various disciplines, such as pattern recognition, speech recognition and medical imaging. Various complicated medical imaging problems have already been addressed using deep learning-based algorithms [9], [37]- [41]. Wachinger et al [9] proposed the deep learningbased DeepNAT method to segment the neuroanatomy.…”

Section: A Prior Workmentioning

confidence: 99%

Automatic Localization and Discrete Volume Measurements of Hippocampi From MRI Data Using a Convolutional Neural Network

et al. 2020

View full text Add to dashboard Cite

Automatic hippocampal volume measurement from brain magnetic resonance imaging (MRI) is a crucial task and an important research area, especially in the study of neurodegenerative diseases; hippocampal volume atrophy is known to be connected with Alzheimer's disease. In this research work, we propose a deep learning-based method to automatically measure the discrete hippocampal volume without prior segmentation of the volumetric MRI scans. We constructed a 2-D convolutional neural network (CNN) model that uses 3-channel 2-D patches to predict the number of voxels attributed to the hippocampus; the number of estimated hippocampal voxels is multiplied by the voxel volume to measure the discrete volume of the hippocampus. In addition, we demonstrate a preprocessing scheme to prepare the data using a relatively small number of MRI scans. The average errors in the measured volumes of the proposed approach and the compared atlas-based system were 4.3173 ± 3.5436 (avg. error% ± STD) and 4.1562 ±3.5262 (avg. error % ± STD) for the left and right hippocampi, respectively. The correlation coefficients of the proposed approach with atlas-based volume measurement were statistically significant (p-value < 0.01, R 2 = 0.834 (left hippocampus), and R 2 = 0.848 (right hippocampus) based on 0.05 significance level), which suggests that the proposed approach can be used as a proxy method for the atlas-based system. Furthermore, the proposed approach is computationally efficient and requires less than 2 seconds to calculate the number of voxels for an MRI scan. Moreover, our method outperforms the state-of-the-art deep learning approach, such as 2-D U-Net and SegNet in the context of voxel/volume estimation errors% for the left and right hippocampi.

show abstract

“…A Deep CNN was trained using PET images, to classify AD, MCI and NC states. Hong et al [16] propose an alternative approach utilizing an LSTM model to predict the progress of Alzheimer's Disease. Basaia et al [17] develop a 3D CNN model to classify MRI data.…”

Section: B Deep Network Feature Selection and Deep Network Classificmentioning

confidence: 99%

“…Linear interpolation is applied to the incomplete data at M00 in row R3. Data for a particular subject is interpolated using the same method as Hong et al [16]. (2) Missing data: At specific points, some subjects lack several values of ROIs.…”

Section: B Data Interpolationmentioning

confidence: 99%

See 1 more Smart Citation

ADPM: An Alzheimer’s Disease Prediction Model for Time Series Neuroimage Analysis

et al. 2020

Self Cite

View full text Add to dashboard Cite

Alzheimer's Disease (AD) is a form of dementia which causes memory, thinking, and behavior disorders in humans. Effective early diagnosis and treatment of AD is of fundamental importance as it can reduce disease progression, allow more effective management of symptoms, facilitate timely patient access to advice and support, and lower associated costs of health care. Given that Alzheimer's typically progresses in stages over an extended period of time, we propose that automated analysis of time sequential data may enhance disease prediction. We present a novel time-series Alzheimer's Disease Prediction Model (ADPM) comprising Random Forest (RF) region of interest (ROI) selection and Gated Recurrent Units (GRU) prediction. Experiments show that our methodology achieves higher classification accuracy in comparison to existing algorithms, and can facilitate prediction of early onset AD. Furthermore, testing demonstrates that random forest ROI selection can identify disease-relative brain regions across different image modalities (MRI, PET, DTI). INDEX TERMS Alzheimer's disease prediction, time series, random forest, GRU.

show abstract

Predicting Alzheimer’s Disease Using LSTM

Cited by 104 publications

References 27 publications

A Deep Siamese Convolution Neural Network for Multi-Class Classification of Alzheimer Disease

A Deep Siamese Convolution Neural Network for Multi-Class Classification of Alzheimer Disease

Automatic Localization and Discrete Volume Measurements of Hippocampi From MRI Data Using a Convolutional Neural Network

ADPM: An Alzheimer’s Disease Prediction Model for Time Series Neuroimage Analysis

Contact Info

Product

Resources

About