3D Convolutional Neural Network and Stacked Bidirectional Recurrent Neural Network for Alzheimer’s Disease Diagnosis

Feng, Chiyu; Elazab, Ahmed; Yang, Peng; Wang, Tianfu; Lei, Baiying; Xiao, Xiaohua

doi:10.1007/978-3-030-00320-3_17

Cited by 18 publications

(8 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, with this layer, we may extract common closely connected brain structure information from all the SBi-LSTM cells, which may represent constant ''trait'' information of each subject, instead of the part of the brain structure information. Finally, it is noteworthy that the experimental results of our method are consistent with the related previous studies [36].…”

Section: Discussion and Limitationssupporting

confidence: 91%

“…Comparing with the input data that is cut into several blocks to train several relatively independent 3D-CNN modules and then fusion, our method of down-sampling can greatly reduce the demand for data as we have less training parameters. Compared with our previous work [36], LSTM can effectively alleviate the gradient vanishing problem by controlling information flow with several gates. In addition, if we use the FC layer, we can further extract and sort out the output of SBi-LSTM.…”

Section: F Comparision With Other Deep Learning Modelmentioning

confidence: 99%

“…Therefore, we propose to use the stacked Bi-LSTM (SBi-LSTM) instead of the traditional Bi-LSTM [36] in this paper. In addition, each output of LSTM is related to historical input, but the current input has a greater impact.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep Learning Framework for Alzheimer’s Disease Diagnosis via 3D-CNN and FSBi-LSTM

Feng¹,

Elazab

Yang³

et al. 2019

IEEE Access

Self Cite

167

View full text Add to dashboard Cite

Alzheimer's disease (AD) is an irreversible progressive neurodegenerative disorder. Mild cognitive impairment (MCI) is the prodromal state of AD, which is further classified into a progressive state (i.e., pMCI) and a stable state (i.e., sMCI). With the development of deep learning, the convolutional neural networks (CNNs) have made great progress in image recognition using magnetic resonance imaging (MRI) and positron emission tomography (PET) for AD diagnosis. However, due to the limited availability of these imaging data, it is still challenging to effectively use CNNs for AD diagnosis. Toward this end, we design a novel deep learning framework. Specifically, the virtues of 3D-CNN and fully stacked bidirectional long short-term memory (FSBi-LSTM) are exploited in our framework. First, we design a 3D-CNN architecture to derive deep feature representation from both MRI and PET. Then, we apply FSBi-LSTM on the hidden spatial information from deep feature maps to further improve its performance. Finally, we validate our method on the AD neuroimaging initiative (ADNI) dataset. Our method achieves average accuracies of 94.82%, 86.36%, and 65.35% for differentiating AD from normal control (NC), pMCI from NC, and sMCI from NC, respectively, and outperforms the related algorithms in the literature.

show abstract

Section: Discussion and Limitationssupporting

confidence: 91%

Section: F Comparision With Other Deep Learning Modelmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning Framework for Alzheimer’s Disease Diagnosis via 3D-CNN and FSBi-LSTM

Feng¹,

Elazab

Yang³

et al. 2019

IEEE Access

Self Cite

167

View full text Add to dashboard Cite

show abstract

“…Chronic diseases like diabetics, blood pressure, heart problems, and kidney infection are increasing worldwide. It was witnessed that diabetics and blood pressure have strong relation with cognitive decline in elderly people [24,25]. e helpless diabetic control and bad adherence to physician instructions are the primary reason for the elevation of AD or dementia in their late life [26,27].…”

Section: Proposed Workmentioning

confidence: 99%

Early Detection of Cognitive Decline Using Machine Learning Algorithm and Cognitive Ability Test

Revathi

Ramar

Ramana³

et al. 2022

Security and Communication Networks

View full text Add to dashboard Cite

Elderly people are the assets of the country and the government can ensure their peaceful and healthier life. Life expectancy of individuals has expanded with technological advancements and survey tells that the elderly population will become double in the year 2030. The noninfectious cognitive dysfunction is the most important risk factor among elderly people due to a decline in their physiological function. Alzheimer, Vascular Dementia, and Dementia are the key reasons for cognitive inabilities. These diseases require manual assistance, which is difficult to provide in this fast-growing world. Prevention and early detection are the wise solution for the above diseases. Diabetes and hypertension are considered as main risk factors allied with Alzheimer's disease. Our proposed work applies a two-stage classification technique to improve prediction accuracy. In the first stage, we train a Support vector machine and a Random Forest algorithm to analyze the influence of diabetes and high blood pressure on cognitive decline. In the second stage, the cognitive function of the person with the possibility of Dementia is assessed using the neuropsychological test called Cognitive Ability Test (CAT). Multinomial Logistic Regression algorithm is applied to CAT results to predict the possibility of cognitive decline in their postlife. We classified the risk factor using the operational definitions: “No Alzheimer’s,” “Uncertain Alzheimer’s,” and “Definite Alzheimer’s”. SVM of stage 1 classifier predicts with an accuracy of 0.86 and Random Forest with an accuracy of 0.71. Multinomial Logistic algorithm of stage 2 classifier accuracy is 0.89. The proposed work enables early prediction of a person at risk of Alzheimer's Disease using clinical data.

show abstract

“…Focusing on diagnosing AD, especially on its early stage (e.g. pMCI and sMCI) in clinical practice, Feng et al [76] proposed a simple 3D CNN architecture to obtain the deep feature representation of MRI and PET images from the ADNI dataset. In their recent work [77], a CNN‐based deep learning framework was designed.…”

Section: State‐of‐the‐artmentioning

confidence: 99%

Classifying functional nuclear images with convolutional neural networks: a survey

et al. 2020

View full text Add to dashboard Cite

3D Convolutional Neural Network and Stacked Bidirectional Recurrent Neural Network for Alzheimer’s Disease Diagnosis

Cited by 18 publications

References 12 publications

Deep Learning Framework for Alzheimer’s Disease Diagnosis via 3D-CNN and FSBi-LSTM

Deep Learning Framework for Alzheimer’s Disease Diagnosis via 3D-CNN and FSBi-LSTM

Early Detection of Cognitive Decline Using Machine Learning Algorithm and Cognitive Ability Test

Classifying functional nuclear images with convolutional neural networks: a survey

Contact Info

Product

Resources

About