CNN and swin-transformer based efficient model for Alzheimer’s disease diagnosis with sMRI
•Extracting features by combining CNN and swin-transformer.•Lightweight method didn’t degenerate the model with our 2.5D and 2-stream method.•Performance is close to previous 3D methods by only using 2D algorithms.•Only sMRI images are used as input data. Alzheimer's disease (AD) is a primary c...
Saved in:
| Published in: | Biomedical signal processing and control Vol. 86; p. 105189 |
|---|---|
| Main Authors: | , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Elsevier Ltd
01.09.2023
|
| Subjects: | |
| ISSN: | 1746-8094, 1746-8108 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | •Extracting features by combining CNN and swin-transformer.•Lightweight method didn’t degenerate the model with our 2.5D and 2-stream method.•Performance is close to previous 3D methods by only using 2D algorithms.•Only sMRI images are used as input data.
Alzheimer's disease (AD) is a primary cause of dementia. Its early diagnosis is crucial to delay the progression of the disease. So far, many computer aided diagnosis (CAD) methods that combined deep learning algorithms and structural MRI have achieved encouraging results. To improve the AD diagnosis performance, more and more models are based on 3D algorithms, which make the training and deployment of these methods unaffordable. In this study, a CNN and swin-transformer based efficient model, Efficient Conv-Swin Net (ECSnet), was developed. In this model: (1) a 2.5D-subject method and two-stream structure are used to help the model to encode 3D information to 2D feature maps; (2) convolution blocks are applied in the early stages of the transformer-based backbone network to improve the generalization ability; (3) a series of lightweight approaches are applied to reduce the parameters and computational cost of the model to enable the model to train and infer efficiently. Due to the lack of multi-center data and the differences between test sets, it is difficult to make a fair comparison between the previous methods. Our model was trained on the ADNI dataset and evaluated on an independent test set from AIBL. After being lightened, our proposed method showed no performance degradation on both ADNI and AIBL compared to models such as swin-T tiny. The ECSnet achieved 92.8% balance accuracy and 91.1% sensitivity on the AIBL, which are better than those of previous works while the model is more efficient than those 3D methods. |
|---|---|
| AbstractList | •Extracting features by combining CNN and swin-transformer.•Lightweight method didn’t degenerate the model with our 2.5D and 2-stream method.•Performance is close to previous 3D methods by only using 2D algorithms.•Only sMRI images are used as input data.
Alzheimer's disease (AD) is a primary cause of dementia. Its early diagnosis is crucial to delay the progression of the disease. So far, many computer aided diagnosis (CAD) methods that combined deep learning algorithms and structural MRI have achieved encouraging results. To improve the AD diagnosis performance, more and more models are based on 3D algorithms, which make the training and deployment of these methods unaffordable. In this study, a CNN and swin-transformer based efficient model, Efficient Conv-Swin Net (ECSnet), was developed. In this model: (1) a 2.5D-subject method and two-stream structure are used to help the model to encode 3D information to 2D feature maps; (2) convolution blocks are applied in the early stages of the transformer-based backbone network to improve the generalization ability; (3) a series of lightweight approaches are applied to reduce the parameters and computational cost of the model to enable the model to train and infer efficiently. Due to the lack of multi-center data and the differences between test sets, it is difficult to make a fair comparison between the previous methods. Our model was trained on the ADNI dataset and evaluated on an independent test set from AIBL. After being lightened, our proposed method showed no performance degradation on both ADNI and AIBL compared to models such as swin-T tiny. The ECSnet achieved 92.8% balance accuracy and 91.1% sensitivity on the AIBL, which are better than those of previous works while the model is more efficient than those 3D methods. |
| ArticleNumber | 105189 |
| Author | Tang, Xiaoying Wang, Ancong Guo, Rui Liu, Weifeng Xin, Jiaming |
| Author_xml | – sequence: 1 givenname: Jiaming surname: Xin fullname: Xin, Jiaming organization: School of Life Science, Beijing Institute of Technology, Beijing 100081, China – sequence: 2 givenname: Ancong surname: Wang fullname: Wang, Ancong organization: School of Life Science, Beijing Institute of Technology, Beijing 100081, China – sequence: 3 givenname: Rui surname: Guo fullname: Guo, Rui organization: School of Medical Technology, Beijing Institute of Technology, Beijing 100081, China – sequence: 4 givenname: Weifeng orcidid: 0000-0002-1546-214X surname: Liu fullname: Liu, Weifeng email: breeze@bit.edu.cn organization: School of Life Science, Beijing Institute of Technology, Beijing 100081, China – sequence: 5 givenname: Xiaoying surname: Tang fullname: Tang, Xiaoying email: xiaoying@bit.edu.cn organization: School of Life Science, Beijing Institute of Technology, Beijing 100081, China |
| BookMark | eNp9kM9KAzEQh4Mo2FZfwFNeYGuyu90k4KUU_xRqBdGbELLJxKZssyVZLHryNXw9n8Qs1YuHnmaYmW_g9w3RsW89IHRByZgSWl2ux3Xc6nFO8iINJpSLIzSgrKwyTgk__uuJKE_RMMY1ISVntBygl9lyiZU3OO6cz7qgfLRt2EDAtYpgMFjrtAPf4U1roMFpiafNxwpcuvn-_IrYuAjpNFX16tvoIt65boXj_eP8DJ1Y1UQ4_60j9Hxz_TS7yxYPt_PZdJHpgpAuY4Sw0thaFXkuVFVrXSkqlGKGGq6r2oKxk5IJAKUpCMYLZQRjwvCaMNC8GCG-_6tDG2MAK7XrVOdanwK5RlIie0tyLXtLsrck95YSmv9Dt8FtVHg_DF3tIUih3hwEGXtHGowLoDtpWncI_wG9tYXU |
| CitedBy_id | crossref_primary_10_1002_ajmg_b_32979 crossref_primary_10_1016_j_patrec_2025_01_029 crossref_primary_10_1038_s41598_024_78712_9 crossref_primary_10_1016_j_compbiomed_2024_108116 crossref_primary_10_1109_OJIM_2025_3589698 crossref_primary_10_1016_j_bspc_2024_107467 crossref_primary_10_1016_j_asoc_2025_113693 crossref_primary_10_3233_IDT_240652 crossref_primary_10_1109_TIM_2025_3555721 crossref_primary_10_1038_s41598_025_11743_y crossref_primary_10_1049_pel2_12664 crossref_primary_10_3390_math12172720 crossref_primary_10_1016_j_imu_2024_101584 crossref_primary_10_1109_ACCESS_2024_3430325 crossref_primary_10_3390_land14010022 crossref_primary_10_1016_j_procs_2025_04_278 crossref_primary_10_1088_1402_4896_add2a6 crossref_primary_10_1109_ACCESS_2025_3606334 crossref_primary_10_1515_revneuro_2024_0088 crossref_primary_10_1186_s12880_024_01520_0 |
| Cites_doi | 10.1016/j.cmpb.2016.10.007 10.1109/ISBI52829.2022.9761549 10.1016/j.compbiomed.2019.103527 10.1186/s13024-019-0333-5 10.1145/3065386 10.1109/THMS.2023.3238113 10.1097/RLU.0000000000000547 10.1016/j.neuroimage.2017.03.057 10.1016/j.bspc.2020.102397 10.1055/s-0039-1678581 10.1109/CVPR.2017.243 10.1016/j.eswa.2021.115456 10.1016/j.bspc.2021.103445 10.1109/CVPR.2016.90 10.1109/RBME.2018.2796598 10.1016/j.neuron.2013.01.002 10.1007/s12021-013-9204-3 10.1016/j.jalz.2010.03.009 10.1002/alz.12068 10.1038/nature14539 10.1109/TMI.2021.3077079 10.1016/j.media.2020.101694 10.4018/978-1-6684-3947-0.ch012 10.1088/1361-6560/ac5ed5 10.1126/science.1132813 10.1002/jmri.21049 10.1093/brain/awaa137 10.1109/CVPR.2018.00378 10.1016/j.bspc.2021.103051 10.1007/s00259-011-2021-8 10.1109/CVPR.2018.00745 10.1088/1741-2552/ac37cc 10.1109/CVPR42600.2020.00165 10.1088/1361-6560/aa5dbe 10.1016/j.compbiomed.2021.104678 10.1109/ICCV48922.2021.00986 10.1016/j.nicl.2013.07.006 10.1186/alzrt100 |
| ContentType | Journal Article |
| Copyright | 2023 Elsevier Ltd |
| Copyright_xml | – notice: 2023 Elsevier Ltd |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.bspc.2023.105189 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1746-8108 |
| ExternalDocumentID | 10_1016_j_bspc_2023_105189 S1746809423006225 |
| GroupedDBID | --- --K --M .~1 0R~ 1B1 1~. 1~5 23N 4.4 457 4G. 5GY 5VS 6J9 7-5 71M 8P~ AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAXUO AAYFN ABBOA ABFNM ABFRF ABJNI ABMAC ABXDB ABYKQ ACDAQ ACGFO ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADMUD ADTZH AEBSH AECPX AEFWE AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD AXJTR BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F5P FDB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HZ~ IHE J1W JJJVA KOM M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 RIG ROL RPZ SDF SDG SES SPC SPCBC SST SSV SSZ T5K UNMZH ~G- 9DU AATTM AAXKI AAYWO AAYXX ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD |
| ID | FETCH-LOGICAL-c300t-70074dfba3229a6bcc6a19aa7d1d8c6bfedf5479eeac1e9783ad9779d8b07ec83 |
| ISICitedReferencesCount | 27 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001038041200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1746-8094 |
| IngestDate | Sat Nov 29 06:58:08 EST 2025 Tue Nov 18 21:43:23 EST 2025 Fri Feb 23 02:36:20 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Deep learning Alzheimer’s disease Magnetic resonance imaging Computational complexity Image classification |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c300t-70074dfba3229a6bcc6a19aa7d1d8c6bfedf5479eeac1e9783ad9779d8b07ec83 |
| ORCID | 0000-0002-1546-214X |
| ParticipantIDs | crossref_citationtrail_10_1016_j_bspc_2023_105189 crossref_primary_10_1016_j_bspc_2023_105189 elsevier_sciencedirect_doi_10_1016_j_bspc_2023_105189 |
| PublicationCentury | 2000 |
| PublicationDate | September 2023 2023-09-00 |
| PublicationDateYYYYMMDD | 2023-09-01 |
| PublicationDate_xml | – month: 09 year: 2023 text: September 2023 |
| PublicationDecade | 2020 |
| PublicationTitle | Biomedical signal processing and control |
| PublicationYear | 2023 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, B. Guo. Swin transformer: Hierarchical vision transformer using shifted windows. S. Sarraf, J. Sun. Functional brain imaging: A comprehensive survey (2016). Atri (b0020) 2019; 39 LeCun, Bengio, Hinton (b0095) 2015; 521 Hosseini-Asl, Keynton, El-Baz (b0080) 2016; 2016 https://doi.org/10.48550/arXiv.2206.02680. Khan, Pachori (b0255) 2021; 184 S. Wang, B.Z. Li, M. Khabsa, H. Fang, H. Ma. Linformer: Self-attention with linear complexity (2020). G. Huang, Z. Liu, L. Van Der Maaten, K.Q. Weinberger. Densely connected convolutional networks. S.I. Khan, R.B. Pachori. Automated Eye Movement Classification Based on EMG of EOM Signals Using FBSE-EWT Technique. Ieee Transactions on Human-Machine Systems. https://doi.org/10.1109/thms.2023.3238113. (2021), 10012-10022. https://doi.org/10.48550/arXiv.2103.14030. Jack, Bernstein, Fox, Thompson, Alexander, Harvey, Borowski, Britson, Whitwell, Ward (b0190) 2008; 27 Zhang, Du, Liu (b0200) 2021; 18 Rathore, Habes, Iftikhar, Shacklett, Davatzikos (b0075) 2017; 155 Marcus, Mena, Subramaniam (b0055) 2014; 39 Kang, Lin, Zhang, Shen, Wu, Initiative (b0130) 2021; 136 Krizhevsky, Sutskever, Hinton (b0150) 2017; 60 Hon, Khan (b0120) 2017 (2018), 3588–3597. https://doi.org/10.1109/CVPR.2018.00378. S.I. Khan, R.B. Pachori. Empirical Wavelet Transform-Based Framework for Diagnosis of Epilepsy Using EEG Signals. (2022). In R. K. Chaurasiya, D. Agrawal, & R. B. Pachori (Eds.), AI-Enabled Smart Healthcare Using Biomedical Signals (pp. 217-239). IGI Global. https://doi.org/10.4018/978-1-6684-3947-0.ch012. J. Hu, L. Shen, G. Sun. Squeeze-and-excitation networks. DeTure, Dickson (b0210) 2019; 14 https://doi.org/10.48550/arXiv.1704.04861. K. Han, Y. Wang, Q. Tian, J. Guo, C. Xu, C. Xu. Ghostnet: More features from cheap operations. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (2020). A.G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, H. Adam. Mobilenets: Efficient convolutional neural networks for mobile vision applications (2017). Xiao, Singh, Mintun, Darrell, Dollár, Girshick (b0215) 2021; 34 Qiu, Joshi, Miller, Xue, Zhou, Karjadi, Chang, Joshi, Dwyer, Zhu (b0205) 2020; 143 , Gao, Hui, Tian (b0085) 2017; 138 Alzheimer's disease facts and figures. (2020). (3),(2010), 291-296. https://doi.org/10.1016/j.jalz.2010.03.009. Raffel, Shazeer, Roberts, Lee, Narang, Matena, Zhou, Li, Liu (b0220) 2020; 21 Xu, Ba, Kiros, Cho, Courville, Salakhudinov, Zemel, Bengio (b0170) 2015 Vemuri, Jones, Jack (b0045) 2012; 4 Roberson, Mucke (b0005) 2006; 314 Maggipinto, Bellotti, Amoroso, Diacono, Donvito, Lella, Monaco, Scelsi, Tangaro, Initiative (b0065) 2017; 62 Khojaste-Sarakhsi, Haghighi, Ghomi, Marchiori (b0090) 2022; 102332 Wen, Thibeau-Sutre, Diaz-Melo, Samper-González, Routier, Bottani, Dormont, Durrleman, Burgos, Colliot (b0115) 2020; 63 S. Mehta, M. Rastegari. Separable Self-attention for Mobile Vision Transformers (2022). H. Hu, J. Gu, Z. Zhang, J. Dai, Y. Wei. Relation networks for object detection. Khan, Qaisar, Pachori (b0030) 2022; 73 Mendoza-Léon, Puentes, Uriza, Hoyos (b0125) 2020; 116 https://doi.org/10.48550/arXiv.2010.11929. (2016), 770-778. (2022), 1-5. https://doi.org/10.1109/ISBI52829.2022.9761549. Hedayati, Khedmati, Taghipour-Gorjikolaie (b0145) 2021; 66 Khan, Pachori (b0230) 2021; 70 C. Li, Y. Cui, N. Luo, Y. Liu, P. Bourgeat, J. Fripp, T. Jiang. Trans-ResNet: Integrating Transformers and CNNs for Alzheimer’s disease classification. Jagust (b0015) 2013; 77 https://doi.org/10.48550/arXiv.1602.02225. Nir, Jahanshad, Villalon-Reina, Toga, Jack, Weiner, Thompson, Initiative (b0060) 2013; 3 (2018), 7132-7141. https://doi.org/10.1109/TPAMI.2019.2913372. Abraham, Pedregosa, Eickenberg, Gervais, Mueller, Kossaifi, Gramfort, Thirion, Varoquaux (b0105) 2014; 14 Leandrou, Petroudi, Kyriacou, Reyes-Aldasoro, Pattichis (b0070) 2018; 11 4700-4708 (2017). https://doi.org/10.1109/CVPR.2017.243. Han, He, Yang, Zhang (b0245) 2022; 67 https://doi.org/10.48550/arXiv.2006.04768. K.A. Ellis, C.C. Rowe, V.L. Villemagne, R.N. Martins, C.L. Masters, O. Salvado, C. Szoeke, D. Ames, Group, A. R. Addressing population aging and Alzheimer's disease through the Australian Imaging Biomarkers and Lifestyle study: Collaboration with the Alzheimer's Disease Neuroimaging Initiative. Mwangi, Tian, Soares (b0110) 2014; 12 K. He, X. Zhang, S. Ren, J. Sun. Deep residual learning for image recognition. https://doi.org/10.1002/alz.12068. Lian, Liu, Pan, Shen (b0140) 2020 Zhu, Sun, Huang, Han, Zhang (b0135) 2021; 40 Camus, Payoux, Barré, Desgranges, Voisin, Tauber, La Joie, Tafani, Hommet, Chételat (b0050) 2012; 39 A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly. An image is worth 16x16 words: Transformers for image recognition at scale (2020). 10.1016/j.bspc.2023.105189_b0165 DeTure (10.1016/j.bspc.2023.105189_b0210) 2019; 14 10.1016/j.bspc.2023.105189_b0240 10.1016/j.bspc.2023.105189_b0040 Hosseini-Asl (10.1016/j.bspc.2023.105189_b0080) 2016; 2016 Vemuri (10.1016/j.bspc.2023.105189_b0045) 2012; 4 Jack (10.1016/j.bspc.2023.105189_b0190) 2008; 27 Jagust (10.1016/j.bspc.2023.105189_b0015) 2013; 77 Zhang (10.1016/j.bspc.2023.105189_b0200) 2021; 18 Han (10.1016/j.bspc.2023.105189_b0245) 2022; 67 Wen (10.1016/j.bspc.2023.105189_b0115) 2020; 63 Khan (10.1016/j.bspc.2023.105189_b0255) 2021; 184 10.1016/j.bspc.2023.105189_b0035 Raffel (10.1016/j.bspc.2023.105189_b0220) 2020; 21 Zhu (10.1016/j.bspc.2023.105189_b0135) 2021; 40 10.1016/j.bspc.2023.105189_b0155 10.1016/j.bspc.2023.105189_b0195 Kang (10.1016/j.bspc.2023.105189_b0130) 2021; 136 Atri (10.1016/j.bspc.2023.105189_b0020) 2019; 39 10.1016/j.bspc.2023.105189_b0235 Khan (10.1016/j.bspc.2023.105189_b0230) 2021; 70 Khan (10.1016/j.bspc.2023.105189_b0030) 2022; 73 Gao (10.1016/j.bspc.2023.105189_b0085) 2017; 138 10.1016/j.bspc.2023.105189_b0160 10.1016/j.bspc.2023.105189_b0025 Maggipinto (10.1016/j.bspc.2023.105189_b0065) 2017; 62 10.1016/j.bspc.2023.105189_b0100 10.1016/j.bspc.2023.105189_b0185 Xiao (10.1016/j.bspc.2023.105189_b0215) 2021; 34 Xu (10.1016/j.bspc.2023.105189_b0170) 2015 Qiu (10.1016/j.bspc.2023.105189_b0205) 2020; 143 Abraham (10.1016/j.bspc.2023.105189_b0105) 2014; 14 Nir (10.1016/j.bspc.2023.105189_b0060) 2013; 3 10.1016/j.bspc.2023.105189_b0225 Mwangi (10.1016/j.bspc.2023.105189_b0110) 2014; 12 LeCun (10.1016/j.bspc.2023.105189_b0095) 2015; 521 Mendoza-Léon (10.1016/j.bspc.2023.105189_b0125) 2020; 116 Hon (10.1016/j.bspc.2023.105189_b0120) 2017 Hedayati (10.1016/j.bspc.2023.105189_b0145) 2021; 66 Krizhevsky (10.1016/j.bspc.2023.105189_b0150) 2017; 60 Camus (10.1016/j.bspc.2023.105189_b0050) 2012; 39 10.1016/j.bspc.2023.105189_b0010 10.1016/j.bspc.2023.105189_b0175 10.1016/j.bspc.2023.105189_b0250 Rathore (10.1016/j.bspc.2023.105189_b0075) 2017; 155 Lian (10.1016/j.bspc.2023.105189_b0140) 2020 Roberson (10.1016/j.bspc.2023.105189_b0005) 2006; 314 Marcus (10.1016/j.bspc.2023.105189_b0055) 2014; 39 Khojaste-Sarakhsi (10.1016/j.bspc.2023.105189_b0090) 2022; 102332 Leandrou (10.1016/j.bspc.2023.105189_b0070) 2018; 11 10.1016/j.bspc.2023.105189_b0180 |
| References_xml | – reference: . https://doi.org/10.48550/arXiv.1602.02225. – reference: (2022), 1-5. https://doi.org/10.1109/ISBI52829.2022.9761549. – volume: 77 start-page: 219 year: 2013 end-page: 234 ident: b0015 article-title: Vulnerable neural systems and the borderland of brain aging and neurodegeneration publication-title: Neuron – reference: K. Han, Y. Wang, Q. Tian, J. Guo, C. Xu, C. Xu. Ghostnet: More features from cheap operations. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (2020). – volume: 184 year: 2021 ident: b0255 article-title: Automated classification of lung sound signals based on empirical mode decomposition publication-title: Expert Syst. Appl. – reference: K. He, X. Zhang, S. Ren, J. Sun. Deep residual learning for image recognition. – volume: 70 year: 2021 ident: b0230 article-title: Derived vectorcardiogram based automated detection of posterior myocardial infarction using FBSE-EWT technique [Article] publication-title: Biomed. Signal Process. Control – volume: 314 start-page: 781 year: 2006 end-page: 784 ident: b0005 article-title: 100 years and counting: prospects for defeating Alzheimer's disease publication-title: Science – volume: 136 year: 2021 ident: b0130 article-title: Multi-model and multi-slice ensemble learning architecture based on 2D convolutional neural networks for Alzheimer's disease diagnosis publication-title: Comput. Biol. Med. – volume: 63 year: 2020 ident: b0115 article-title: Convolutional neural networks for classification of Alzheimer's disease: Overview and reproducible evaluation publication-title: Med. Image Anal. – volume: 67 year: 2022 ident: b0245 article-title: Multi-task multi-level feature adversarial network for joint Alzheimer’s disease diagnosis and atrophy localization using sMRI publication-title: Phys. Med. Biol. – volume: 143 start-page: 1920 year: 2020 end-page: 1933 ident: b0205 article-title: Development and validation of an interpretable deep learning framework for Alzheimer’s disease classification publication-title: Brain – volume: 14 start-page: 1 year: 2019 end-page: 18 ident: b0210 article-title: The neuropathological diagnosis of Alzheimer’s disease publication-title: Mol. Neurodegener. – volume: 155 start-page: 530 year: 2017 end-page: 548 ident: b0075 article-title: A review on neuroimaging-based classification studies and associated feature extraction methods for Alzheimer's disease and its prodromal stages publication-title: Neuroimage – volume: 521 start-page: 436 year: 2015 end-page: 444 ident: b0095 article-title: Deep learning publication-title: Nature – reference: G. Huang, Z. Liu, L. Van Der Maaten, K.Q. Weinberger. Densely connected convolutional networks. – volume: 39 start-page: 227 year: 2019 end-page: 240 ident: b0020 article-title: Current and future treatments in Alzheimer's disease publication-title: Semin. Neurol. – reference: S. Mehta, M. Rastegari. Separable Self-attention for Mobile Vision Transformers (2022). – reference: K.A. Ellis, C.C. Rowe, V.L. Villemagne, R.N. Martins, C.L. Masters, O. Salvado, C. Szoeke, D. Ames, Group, A. R. Addressing population aging and Alzheimer's disease through the Australian Imaging Biomarkers and Lifestyle study: Collaboration with the Alzheimer's Disease Neuroimaging Initiative. – volume: 34 start-page: 30392 year: 2021 end-page: 30400 ident: b0215 article-title: Early convolutions help transformers see better publication-title: Adv. Neural Inf. Proces. Syst. – year: 2020 ident: b0140 article-title: Attention-guided hybrid network for dementia diagnosis with structural MR images publication-title: IEEE Trans. Cybern. – start-page: 2048 year: 2015 end-page: 2057 ident: b0170 article-title: Show, attend and tell: Neural image caption generation with visual attention publication-title: International conference on machine learning – year: 2017 ident: b0120 article-title: Towards Alzheimer's disease classification through transfer learning publication-title: 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) – volume: 40 start-page: 2354 year: 2021 end-page: 2366 ident: b0135 article-title: Dual attention multi-instance deep learning for Alzheimer’s disease diagnosis with structural MRI publication-title: IEEE Trans. Med. Imaging – reference: (2018), 7132-7141. https://doi.org/10.1109/TPAMI.2019.2913372. – volume: 27 start-page: 685 year: 2008 end-page: 691 ident: b0190 article-title: The Alzheimer's disease neuroimaging initiative (ADNI): MRI methods publication-title: Journal of Magnetic Resonance Imaging: An Official Journal of the International Society for Magnetic Resonance in Medicine – volume: 73 year: 2022 ident: b0030 article-title: Automated classification of valvular heart diseases using FBSE-EWT and PSR based geometrical features publication-title: Biomed. Signal Process. Control – reference: (2016), 770-778. – volume: 138 start-page: 49 year: 2017 end-page: 56 ident: b0085 article-title: Classification of CT brain images based on deep learning networks publication-title: Comput. Methods Programs Biomed. – reference: Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, B. Guo. Swin transformer: Hierarchical vision transformer using shifted windows. – reference: . https://doi.org/10.48550/arXiv.2006.04768. – reference: . https://doi.org/10.48550/arXiv.2206.02680. – reference: S.I. Khan, R.B. Pachori. Empirical Wavelet Transform-Based Framework for Diagnosis of Epilepsy Using EEG Signals. (2022). In R. K. Chaurasiya, D. Agrawal, & R. B. Pachori (Eds.), AI-Enabled Smart Healthcare Using Biomedical Signals (pp. 217-239). IGI Global. https://doi.org/10.4018/978-1-6684-3947-0.ch012. – reference: A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly. An image is worth 16x16 words: Transformers for image recognition at scale (2020). – reference: . https://doi.org/10.48550/arXiv.1704.04861. – volume: 21 start-page: 1 year: 2020 end-page: 67 ident: b0220 article-title: Exploring the limits of transfer learning with a unified text-to-text transformer publication-title: J. Mach. Learn. Res. – volume: 14 year: 2014 ident: b0105 article-title: Machine learning for neuroimaging with scikit-learn publication-title: Front. Neuroinf. – reference: (2018), 3588–3597. https://doi.org/10.1109/CVPR.2018.00378. – volume: 3 start-page: 180 year: 2013 end-page: 195 ident: b0060 article-title: Effectiveness of regional DTI measures in distinguishing Alzheimer's disease, MCI, and normal aging publication-title: NeuroImage: clinical – volume: 116 year: 2020 ident: b0125 article-title: Single-slice Alzheimer's disease classification and disease regional analysis with Supervised Switching Autoencoders publication-title: Comput. Biol. Med. – reference: , – reference: J. Hu, L. Shen, G. Sun. Squeeze-and-excitation networks. – reference: S. Sarraf, J. Sun. Functional brain imaging: A comprehensive survey (2016). – volume: 62 start-page: 2361 year: 2017 ident: b0065 article-title: DTI measurements for Alzheimer’s classification publication-title: Phys. Med. Biol. – reference: Alzheimer's disease facts and figures. (2020). – reference: . https://doi.org/10.48550/arXiv.2010.11929. – reference: . https://doi.org/10.1002/alz.12068. – reference: H. Hu, J. Gu, Z. Zhang, J. Dai, Y. Wei. Relation networks for object detection. – volume: 18 year: 2021 ident: b0200 article-title: A whole-process interpretable and multi-modal deep reinforcement learning for diagnosis and analysis of Alzheimer’s disease∗ publication-title: J. Neural Eng. – reference: (3),(2010), 291-296. https://doi.org/10.1016/j.jalz.2010.03.009. – reference: S.I. Khan, R.B. Pachori. Automated Eye Movement Classification Based on EMG of EOM Signals Using FBSE-EWT Technique. Ieee Transactions on Human-Machine Systems. https://doi.org/10.1109/thms.2023.3238113. – volume: 39 start-page: e413 year: 2014 ident: b0055 article-title: Brain PET in the diagnosis of Alzheimer’s disease publication-title: Clin. Nucl. Med. – volume: 11 start-page: 97 year: 2018 end-page: 111 ident: b0070 article-title: Quantitative MRI brain studies in mild cognitive impairment and Alzheimer's disease: A methodological review publication-title: IEEE Rev. Biomed. Eng. – volume: 12 start-page: 229 year: 2014 end-page: 244 ident: b0110 article-title: A review of feature reduction techniques in neuroimaging publication-title: Neuroinformatics – volume: 66 year: 2021 ident: b0145 article-title: Deep feature extraction method based on ensemble of convolutional auto encoders: Application to Alzheimer’s disease diagnosis publication-title: Biomed. Signal Process. Control – reference: , 4700-4708 (2017). https://doi.org/10.1109/CVPR.2017.243. – volume: 2016 start-page: 126 year: 2016 end-page: 130 ident: b0080 article-title: Alzheimer's disease diagnostics by adaptation of 3D convolutional network publication-title: IEEE international conference on image processing (ICIP) – reference: A.G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, H. Adam. Mobilenets: Efficient convolutional neural networks for mobile vision applications (2017). – volume: 4 start-page: 1 year: 2012 end-page: 9 ident: b0045 article-title: Resting state functional MRI in Alzheimer's Disease publication-title: Alzheimers Res. Ther. – volume: 39 start-page: 621 year: 2012 end-page: 631 ident: b0050 article-title: Using PET with 18F-AV-45 (florbetapir) to quantify brain amyloid load in a clinical environment publication-title: Eur. J. Nucl. Med. Mol. Imag. – volume: 102332 year: 2022 ident: b0090 article-title: Deep learning for Alzheimer's disease diagnosis: A survey publication-title: Artif. Intell. Med. – volume: 60 start-page: 84 year: 2017 end-page: 90 ident: b0150 article-title: Imagenet classification with deep convolutional neural networks publication-title: Commun. ACM – reference: (2021), 10012-10022. https://doi.org/10.48550/arXiv.2103.14030. – reference: C. Li, Y. Cui, N. Luo, Y. Liu, P. Bourgeat, J. Fripp, T. Jiang. Trans-ResNet: Integrating Transformers and CNNs for Alzheimer’s disease classification. – reference: S. Wang, B.Z. Li, M. Khabsa, H. Fang, H. Ma. Linformer: Self-attention with linear complexity (2020). – volume: 138 start-page: 49 year: 2017 ident: 10.1016/j.bspc.2023.105189_b0085 article-title: Classification of CT brain images based on deep learning networks publication-title: Comput. Methods Programs Biomed. doi: 10.1016/j.cmpb.2016.10.007 – ident: 10.1016/j.bspc.2023.105189_b0250 doi: 10.1109/ISBI52829.2022.9761549 – volume: 14 year: 2014 ident: 10.1016/j.bspc.2023.105189_b0105 article-title: Machine learning for neuroimaging with scikit-learn publication-title: Front. Neuroinf. – volume: 116 year: 2020 ident: 10.1016/j.bspc.2023.105189_b0125 article-title: Single-slice Alzheimer's disease classification and disease regional analysis with Supervised Switching Autoencoders publication-title: Comput. Biol. Med. doi: 10.1016/j.compbiomed.2019.103527 – volume: 14 start-page: 1 issue: 1 year: 2019 ident: 10.1016/j.bspc.2023.105189_b0210 article-title: The neuropathological diagnosis of Alzheimer’s disease publication-title: Mol. Neurodegener. doi: 10.1186/s13024-019-0333-5 – ident: 10.1016/j.bspc.2023.105189_b0100 – volume: 60 start-page: 84 issue: 6 year: 2017 ident: 10.1016/j.bspc.2023.105189_b0150 article-title: Imagenet classification with deep convolutional neural networks publication-title: Commun. ACM doi: 10.1145/3065386 – ident: 10.1016/j.bspc.2023.105189_b0185 – ident: 10.1016/j.bspc.2023.105189_b0025 doi: 10.1109/THMS.2023.3238113 – volume: 39 start-page: e413 issue: 10 year: 2014 ident: 10.1016/j.bspc.2023.105189_b0055 article-title: Brain PET in the diagnosis of Alzheimer’s disease publication-title: Clin. Nucl. Med. doi: 10.1097/RLU.0000000000000547 – volume: 155 start-page: 530 year: 2017 ident: 10.1016/j.bspc.2023.105189_b0075 article-title: A review on neuroimaging-based classification studies and associated feature extraction methods for Alzheimer's disease and its prodromal stages publication-title: Neuroimage doi: 10.1016/j.neuroimage.2017.03.057 – volume: 66 year: 2021 ident: 10.1016/j.bspc.2023.105189_b0145 article-title: Deep feature extraction method based on ensemble of convolutional auto encoders: Application to Alzheimer’s disease diagnosis publication-title: Biomed. Signal Process. Control doi: 10.1016/j.bspc.2020.102397 – volume: 39 start-page: 227 issue: 02 year: 2019 ident: 10.1016/j.bspc.2023.105189_b0020 article-title: Current and future treatments in Alzheimer's disease publication-title: Semin. Neurol. doi: 10.1055/s-0039-1678581 – year: 2017 ident: 10.1016/j.bspc.2023.105189_b0120 article-title: Towards Alzheimer's disease classification through transfer learning – ident: 10.1016/j.bspc.2023.105189_b0160 doi: 10.1109/CVPR.2017.243 – volume: 184 year: 2021 ident: 10.1016/j.bspc.2023.105189_b0255 article-title: Automated classification of lung sound signals based on empirical mode decomposition publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2021.115456 – volume: 73 year: 2022 ident: 10.1016/j.bspc.2023.105189_b0030 article-title: Automated classification of valvular heart diseases using FBSE-EWT and PSR based geometrical features publication-title: Biomed. Signal Process. Control doi: 10.1016/j.bspc.2021.103445 – ident: 10.1016/j.bspc.2023.105189_b0040 – ident: 10.1016/j.bspc.2023.105189_b0180 – ident: 10.1016/j.bspc.2023.105189_b0235 doi: 10.1109/CVPR.2016.90 – volume: 11 start-page: 97 year: 2018 ident: 10.1016/j.bspc.2023.105189_b0070 article-title: Quantitative MRI brain studies in mild cognitive impairment and Alzheimer's disease: A methodological review publication-title: IEEE Rev. Biomed. Eng. doi: 10.1109/RBME.2018.2796598 – volume: 77 start-page: 219 issue: 2 year: 2013 ident: 10.1016/j.bspc.2023.105189_b0015 article-title: Vulnerable neural systems and the borderland of brain aging and neurodegeneration publication-title: Neuron doi: 10.1016/j.neuron.2013.01.002 – volume: 34 start-page: 30392 year: 2021 ident: 10.1016/j.bspc.2023.105189_b0215 article-title: Early convolutions help transformers see better publication-title: Adv. Neural Inf. Proces. Syst. – volume: 12 start-page: 229 issue: 2 year: 2014 ident: 10.1016/j.bspc.2023.105189_b0110 article-title: A review of feature reduction techniques in neuroimaging publication-title: Neuroinformatics doi: 10.1007/s12021-013-9204-3 – ident: 10.1016/j.bspc.2023.105189_b0195 doi: 10.1016/j.jalz.2010.03.009 – ident: 10.1016/j.bspc.2023.105189_b0010 doi: 10.1002/alz.12068 – volume: 521 start-page: 436 issue: 7553 year: 2015 ident: 10.1016/j.bspc.2023.105189_b0095 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539 – volume: 40 start-page: 2354 issue: 9 year: 2021 ident: 10.1016/j.bspc.2023.105189_b0135 article-title: Dual attention multi-instance deep learning for Alzheimer’s disease diagnosis with structural MRI publication-title: IEEE Trans. Med. Imaging doi: 10.1109/TMI.2021.3077079 – volume: 63 year: 2020 ident: 10.1016/j.bspc.2023.105189_b0115 article-title: Convolutional neural networks for classification of Alzheimer's disease: Overview and reproducible evaluation publication-title: Med. Image Anal. doi: 10.1016/j.media.2020.101694 – ident: 10.1016/j.bspc.2023.105189_b0035 doi: 10.4018/978-1-6684-3947-0.ch012 – volume: 67 issue: 8 year: 2022 ident: 10.1016/j.bspc.2023.105189_b0245 article-title: Multi-task multi-level feature adversarial network for joint Alzheimer’s disease diagnosis and atrophy localization using sMRI publication-title: Phys. Med. Biol. doi: 10.1088/1361-6560/ac5ed5 – volume: 314 start-page: 781 issue: 5800 year: 2006 ident: 10.1016/j.bspc.2023.105189_b0005 article-title: 100 years and counting: prospects for defeating Alzheimer's disease publication-title: Science doi: 10.1126/science.1132813 – volume: 21 start-page: 1 issue: 140 year: 2020 ident: 10.1016/j.bspc.2023.105189_b0220 article-title: Exploring the limits of transfer learning with a unified text-to-text transformer publication-title: J. Mach. Learn. Res. – volume: 27 start-page: 685 issue: 4 year: 2008 ident: 10.1016/j.bspc.2023.105189_b0190 article-title: The Alzheimer's disease neuroimaging initiative (ADNI): MRI methods publication-title: Journal of Magnetic Resonance Imaging: An Official Journal of the International Society for Magnetic Resonance in Medicine doi: 10.1002/jmri.21049 – volume: 143 start-page: 1920 issue: 6 year: 2020 ident: 10.1016/j.bspc.2023.105189_b0205 article-title: Development and validation of an interpretable deep learning framework for Alzheimer’s disease classification publication-title: Brain doi: 10.1093/brain/awaa137 – ident: 10.1016/j.bspc.2023.105189_b0225 doi: 10.1109/CVPR.2018.00378 – volume: 70 year: 2021 ident: 10.1016/j.bspc.2023.105189_b0230 article-title: Derived vectorcardiogram based automated detection of posterior myocardial infarction using FBSE-EWT technique [Article] publication-title: Biomed. Signal Process. Control doi: 10.1016/j.bspc.2021.103051 – volume: 102332 year: 2022 ident: 10.1016/j.bspc.2023.105189_b0090 article-title: Deep learning for Alzheimer's disease diagnosis: A survey publication-title: Artif. Intell. Med. – ident: 10.1016/j.bspc.2023.105189_b0155 – volume: 39 start-page: 621 issue: 4 year: 2012 ident: 10.1016/j.bspc.2023.105189_b0050 article-title: Using PET with 18F-AV-45 (florbetapir) to quantify brain amyloid load in a clinical environment publication-title: Eur. J. Nucl. Med. Mol. Imag. doi: 10.1007/s00259-011-2021-8 – ident: 10.1016/j.bspc.2023.105189_b0240 doi: 10.1109/CVPR.2018.00745 – volume: 18 issue: 6 year: 2021 ident: 10.1016/j.bspc.2023.105189_b0200 article-title: A whole-process interpretable and multi-modal deep reinforcement learning for diagnosis and analysis of Alzheimer’s disease∗ publication-title: J. Neural Eng. doi: 10.1088/1741-2552/ac37cc – ident: 10.1016/j.bspc.2023.105189_b0165 doi: 10.1109/CVPR42600.2020.00165 – year: 2020 ident: 10.1016/j.bspc.2023.105189_b0140 article-title: Attention-guided hybrid network for dementia diagnosis with structural MR images publication-title: IEEE Trans. Cybern. – volume: 62 start-page: 2361 issue: 6 year: 2017 ident: 10.1016/j.bspc.2023.105189_b0065 article-title: DTI measurements for Alzheimer’s classification publication-title: Phys. Med. Biol. doi: 10.1088/1361-6560/aa5dbe – volume: 136 year: 2021 ident: 10.1016/j.bspc.2023.105189_b0130 article-title: Multi-model and multi-slice ensemble learning architecture based on 2D convolutional neural networks for Alzheimer's disease diagnosis publication-title: Comput. Biol. Med. doi: 10.1016/j.compbiomed.2021.104678 – start-page: 2048 year: 2015 ident: 10.1016/j.bspc.2023.105189_b0170 article-title: Show, attend and tell: Neural image caption generation with visual attention publication-title: International conference on machine learning – ident: 10.1016/j.bspc.2023.105189_b0175 doi: 10.1109/ICCV48922.2021.00986 – volume: 3 start-page: 180 year: 2013 ident: 10.1016/j.bspc.2023.105189_b0060 article-title: Effectiveness of regional DTI measures in distinguishing Alzheimer's disease, MCI, and normal aging publication-title: NeuroImage: clinical doi: 10.1016/j.nicl.2013.07.006 – volume: 2016 start-page: 126 year: 2016 ident: 10.1016/j.bspc.2023.105189_b0080 article-title: Alzheimer's disease diagnostics by adaptation of 3D convolutional network publication-title: IEEE international conference on image processing (ICIP) – volume: 4 start-page: 1 issue: 1 year: 2012 ident: 10.1016/j.bspc.2023.105189_b0045 article-title: Resting state functional MRI in Alzheimer's Disease publication-title: Alzheimers Res. Ther. doi: 10.1186/alzrt100 |
| SSID | ssj0048714 |
| Score | 2.453796 |
| Snippet | •Extracting features by combining CNN and swin-transformer.•Lightweight method didn’t degenerate the model with our 2.5D and 2-stream method.•Performance is... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 105189 |
| SubjectTerms | Alzheimer’s disease Computational complexity Deep learning Image classification Magnetic resonance imaging |
| Title | CNN and swin-transformer based efficient model for Alzheimer’s disease diagnosis with sMRI |
| URI | https://dx.doi.org/10.1016/j.bspc.2023.105189 |
| Volume | 86 |
| WOSCitedRecordID | wos001038041200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: ScienceDirect database customDbUrl: eissn: 1746-8108 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0048714 issn: 1746-8094 databaseCode: AIEXJ dateStart: 20060101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELaWlgMcEE_R8pAP3KpUeW0cH1dVgaKyQlVBe0CKHNuBVKuw2uy2FScu_Aj-Hr-EGb-6XaCiBy7Ryus4UebTzHj8zQwhLzKma1EXRZQUQkc5kwWSANKIs7jJmzxhtWETfjhk43E5mfB3g8F3nwtzOmVdV56f89l_FTWMgbAxdfYa4g6LwgD8BqHDFcQO138S_N54bE4E-rO2ixbeL9XzHTRYCgkcrUmCtE1wDM1wNP36WbfYR8VRH3jvT24wOItcvNalwfVvjw4uHQSb9H2bW9l-Qtd2ZlMPfPKj48J7wU5c9y_MJ3dG04TzrcoZdTA9jL5amjju0bL1I4ft0pACddtoN89FLNIsULK8kmU5FkG2zY29Fi5X1Sg4fYntLPSbhrfBhpPdup9hBco0272YfLmc9pqZC-RDz2s7qXCNCteo7Bo3yGbKhhyU4-boYH_yxpt02NSZIvHhxV32lSUKrr_Jnz2cFa_l-C6547YbdGRhco8MdHef3F4pQvmAfATAUJAUXQcMNYChATDUAIbCnzQA5ue3Hz11UKEBKhShQhEqD8n7l_vHe68j13MjklkcLyKGPqVqagGKnouilrIQCReCqUSVsqgbrZphzrgGg51ojBsKBVsIrso6ZlqW2SOy0X3p9GNChcrSrEmRBZTlucxLpXjcDEupcc_K4y2S-O9USVeQHvuiTKu_S2iL7IR7ZrYcy5Wzh_7zV86htI5iBWi64r7taz3lCbl1gfKnZGMxX-pn5KY8XbT9_LmD0i8wF5eW |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=CNN+and+swin-transformer+based+efficient+model+for+Alzheimer%E2%80%99s+disease+diagnosis+with+sMRI&rft.jtitle=Biomedical+signal+processing+and+control&rft.au=Xin%2C+Jiaming&rft.au=Wang%2C+Ancong&rft.au=Guo%2C+Rui&rft.au=Liu%2C+Weifeng&rft.date=2023-09-01&rft.issn=1746-8094&rft.volume=86&rft.spage=105189&rft_id=info:doi/10.1016%2Fj.bspc.2023.105189&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_bspc_2023_105189 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1746-8094&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1746-8094&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1746-8094&client=summon |