Early Detection of Alzheimer’s Disease Using Polar Harmonic Transforms and Optimized Wavelet Neural Network
Effective and accurate diagnosis of Alzheimer’s disease (AD), as well as early-stage detection, has gained more and more attention in recent years. For AD classification, we propose a new hybrid method for early detection of Alzheimer’s disease (AD) using Polar Harmonic Transforms (PHT) and Self-ada...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/4/1574 |
| _version_ | 1797412179159285760 |
|---|---|
| author | Shabana Urooj Satya P. Singh Areej Malibari Fadwa Alrowais Shaeen Kalathil |
| author_facet | Shabana Urooj Satya P. Singh Areej Malibari Fadwa Alrowais Shaeen Kalathil |
| author_sort | Shabana Urooj |
| collection | DOAJ |
| description | Effective and accurate diagnosis of Alzheimer’s disease (AD), as well as early-stage detection, has gained more and more attention in recent years. For AD classification, we propose a new hybrid method for early detection of Alzheimer’s disease (AD) using Polar Harmonic Transforms (PHT) and Self-adaptive Differential Evolution Wavelet Neural Network (SaDE-WNN). The orthogonal moments are used for feature extraction from the grey matter tissues of structural Magnetic Resonance Imaging (MRI) data. Irrelevant features are removed by the feature selection process through evaluating the in-class and among-class variance. In recent years, WNNs have gained attention in classification tasks; however, they suffer from the problem of initial parameter tuning, parameter setting. We proposed a WNN with the self-adaptation technique for controlling the Differential Evolution (DE) parameters, i.e., the mutation scale factor (F) and the cross-over rate (CR). Experimental results on the Alzheimer’s disease Neuroimaging Initiative (ADNI) database indicate that the proposed method yields the best overall classification results between AD and mild cognitive impairment (MCI) (93.7% accuracy, 86.0% sensitivity, 98.0% specificity, and 0.97 area under the curve (AUC)), MCI and healthy control (HC) (92.9% accuracy, 95.2% sensitivity, 88.9% specificity, and 0.98 AUC), and AD and HC (94.4% accuracy, 88.7% sensitivity, 98.9% specificity and 0.99 AUC). |
| first_indexed | 2024-03-09T04:57:22Z |
| format | Article |
| id | doaj.art-a55411d07f6540fda7c422ba5dc183a7 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T04:57:22Z |
| publishDate | 2021-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-a55411d07f6540fda7c422ba5dc183a72023-12-03T13:03:52ZengMDPI AGApplied Sciences2076-34172021-02-01114157410.3390/app11041574Early Detection of Alzheimer’s Disease Using Polar Harmonic Transforms and Optimized Wavelet Neural NetworkShabana Urooj0Satya P. Singh1Areej Malibari2Fadwa Alrowais3Shaeen Kalathil4Department of Electrical Engineering, College of Engineering, Princess Nourah Bint Abdulrahman University, Riyadh 84428, Saudi ArabiaLee Kong Chian School of Medicine, Nanyang Technological University, Singapore 608232, SingaporeCollege of Engineering, Princess Nourah Bint Abdulrahman University, Riyadh 84428, Saudi ArabiaDepartment of Computer Sciences, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University, Riyadh 84428, Saudi ArabiaDepartment of Electrical Engineering, College of Engineering, Princess Nourah Bint Abdulrahman University, Riyadh 84428, Saudi ArabiaEffective and accurate diagnosis of Alzheimer’s disease (AD), as well as early-stage detection, has gained more and more attention in recent years. For AD classification, we propose a new hybrid method for early detection of Alzheimer’s disease (AD) using Polar Harmonic Transforms (PHT) and Self-adaptive Differential Evolution Wavelet Neural Network (SaDE-WNN). The orthogonal moments are used for feature extraction from the grey matter tissues of structural Magnetic Resonance Imaging (MRI) data. Irrelevant features are removed by the feature selection process through evaluating the in-class and among-class variance. In recent years, WNNs have gained attention in classification tasks; however, they suffer from the problem of initial parameter tuning, parameter setting. We proposed a WNN with the self-adaptation technique for controlling the Differential Evolution (DE) parameters, i.e., the mutation scale factor (F) and the cross-over rate (CR). Experimental results on the Alzheimer’s disease Neuroimaging Initiative (ADNI) database indicate that the proposed method yields the best overall classification results between AD and mild cognitive impairment (MCI) (93.7% accuracy, 86.0% sensitivity, 98.0% specificity, and 0.97 area under the curve (AUC)), MCI and healthy control (HC) (92.9% accuracy, 95.2% sensitivity, 88.9% specificity, and 0.98 AUC), and AD and HC (94.4% accuracy, 88.7% sensitivity, 98.9% specificity and 0.99 AUC).https://www.mdpi.com/2076-3417/11/4/1574Alzheimer’s diseasediscriminative analysishealthy controlmild cognitive impairmentpolar harmonic transformwavelet neural networks |
| spellingShingle | Shabana Urooj Satya P. Singh Areej Malibari Fadwa Alrowais Shaeen Kalathil Early Detection of Alzheimer’s Disease Using Polar Harmonic Transforms and Optimized Wavelet Neural Network Applied Sciences Alzheimer’s disease discriminative analysis healthy control mild cognitive impairment polar harmonic transform wavelet neural networks |
| title | Early Detection of Alzheimer’s Disease Using Polar Harmonic Transforms and Optimized Wavelet Neural Network |
| title_full | Early Detection of Alzheimer’s Disease Using Polar Harmonic Transforms and Optimized Wavelet Neural Network |
| title_fullStr | Early Detection of Alzheimer’s Disease Using Polar Harmonic Transforms and Optimized Wavelet Neural Network |
| title_full_unstemmed | Early Detection of Alzheimer’s Disease Using Polar Harmonic Transforms and Optimized Wavelet Neural Network |
| title_short | Early Detection of Alzheimer’s Disease Using Polar Harmonic Transforms and Optimized Wavelet Neural Network |
| title_sort | early detection of alzheimer s disease using polar harmonic transforms and optimized wavelet neural network |
| topic | Alzheimer’s disease discriminative analysis healthy control mild cognitive impairment polar harmonic transform wavelet neural networks |
| url | https://www.mdpi.com/2076-3417/11/4/1574 |
| work_keys_str_mv | AT shabanaurooj earlydetectionofalzheimersdiseaseusingpolarharmonictransformsandoptimizedwaveletneuralnetwork AT satyapsingh earlydetectionofalzheimersdiseaseusingpolarharmonictransformsandoptimizedwaveletneuralnetwork AT areejmalibari earlydetectionofalzheimersdiseaseusingpolarharmonictransformsandoptimizedwaveletneuralnetwork AT fadwaalrowais earlydetectionofalzheimersdiseaseusingpolarharmonictransformsandoptimizedwaveletneuralnetwork AT shaeenkalathil earlydetectionofalzheimersdiseaseusingpolarharmonictransformsandoptimizedwaveletneuralnetwork |