Diagnosis of Alzheimer’s Disease Based on Accelerated Mirror Descent Optimization and a Three-Dimensional Aggregated Residual Network
Alzheimer’s disease (AD), a neuropsychiatric disorder, continually arises in the elderly. To date, no targeted medications have been developed for AD. Early and fast diagnosis of AD plays a pivotal role in identifying potential AD patients, enabling timely medical interventions, and mitigating disea...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/21/8708 |
| _version_ | 1797631364525195264 |
|---|---|
| author | Yue Tu Shukuan Lin Jianzhong Qiao Peng Zhang Kuankuan Hao |
| author_facet | Yue Tu Shukuan Lin Jianzhong Qiao Peng Zhang Kuankuan Hao |
| author_sort | Yue Tu |
| collection | DOAJ |
| description | Alzheimer’s disease (AD), a neuropsychiatric disorder, continually arises in the elderly. To date, no targeted medications have been developed for AD. Early and fast diagnosis of AD plays a pivotal role in identifying potential AD patients, enabling timely medical interventions, and mitigating disease progression. Computer-aided diagnosis (CAD) becomes possible with the burgeoning of deep learning. However, the existing CAD models for processing 3D Alzheimer’s disease images usually have the problems of slow convergence, disappearance of gradient, and falling into local optimum. This makes the training of 3D diagnosis models need a lot of time, and the accuracy is often poor. In this paper, a novel 3D aggregated residual network with accelerated mirror descent optimization is proposed for diagnosing AD. First, a novel unbiased subgradient accelerated mirror descent (SAMD) optimization algorithm is proposed to speed up diagnosis network training. By optimizing the nonlinear projection process, our proposed algorithm can avoid the occurrence of the local optimum in the non-Euclidean distance metric. The most notable aspect is that, to the best of our knowledge, this is the pioneering attempt to optimize the AD diagnosis training process by improving the optimization algorithm. Then, we provide a rigorous proof of the SAMD’s convergence, and the convergence of SAMD is better than any existing gradient descent algorithms. Finally, we use our proposed SAMD algorithm to train our proposed 3D aggregated residual network architecture (ARCNN). We employed the ADNI dataset to train ARCNN diagnostic models separately for the AD vs. NC task and the sMCI vs. pMCI task, followed by testing to evaluate the disease diagnostic outcomes. The results reveal that the accuracy can be improved in diagnosing AD, and the training speed can be accelerated. Our proposed method achieves 95.4% accuracy in AD diagnosis and 79.9% accuracy in MCI diagnosis; the best results contrasted with several state-of-the-art diagnosis methods. In addition, our proposed SAMD algorithm can save about 19% of the convergence time on average in the AD diagnosis model compared with the gradient descent algorithms, which is very momentous in clinic. |
| first_indexed | 2024-03-11T11:21:49Z |
| format | Article |
| id | doaj.art-e005207b274b4ca6a57c26b25a3fdeaf |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T11:21:49Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-e005207b274b4ca6a57c26b25a3fdeaf2023-11-10T15:11:46ZengMDPI AGSensors1424-82202023-10-012321870810.3390/s23218708Diagnosis of Alzheimer’s Disease Based on Accelerated Mirror Descent Optimization and a Three-Dimensional Aggregated Residual NetworkYue Tu0Shukuan Lin1Jianzhong Qiao2Peng Zhang3Kuankuan Hao4Department of Computer Science and Engineering, Northeastern University, Shenyang 110819, ChinaDepartment of Computer Science and Engineering, Northeastern University, Shenyang 110819, ChinaDepartment of Computer Science and Engineering, Northeastern University, Shenyang 110819, ChinaDepartment of Computer Science and Engineering, Northeastern University, Shenyang 110819, ChinaDepartment of Computer Science and Engineering, Northeastern University, Shenyang 110819, ChinaAlzheimer’s disease (AD), a neuropsychiatric disorder, continually arises in the elderly. To date, no targeted medications have been developed for AD. Early and fast diagnosis of AD plays a pivotal role in identifying potential AD patients, enabling timely medical interventions, and mitigating disease progression. Computer-aided diagnosis (CAD) becomes possible with the burgeoning of deep learning. However, the existing CAD models for processing 3D Alzheimer’s disease images usually have the problems of slow convergence, disappearance of gradient, and falling into local optimum. This makes the training of 3D diagnosis models need a lot of time, and the accuracy is often poor. In this paper, a novel 3D aggregated residual network with accelerated mirror descent optimization is proposed for diagnosing AD. First, a novel unbiased subgradient accelerated mirror descent (SAMD) optimization algorithm is proposed to speed up diagnosis network training. By optimizing the nonlinear projection process, our proposed algorithm can avoid the occurrence of the local optimum in the non-Euclidean distance metric. The most notable aspect is that, to the best of our knowledge, this is the pioneering attempt to optimize the AD diagnosis training process by improving the optimization algorithm. Then, we provide a rigorous proof of the SAMD’s convergence, and the convergence of SAMD is better than any existing gradient descent algorithms. Finally, we use our proposed SAMD algorithm to train our proposed 3D aggregated residual network architecture (ARCNN). We employed the ADNI dataset to train ARCNN diagnostic models separately for the AD vs. NC task and the sMCI vs. pMCI task, followed by testing to evaluate the disease diagnostic outcomes. The results reveal that the accuracy can be improved in diagnosing AD, and the training speed can be accelerated. Our proposed method achieves 95.4% accuracy in AD diagnosis and 79.9% accuracy in MCI diagnosis; the best results contrasted with several state-of-the-art diagnosis methods. In addition, our proposed SAMD algorithm can save about 19% of the convergence time on average in the AD diagnosis model compared with the gradient descent algorithms, which is very momentous in clinic.https://www.mdpi.com/1424-8220/23/21/8708Alzheimer’s diseaseoptimization algorithmmirror descentCNNMRI |
| spellingShingle | Yue Tu Shukuan Lin Jianzhong Qiao Peng Zhang Kuankuan Hao Diagnosis of Alzheimer’s Disease Based on Accelerated Mirror Descent Optimization and a Three-Dimensional Aggregated Residual Network Sensors Alzheimer’s disease optimization algorithm mirror descent CNN MRI |
| title | Diagnosis of Alzheimer’s Disease Based on Accelerated Mirror Descent Optimization and a Three-Dimensional Aggregated Residual Network |
| title_full | Diagnosis of Alzheimer’s Disease Based on Accelerated Mirror Descent Optimization and a Three-Dimensional Aggregated Residual Network |
| title_fullStr | Diagnosis of Alzheimer’s Disease Based on Accelerated Mirror Descent Optimization and a Three-Dimensional Aggregated Residual Network |
| title_full_unstemmed | Diagnosis of Alzheimer’s Disease Based on Accelerated Mirror Descent Optimization and a Three-Dimensional Aggregated Residual Network |
| title_short | Diagnosis of Alzheimer’s Disease Based on Accelerated Mirror Descent Optimization and a Three-Dimensional Aggregated Residual Network |
| title_sort | diagnosis of alzheimer s disease based on accelerated mirror descent optimization and a three dimensional aggregated residual network |
| topic | Alzheimer’s disease optimization algorithm mirror descent CNN MRI |
| url | https://www.mdpi.com/1424-8220/23/21/8708 |
| work_keys_str_mv | AT yuetu diagnosisofalzheimersdiseasebasedonacceleratedmirrordescentoptimizationandathreedimensionalaggregatedresidualnetwork AT shukuanlin diagnosisofalzheimersdiseasebasedonacceleratedmirrordescentoptimizationandathreedimensionalaggregatedresidualnetwork AT jianzhongqiao diagnosisofalzheimersdiseasebasedonacceleratedmirrordescentoptimizationandathreedimensionalaggregatedresidualnetwork AT pengzhang diagnosisofalzheimersdiseasebasedonacceleratedmirrordescentoptimizationandathreedimensionalaggregatedresidualnetwork AT kuankuanhao diagnosisofalzheimersdiseasebasedonacceleratedmirrordescentoptimizationandathreedimensionalaggregatedresidualnetwork |