DSNN: A DenseNet-Based SNN for Explainable Brain Disease Classification
Aims: Brain diseases refer to intracranial tissue and organ inflammation, vascular diseases, tumors, degeneration, malformations, genetic diseases, immune diseases, nutritional and metabolic diseases, poisoning, trauma, parasitic diseases, etc. Taking Alzheimer’s disease (AD) as an example, the numb...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-05-01
|
| Series: | Frontiers in Systems Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnsys.2022.838822/full |
| _version_ | 1828217119123177472 |
|---|---|
| author | Ziquan Zhu Siyuan Lu Shui-Hua Wang Shui-Hua Wang Juan Manuel Gorriz Yu-Dong Zhang Yu-Dong Zhang Yu-Dong Zhang |
| author_facet | Ziquan Zhu Siyuan Lu Shui-Hua Wang Shui-Hua Wang Juan Manuel Gorriz Yu-Dong Zhang Yu-Dong Zhang Yu-Dong Zhang |
| author_sort | Ziquan Zhu |
| collection | DOAJ |
| description | Aims: Brain diseases refer to intracranial tissue and organ inflammation, vascular diseases, tumors, degeneration, malformations, genetic diseases, immune diseases, nutritional and metabolic diseases, poisoning, trauma, parasitic diseases, etc. Taking Alzheimer’s disease (AD) as an example, the number of patients dramatically increases in developed countries. By 2025, the number of elderly patients with AD aged 65 and over will reach 7.1 million, an increase of nearly 29% over the 5.5 million patients of the same age in 2018. Unless medical breakthroughs are made, AD patients may increase from 5.5 million to 13.8 million by 2050, almost three times the original. Researchers have focused on developing complex machine learning (ML) algorithms, i.e., convolutional neural networks (CNNs), containing millions of parameters. However, CNN models need many training samples. A small number of training samples in CNN models may lead to overfitting problems. With the continuous research of CNN, other networks have been proposed, such as randomized neural networks (RNNs). Schmidt neural network (SNN), random vector functional link (RVFL), and extreme learning machine (ELM) are three types of RNNs.Methods: We propose three novel models to classify brain diseases to cope with these problems. The proposed models are DenseNet-based SNN (DSNN), DenseNet-based RVFL (DRVFL), and DenseNet-based ELM (DELM). The backbone of the three proposed models is the pre-trained “customize” DenseNet. The modified DenseNet is fine-tuned on the empirical dataset. Finally, the last five layers of the fine-tuned DenseNet are substituted by SNN, ELM, and RVFL, respectively.Results: Overall, the DSNN gets the best performance among the three proposed models in classification performance. We evaluate the proposed DSNN by five-fold cross-validation. The accuracy, sensitivity, specificity, precision, and F1-score of the proposed DSNN on the test set are 98.46% ± 2.05%, 100.00% ± 0.00%, 85.00% ± 20.00%, 98.36% ± 2.17%, and 99.16% ± 1.11%, respectively. The proposed DSNN is compared with restricted DenseNet, spiking neural network, and other state-of-the-art methods. Finally, our model obtains the best results among all models.Conclusions: DSNN is an effective model for classifying brain diseases. |
| first_indexed | 2024-04-12T15:41:58Z |
| format | Article |
| id | doaj.art-52f92e38b52346fb82d7c1b1f531ce85 |
| institution | Directory Open Access Journal |
| issn | 1662-5137 |
| language | English |
| last_indexed | 2024-04-12T15:41:58Z |
| publishDate | 2022-05-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Systems Neuroscience |
| spelling | doaj.art-52f92e38b52346fb82d7c1b1f531ce852022-12-22T03:26:45ZengFrontiers Media S.A.Frontiers in Systems Neuroscience1662-51372022-05-011610.3389/fnsys.2022.838822838822DSNN: A DenseNet-Based SNN for Explainable Brain Disease ClassificationZiquan Zhu0Siyuan Lu1Shui-Hua Wang2Shui-Hua Wang3Juan Manuel Gorriz4Yu-Dong Zhang5Yu-Dong Zhang6Yu-Dong Zhang7School of Computing and Mathematical Sciences, University of Leicester, East Midlands, United KingdomSchool of Computing and Mathematical Sciences, University of Leicester, East Midlands, United KingdomSchool of Computing and Mathematical Sciences, University of Leicester, East Midlands, United KingdomSchool of Computer Science and Technology, Henan Polytechnic University, Jiaozuo, ChinaDepartment of Signal Theory, Networking and Communications, University of Granada, Granada, SpainSchool of Computing and Mathematical Sciences, University of Leicester, East Midlands, United KingdomSchool of Computer Science and Technology, Henan Polytechnic University, Jiaozuo, ChinaGuangxi Key Laboratory of Trusted Software, Guilin University of Electronic Technology, Guilin, ChinaAims: Brain diseases refer to intracranial tissue and organ inflammation, vascular diseases, tumors, degeneration, malformations, genetic diseases, immune diseases, nutritional and metabolic diseases, poisoning, trauma, parasitic diseases, etc. Taking Alzheimer’s disease (AD) as an example, the number of patients dramatically increases in developed countries. By 2025, the number of elderly patients with AD aged 65 and over will reach 7.1 million, an increase of nearly 29% over the 5.5 million patients of the same age in 2018. Unless medical breakthroughs are made, AD patients may increase from 5.5 million to 13.8 million by 2050, almost three times the original. Researchers have focused on developing complex machine learning (ML) algorithms, i.e., convolutional neural networks (CNNs), containing millions of parameters. However, CNN models need many training samples. A small number of training samples in CNN models may lead to overfitting problems. With the continuous research of CNN, other networks have been proposed, such as randomized neural networks (RNNs). Schmidt neural network (SNN), random vector functional link (RVFL), and extreme learning machine (ELM) are three types of RNNs.Methods: We propose three novel models to classify brain diseases to cope with these problems. The proposed models are DenseNet-based SNN (DSNN), DenseNet-based RVFL (DRVFL), and DenseNet-based ELM (DELM). The backbone of the three proposed models is the pre-trained “customize” DenseNet. The modified DenseNet is fine-tuned on the empirical dataset. Finally, the last five layers of the fine-tuned DenseNet are substituted by SNN, ELM, and RVFL, respectively.Results: Overall, the DSNN gets the best performance among the three proposed models in classification performance. We evaluate the proposed DSNN by five-fold cross-validation. The accuracy, sensitivity, specificity, precision, and F1-score of the proposed DSNN on the test set are 98.46% ± 2.05%, 100.00% ± 0.00%, 85.00% ± 20.00%, 98.36% ± 2.17%, and 99.16% ± 1.11%, respectively. The proposed DSNN is compared with restricted DenseNet, spiking neural network, and other state-of-the-art methods. Finally, our model obtains the best results among all models.Conclusions: DSNN is an effective model for classifying brain diseases.https://www.frontiersin.org/articles/10.3389/fnsys.2022.838822/fullbrain diseasesconvolutional neural networkrandomized neural networkDenseNetMRI |
| spellingShingle | Ziquan Zhu Siyuan Lu Shui-Hua Wang Shui-Hua Wang Juan Manuel Gorriz Yu-Dong Zhang Yu-Dong Zhang Yu-Dong Zhang DSNN: A DenseNet-Based SNN for Explainable Brain Disease Classification Frontiers in Systems Neuroscience brain diseases convolutional neural network randomized neural network DenseNet MRI |
| title | DSNN: A DenseNet-Based SNN for Explainable Brain Disease Classification |
| title_full | DSNN: A DenseNet-Based SNN for Explainable Brain Disease Classification |
| title_fullStr | DSNN: A DenseNet-Based SNN for Explainable Brain Disease Classification |
| title_full_unstemmed | DSNN: A DenseNet-Based SNN for Explainable Brain Disease Classification |
| title_short | DSNN: A DenseNet-Based SNN for Explainable Brain Disease Classification |
| title_sort | dsnn a densenet based snn for explainable brain disease classification |
| topic | brain diseases convolutional neural network randomized neural network DenseNet MRI |
| url | https://www.frontiersin.org/articles/10.3389/fnsys.2022.838822/full |
| work_keys_str_mv | AT ziquanzhu dsnnadensenetbasedsnnforexplainablebraindiseaseclassification AT siyuanlu dsnnadensenetbasedsnnforexplainablebraindiseaseclassification AT shuihuawang dsnnadensenetbasedsnnforexplainablebraindiseaseclassification AT shuihuawang dsnnadensenetbasedsnnforexplainablebraindiseaseclassification AT juanmanuelgorriz dsnnadensenetbasedsnnforexplainablebraindiseaseclassification AT yudongzhang dsnnadensenetbasedsnnforexplainablebraindiseaseclassification AT yudongzhang dsnnadensenetbasedsnnforexplainablebraindiseaseclassification AT yudongzhang dsnnadensenetbasedsnnforexplainablebraindiseaseclassification |