MR Görüntülerinden Alzheimer Hastalığının Sınıflandırılması için Inception ve Sıkma-Uyarma Ağı Tabanlı Derin Öğrenme Modeli

Yıl 2024, Cilt: 39 Sayı: 2, 555 – 567, 11.07.2024

Hüseyin Fırat , Hüseyin Üzen

https://doi.org/10.21605/cukurovaumfd.1514656

Öz

Alzheimer’s disease (AD) is a progressive brain disorder, the leading cause of dementia in older adults. Early identification is vital, as treatment is more effective in the disease’s initial stages. Deep learning techniques have proven to be effective in medical imaging, including AD detection. This study introduces a novel method for AD classification from MRI images, combining an Inception module and a squeeze-and-excitation block. The Inception module increases convolutional neural network accuracy by using multiple parallel convolutions at different scales. The squeeze-and-excitation block enhances performance with minimal added parameters. The experimental results on the four-class Kaggle dataset yielded an accuracy of 98.28%. Comparisons with recent studies in the literature clearly demonstrate the success of the proposed method in classifying AD with high accuracy. This approach holds promise for accurately classifying AD from medical images, enabling earlier diagnosis and intervention.

Anahtar Kelimeler

Inception module, Squeeze-and-excitation block, Alzheimer’s disease, Classification

Kaynakça

• 1. Dadar, M., Pascoal, T.A., Manitsirikul, S., 2017. Validation of a Regression Technique for Segmentation of White Matter Hyperintensities in Alzheimer’s Disease. IEEE Transactions on Medical Imaging, 36, 1758-1768.
• 2. Livingston, G., Sommerlad, A., Orgeta, V., 2017. Dementia Prevention, Intervention, and Care. Lancet, 390, 2673-2734.
• 3. Ahmed, G., Er, M.J., Muhammad, M., 2022. DAD-Net : Classification of Alzheimer’s Disease Using Neural Network. Molecules, 27, 1-21
• 4. Tufail, Bin A., Ma, Y.K., Zhang, Q.N., 2020 Binary Classification of Alzheimer’s Disease Using sMRI Imaging Modality and Deep Learning. Journal of Digital Imaging, 33, 1073-1090.
• 5. Tiwari, S., Venkata, A., Kaushik, A., 2019. Alzheimer’s Disease Diagnostics and Therapeutics Market. International Journal of Nanomedicine, 14, 5541-5554
• 6. Loddo, A., Buttau, S., Di Ruberto, C., 2022. Deep Learning Based Pipelines for Alzheimer’s Disease Diagnosis: A Comparative Study and a Novel Deep-ensemble Method. Computers in Biology and Medicine, 141, 105032.
• 7. El-Latif, A.A.A., Chelloug, S.A, Alabdulhafith, M., Hammad, M., 2023. Accurate Detection of Alzheimer’s Disease Using Lightweight Deep Learning Model on MRI Data. Diagnostics, 13, 1-21.
• 8. Bangyal, W.H., Rehman, N.U., Nawaz, A., 2022. Constructing Domain Ontology for Alzheimer Disease Using Deep Learning Based Approach. Electronics, 11.
• 9. Balasundaram, A., Srinivasan, S., Prasad, A., 2023. Hippocampus Segmentation-Based Alzheimer’s Disease Diagnosis and Classification of MRI Images. Arabian Journal for Science and Engineering, 48, 10249- 10265.
• 10. Mohammed, B.A., Senan, E.M., Rassem, T.H., 2021. Multi-method Analysis of Medical Records and Mri Images for Early Diagnosis of Dementia and Alzheimer’s Disease Based on Deep Learning and Hybrid Methods. Electronics, 10, 1-20.
• 11. Murugan, S., Venkatesan, C., Sumithra, M.G., 2021. DEMNET: A Deep Learning Model for Early Diagnosis of Alzheimer Diseases and Dementia from MR Images. IEEE Access, 9, 90319-90329.
• 12. Kumar, S., 2021. Alzheimer MRI Preprocessed Dataset. https://www.kaggle.com/datasets/ sachinkumar413/alzheimer-mri-dataset. Access date: 12 October 2023.
• 13. Fırat, H., Emin, M., Mehmet, A., Hanbay, D., 2022 Hybrid 3D/2D Complete Inception Module and Convolutional Neural Network for Hyperspectral Remote Sensing Image Classification. Neural Process Letters, 1-44.
• 14. Szegedy, C., Liu, W., Jia, Y., 2015. Going Deeper with Convolutions. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 1-9.
• 15. Hu, J., Shen, L., Sun, G., 2018. Squeeze-and-Excitation Networks. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognition, 7132-7141.
• 16. Fırat, H., 2023. Classification of White Blood Cells Using the Squeeze-Excitation Residual Network. Bilişim Teknolojileri Dergisi, 16, 189-205.
• 17. Asker, M.E., 2023. Hyperspectral Image Classification Method Based on Squeeze-and-Excitation Networks, Depthwise Separable Convolution and Multibranch Feature Fusion. Earth Science Informatics, 1427- 1448.

MR Görüntülerinden Alzheimer Hastalığının Sınıflandırılması için Inception ve Sıkma-Uyarma Ağı Tabanlı Derin Öğrenme Modeli

Yıl 2024, Cilt: 39 Sayı: 2, 555 – 567, 11.07.2024

Hüseyin Fırat , Hüseyin Üzen

https://doi.org/10.21605/cukurovaumfd.1514656

Öz

Alzheimer hastalığı (AH) ilerleyici bir beyin hastalığıdır ve yaşlı yetişkinlerde demansın önde gelen nedenidir. Hastalığın ilk aşamalarında tedavi daha etkili olduğu için erken teşhis hayati önem taşımaktadır. Derin öğrenme tekniklerinin, AH tespiti de dahil olmak üzere tıbbi görüntülemede etkili olduğu kanıtlanmıştır. Bu çalışmada, manyetik rezonans görüntüleme görüntülerinden AH sınıflandırması için bir Inception modülü ile bir sıkma ve uyarma bloğunu birleştiren yeni bir yöntem tanıtılmaktadır. Inception modülü, farklı ölçeklerde çoklu paralel evrişimler kullanarak evrişimsel sinir ağı doğruluğunu arttırmaktadır. Sıkma ve uyarma bloğu, minimum ek parametre ile performansı arttırmaktadır. Dört sınıflı Kaggle veri seti üzerindeki deneysel sonuçlar ile %98,28’lik bir doğruluk değeri elde edilmiştir. Literatürdeki son çalışmalarla yapılan karşılaştırmalar, önerilen yöntemin AH’yi yüksek doğrulukla sınıflandırmadaki başarısını açıkça göstermektedir. Bu yaklaşım, tıbbi görüntülerden AH’yi doğru bir şekilde sınıflandırarak daha erken teşhis ve müdahaleye olanak sağlama konusunda umut vaat etmektedir.

Anahtar Kelimeler

Inception modülü, Sıkma-uyarma bloğu, Alzheimer hastalığı, Sınıflandırma

Kaynakça

• 1. Dadar, M., Pascoal, T.A., Manitsirikul, S., 2017. Validation of a Regression Technique for Segmentation of White Matter Hyperintensities in Alzheimer’s Disease. IEEE Transactions on Medical Imaging, 36, 1758-1768.
• 2. Livingston, G., Sommerlad, A., Orgeta, V., 2017. Dementia Prevention, Intervention, and Care. Lancet, 390, 2673-2734.
• 3. Ahmed, G., Er, M.J., Muhammad, M., 2022. DAD-Net : Classification of Alzheimer’s Disease Using Neural Network. Molecules, 27, 1-21
• 4. Tufail, Bin A., Ma, Y.K., Zhang, Q.N., 2020 Binary Classification of Alzheimer’s Disease Using sMRI Imaging Modality and Deep Learning. Journal of Digital Imaging, 33, 1073-1090.
• 5. Tiwari, S., Venkata, A., Kaushik, A., 2019. Alzheimer’s Disease Diagnostics and Therapeutics Market. International Journal of Nanomedicine, 14, 5541-5554
• 6. Loddo, A., Buttau, S., Di Ruberto, C., 2022. Deep Learning Based Pipelines for Alzheimer’s Disease Diagnosis: A Comparative Study and a Novel Deep-ensemble Method. Computers in Biology and Medicine, 141, 105032.
• 7. El-Latif, A.A.A., Chelloug, S.A, Alabdulhafith, M., Hammad, M., 2023. Accurate Detection of Alzheimer’s Disease Using Lightweight Deep Learning Model on MRI Data. Diagnostics, 13, 1-21.
• 8. Bangyal, W.H., Rehman, N.U., Nawaz, A., 2022. Constructing Domain Ontology for Alzheimer Disease Using Deep Learning Based Approach. Electronics, 11.
• 9. Balasundaram, A., Srinivasan, S., Prasad, A., 2023. Hippocampus Segmentation-Based Alzheimer’s Disease Diagnosis and Classification of MRI Images. Arabian Journal for Science and Engineering, 48, 10249- 10265.
• 10. Mohammed, B.A., Senan, E.M., Rassem, T.H., 2021. Multi-method Analysis of Medical Records and Mri Images for Early Diagnosis of Dementia and Alzheimer’s Disease Based on Deep Learning and Hybrid Methods. Electronics, 10, 1-20.
• 11. Murugan, S., Venkatesan, C., Sumithra, M.G., 2021. DEMNET: A Deep Learning Model for Early Diagnosis of Alzheimer Diseases and Dementia from MR Images. IEEE Access, 9, 90319-90329.
• 12. Kumar, S., 2021. Alzheimer MRI Preprocessed Dataset. https://www.kaggle.com/datasets/ sachinkumar413/alzheimer-mri-dataset. Access date: 12 October 2023.
• 13. Fırat, H., Emin, M., Mehmet, A., Hanbay, D., 2022 Hybrid 3D/2D Complete Inception Module and Convolutional Neural Network for Hyperspectral Remote Sensing Image Classification. Neural Process Letters, 1-44.
• 14. Szegedy, C., Liu, W., Jia, Y., 2015. Going Deeper with Convolutions. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 1-9.
• 15. Hu, J., Shen, L., Sun, G., 2018. Squeeze-and-Excitation Networks. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognition, 7132-7141.
• 16. Fırat, H., 2023. Classification of White Blood Cells Using the Squeeze-Excitation Residual Network. Bilişim Teknolojileri Dergisi, 16, 189-205.
• 17. Asker, M.E., 2023. Hyperspectral Image Classification Method Based on Squeeze-and-Excitation Networks, Depthwise Separable Convolution and Multibranch Feature Fusion. Earth Science Informatics, 1427- 1448.

Toplam 17 adet kaynakça vardır.

Ayrıntılar

Kaynak Göster

Download or read online: Click here