1
|
Bapat R, Ma D, Duong TQ. Predicting Four-Year's Alzheimer's Disease Onset Using Longitudinal Neurocognitive Tests and MRI Data Using Explainable Deep Convolutional Neural Networks. J Alzheimers Dis 2024; 97:459-469. [PMID: 38143361 DOI: 10.3233/jad-230893] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/26/2023]
Abstract
BACKGROUND Prognosis of future risk of dementia from neuroimaging and cognitive data is important for optimizing clinical management for patients at early stage of Alzheimer's disease (AD). However, existing studies lack an efficient way to integrate longitudinal information from both modalities to improve prognosis performance. OBJECTIVE In this study, we aim to develop and evaluate an explainable deep learning-based framework to predict mild cognitive impairment (MCI) to AD conversion within four years using longitudinal whole-brain 3D MRI and neurocognitive tests. METHODS We proposed a two-stage framework that first uses a 3D convolutional neural network to extract single-timepoint MRI-based AD-related latent features, followed by multi-modal longitudinal feature concatenation and a 1D convolutional neural network to predict the risk of future dementia onset in four years. RESULTS The proposed deep learning framework showed promising to predict MCI to AD conversion within 4 years using longitudinal whole-brain 3D MRI and cognitive data without extracting regional brain volumes or cortical thickness, reaching a balanced accuracy of 0.834, significantly improved from models trained from single timepoint or single modality. The post hoc model explainability revealed heatmap indicating regions that are important for predicting future risk of AD. CONCLUSIONS The proposed framework sets the stage for future studies for using multi-modal longitudinal data to achieve optimal prediction for prognosis of AD onset, leading to better management of the diseases, thereby improving the quality of life.
Collapse
Affiliation(s)
- Rohan Bapat
- Department of Radiology, Albert Einstein College of Medicine and Montefiore Medical Center, Bronx, NY, USA
| | - Da Ma
- Department of Internal Medicine Section of Gerontology and Geriatric Medicine, Wake Forest University School of Medicine, Winston-Salam, NC, USA
| | - Tim Q Duong
- Department of Radiology, Albert Einstein College of Medicine and Montefiore Medical Center, Bronx, NY, USA
| |
Collapse
|
2
|
Almufareh MF, Tehsin S, Humayun M, Kausar S. Artificial Cognition for Detection of Mental Disability: A Vision Transformer Approach for Alzheimer's Disease. Healthcare (Basel) 2023; 11:2763. [PMID: 37893836 PMCID: PMC10606602 DOI: 10.3390/healthcare11202763] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/25/2023] [Revised: 10/16/2023] [Accepted: 10/17/2023] [Indexed: 10/29/2023] Open
Abstract
Alzheimer's disease is a common neurological disorder and mental disability that causes memory loss and cognitive decline, presenting a major challenge to public health due to its impact on millions of individuals worldwide. It is crucial to diagnose and treat Alzheimer's in a timely manner to improve the quality of life of both patients and caregivers. In the recent past, machine learning techniques have showed potential in detecting Alzheimer's disease by examining neuroimaging data, especially Magnetic Resonance Imaging (MRI). This research proposes an attention-based mechanism that employs the vision transformer approach to detect Alzheimer's using MRI images. The presented technique applies preprocessing to the MRI images and forwards them to a vision transformer network for classification. This network is trained on the publicly available Kaggle dataset, and it illustrated impressive results with an accuracy of 99.06%, precision of 99.06%, recall of 99.14%, and F1-score of 99.1%. Furthermore, a comparative study is also conducted to evaluate the performance of the proposed method against various state-of-the-art techniques on diverse datasets. The proposed method demonstrated superior performance, outperforming other published methods when applied to the Kaggle dataset.
Collapse
Affiliation(s)
- Maram Fahaad Almufareh
- Department of Information Systems, College of Computer and Information Sciences, Jouf University, Sakakah 72388, Saudi Arabia;
| | - Samabia Tehsin
- Department of Computer Science, Bahria University, Islamabad 44000, Pakistan; (S.T.); (S.K.)
| | - Mamoona Humayun
- Department of Information Systems, College of Computer and Information Sciences, Jouf University, Sakakah 72388, Saudi Arabia;
| | - Sumaira Kausar
- Department of Computer Science, Bahria University, Islamabad 44000, Pakistan; (S.T.); (S.K.)
| |
Collapse
|
3
|
Saleh H, Amer E, Abuhmed T, Ali A, Al-Fuqaha A, El-Sappagh S. Computer aided progression detection model based on optimized deep LSTM ensemble model and the fusion of multivariate time series data. Sci Rep 2023; 13:16336. [PMID: 37770490 PMCID: PMC10539296 DOI: 10.1038/s41598-023-42796-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/24/2023] [Accepted: 09/14/2023] [Indexed: 09/30/2023] Open
Abstract
Alzheimer's disease (AD) is the most common form of dementia. Early and accurate detection of AD is crucial to plan for disease modifying therapies that could prevent or delay the conversion to sever stages of the disease. As a chronic disease, patient's multivariate time series data including neuroimaging, genetics, cognitive scores, and neuropsychological battery provides a complete profile about patient's status. This data has been used to build machine learning and deep learning (DL) models for the early detection of the disease. However, these models still have limited performance and are not stable enough to be trusted in real medical settings. Literature shows that DL models outperform classical machine learning models, but ensemble learning has proven to achieve better results than standalone models. This study proposes a novel deep stacking framework which combines multiple DL models to accurately predict AD at an early stage. The study uses long short-term memory (LSTM) models as base models over patient's multivariate time series data to learn the deep longitudinal features. Each base LSTM classifier has been optimized using the Bayesian optimizer using different feature sets. As a result, the final optimized ensembled model employed heterogeneous base models that are trained on heterogeneous data. The performance of the resulting ensemble model has been explored using a cohort of 685 patients from the University of Washington's National Alzheimer's Coordinating Center dataset. Compared to the classical machine learning models and base LSTM classifiers, the proposed ensemble model achieves the highest testing results (i.e., 82.02, 82.25, 82.02, and 82.12 for accuracy, precision, recall, and F1-score, respectively). The resulting model enhances the performance of the state-of-the-art literature, and it could be used to build an accurate clinical decision support tool that can assist domain experts for AD progression detection.
Collapse
Affiliation(s)
- Hager Saleh
- Faculty of Computers and Artificial Intelligence, South Valley University, Hurghada, Egypt
| | - Eslam Amer
- Communications and Information Technology, The Institute of Electronics, Queen's University of Belfast, Belfast, UK
| | - Tamer Abuhmed
- Information Laboratory (InfoLab), College of Computing and Informatics, Sungkyunkwan University, Seoul, Suwon, 16419, South Korea.
| | - Amjad Ali
- Information and Computing Technology (ICT) Division, College of Science and Engineering (CSE), Hamad Bin Khalifa University, Doha, Qatar
| | - Ala Al-Fuqaha
- Information and Computing Technology (ICT) Division, College of Science and Engineering (CSE), Hamad Bin Khalifa University, Doha, Qatar
| | - Shaker El-Sappagh
- Information Laboratory (InfoLab), College of Computing and Informatics, Sungkyunkwan University, Seoul, Suwon, 16419, South Korea.
- Faculty of Computer Science and Engineering, Galala University, Suez, 435611, Egypt.
- Faculty of Computers and Artificial Intelligence, Benha University, Banha, 13518, Egypt.
| |
Collapse
|
4
|
Salehi W, Baglat P, Gupta G, Khan SB, Almusharraf A, Alqahtani A, Kumar A. An Approach to Binary Classification of Alzheimer's Disease Using LSTM. Bioengineering (Basel) 2023; 10:950. [PMID: 37627835 PMCID: PMC10451729 DOI: 10.3390/bioengineering10080950] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/29/2023] [Revised: 07/25/2023] [Accepted: 07/25/2023] [Indexed: 08/27/2023] Open
Abstract
In this study, we use LSTM (Long-Short-Term-Memory) networks to evaluate Magnetic Resonance Imaging (MRI) data to overcome the shortcomings of conventional Alzheimer's disease (AD) detection techniques. Our method offers greater reliability and accuracy in predicting the possibility of AD, in contrast to cognitive testing and brain structure analyses. We used an MRI dataset that we downloaded from the Kaggle source to train our LSTM network. Utilizing the temporal memory characteristics of LSTMs, the network was created to efficiently capture and evaluate the sequential patterns inherent in MRI scans. Our model scored a remarkable AUC of 0.97 and an accuracy of 98.62%. During the training process, we used Stratified Shuffle-Split Cross Validation to make sure that our findings were reliable and generalizable. Our study adds significantly to the body of knowledge by demonstrating the potential of LSTM networks in the specific field of AD prediction and extending the variety of methods investigated for image classification in AD research. We have also designed a user-friendly Web-based application to help with the accessibility of our developed model, bridging the gap between research and actual deployment.
Collapse
Affiliation(s)
- Waleed Salehi
- Yogananda School of AI, Shoolini University, Bajhol 173229, India; (W.S.); (G.G.)
| | - Preety Baglat
- Interactive Technologies Institute (ITI/LARSyS and ARDITI), University of Madeira, 9000-082 Funchal, Portugal;
| | - Gaurav Gupta
- Yogananda School of AI, Shoolini University, Bajhol 173229, India; (W.S.); (G.G.)
| | - Surbhi Bhatia Khan
- Department of Data Science, School of Science, Engineering and Environment, University of Salford, Manchester M5 4WT, UK;
| | - Ahlam Almusharraf
- Department of Business Administration, College of Business and Administration, Princess Nourah Bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi Arabia;
| | - Ali Alqahtani
- Department of Networks and Communications Engineering, College of Computer Science and Information Systems, Najran University, Najran 61441, Saudi Arabia;
| | - Adarsh Kumar
- School of Computer Science, Mohammed VI Polytechnic University, Ben Guerir 43150, Morocco
- School of Computer Science, University of Petroleum and Energy Studies, Dehradun 248007, India
| |
Collapse
|
5
|
Hosni Mahmoud HA, Alabdulkreem E. Bidirectional Neural Network Model for Glaucoma Progression Prediction. J Pers Med 2023; 13:390. [PMID: 36983572 PMCID: PMC10052760 DOI: 10.3390/jpm13030390] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/03/2023] [Revised: 02/17/2023] [Accepted: 02/20/2023] [Indexed: 03/30/2023] Open
Abstract
Deep learning models are usually utilized to learn from spatial data, only a few studies are proposed to predict glaucoma time progression utilizing deep learning models. In this article, we present a bidirectional recurrent deep learning model (Bi-RM) to detect prospective progressive visual field diagnoses. A dataset of 5413 different eyes from 3321 samples is utilized as the learning phase dataset and 1272 eyes are used for testing. Five consecutive diagnoses are recorded from the dataset as input and the sixth progressive visual field diagnosis is matched with the prediction of the Bi-RM. The precision metrics of the Bi-RM are validated in association with the linear regression algorithm (LR) and term memory (TM) technique. The total prediction error of the Bi-RM is significantly less than those of LR and TM. In the class prediction, Bi-RM depicts the least prediction error in all three methods in most of the testing cases. In addition, Bi-RM is not impacted by the reliability keys and the glaucoma degree.
Collapse
Affiliation(s)
- Hanan A. Hosni Mahmoud
- Department of Computer Sciences, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi Arabia
| | | |
Collapse
|
6
|
Naqvi RA, Arsalan M, Qaiser T, Khan TM, Razzak I. Sensor Data Fusion Based on Deep Learning for Computer Vision Applications and Medical Applications. SENSORS (BASEL, SWITZERLAND) 2022; 22:8058. [PMID: 36298412 PMCID: PMC9609765 DOI: 10.3390/s22208058] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/27/2022] [Accepted: 10/14/2022] [Indexed: 06/16/2023]
Abstract
Sensor fusion is the process of merging data from many sources, such as radar, lidar and camera sensors, to provide less uncertain information compared to the information collected from single source [...].
Collapse
Affiliation(s)
- Rizwan Ali Naqvi
- School of Intelligent Mechatronics Engineering, Sejong University, Seoul 05006, Korea
| | - Muhammad Arsalan
- Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 04620, Korea
| | - Talha Qaiser
- Department of Computer Science, University of Warwick, Coventry CV4 7AL, UK
| | - Tariq Mahmood Khan
- School of Computer Science and Engineering, University of New South Wales, Sydney 1466, Australia
| | - Imran Razzak
- School of Computer Science and Engineering, University of New South Wales, Sydney 1466, Australia
| |
Collapse
|