Alzheimer Hastalığının Teşhisinde Görüntü Dönüştürücü (Vision Transformer) Yaklaşımı: Yenilikçi Bir İnceleme

Year 2024, Volume: 36 Issue: 2, 609 - 619, 30.09.2024

Mehmet Emre Sertkaya , Burhan Ergen

https://doi.org/10.35234/fumbd.1411320

Abstract

Nörodejeneratif bir hastalık olan Alzheimer hastalığı, Demans’ın en yaygın türüdür. Şu an için kesin bir tedavisi bulunmayan bu hastalığın ilerlemesini yavaşlatıcı tedavi yöntemleri uygulanmaktadır. Bu nedenle, hastalığın erken teşhisi ve diğer hastalıklarla karıştırılmaması kritik öneme sahiptir. Bu çalışmada, Alzheimer's Disease Neuroimaging Initiative (ADNI) tarafından toplanan üç boyutlu MR görüntüleri kullanılarak Görüntü Dönüştürücü yöntemleriyle Alzheimer hastalığının tespit edilmesi amaçlanmaktadır. Alzheimer hastaları (AD), Hafif Bilişsel Bozukluk (Mild Cognitive Impairment - MCI) ve sağlıklı bireylerden(Cognitive Normal - CN) oluşan bu veri seti, %70'i eğitim, %10'u doğrulama ve %20'si test veri setleri olarak ayrılmıştır. Literatürdeki çeşitli derin öğrenme yöntemlerinin yanı sıra yeni bir yaklaşım olan Görüntü Dönüştürücü (Vision Transformer) kullanılarak sınıflandırma yapılmıştır. Çalışma sonuçları, test görüntülerinde Görüntü Dönüştürücü'nün AD/MCI ikili sınıflandırmasında %79,8 başarı, MCI/CN ikili sınıflandırmasında %80,3 başarı ve AD/CN ikili sınıflandırmada %89,3 başarı elde ettiğini göstermektedir

Keywords

Alzheimer Hastalığı, Görüntü Dönüştürücü, Evrişimsel Ağlar, ADNI veri seti

Vision Transformer Approach in the Diagnosis of Alzheimer’s Disease: An Innovative Review

Abstract

Alzheimer’s disease, a neurodegenerative disease, is the most common type of Dementia. Currently, there is no definitive cure for this disease and treatment methods are applied to slow down the progression of this disease. Therefore, early diagnosis of the disease and prevention of confusion with other diseases is of critical importance. In this study, it is aimed to detect Alzheimer’s disease with Image Transform methods using three-dimensional MR images collected by the Alzheimer's Disease Neuroimaging Initiative (ADNI). This dataset, which consists of Alzheimer’s patients (AD), Mild Cognitive Impairment (MCI) and healthy individuals (Cognitive Normal (CN), is divided into 70% training, 10% validation and 20% test datasets. In addition to various deep learning methods in the literature, classification was performed using a new approach, Vision Transformer. The results of the study show that the Vision Transformer achieved 79.8% success in AD/MCI binary classification, 80.3% success in MCI/CN binary classification and 89.3% success in AD/CN binary classification.

Keywords

Alzheimer, Vision Transformer, Convolutional Networks, ADNI dataset.

References

• Lopez JAS, Gonzalez HM, Leger GC. Alzheimer’s disease. Handb Clin Neurol 2019; 167: 231-255.
• Scheltens P, De Strooper B, Kivipelto M, Holstege H, Chetelat G, Teunissen CE, Cummings J, van der Flier WM. Alzheimer’s disease. The Lancet 2021; 397(10284): 1577-1590.
• Karikari TK, Pascoal TA, Ashton NJ, Janelidze S, Benedet AL, Rodriguez JL, Chamoun M, Savard M, Kang MS, Therriault J, Schöll M, Masson C, Soucy JP, Höglund K, Brinkmalm G, Mattsson-Carlgren N, Palmqvist S, Gauthier S, Stomrud E, Rosa-Neto P, Hansson O, Blennow K, Zetterberg H. Blood phospho-tau in Alzheimer disease: analysis, interpretation, and clinical utility. Nat Rev Neurol 2022; 18(7): 400-418.
• Kivimäki M, Singh-Manoux A, Pentti J, Sabia S, Nyberg ST, Alfredsson L, Bjorner JB, Brunner EJ, Fransson EI, Goldberg M, Knutsson A, Koskenvuo M, Koskinen A, Kouvonen A, Kuula L, Oksanen T, Salo P, Shipley MJ, Stenholm S, Suominen S, Vahtera J, Väänänen A, Westerholm P, Zins M, Hamer M, Batty GD, Ferrie JE. Estimating Dementia Risk Using Multifactorial Prediction Models. JAMA Network Open 2023; 6(6): e2318132.
• Bilal M, Iqbal HMN, Barceló D. Nanomaterials for the treatment and diagnosis of Alzheimer’s disease: An overview. NanoImpact 2020; 20: 100251.
• Scharre DW. Preclinical, prodromal, and dementia stages of Alzheimer’s disease. Pract Neurol 2019; 15: 36-47.
• Odusami M, Maskeliūnas R, Damaševičius R. Pixel-Level Fusion Approach with Vision Transformer for Early Detection of Alzheimer’s Disease. Electronics 2023; 12(5): 1218.
• Fathi S, Ahmadi M, Dehnad A. Early diagnosis of Alzheimer’s disease based on deep learning: A systematic review. Comput Biol Med 2022; 146: 105634.
• Sarraf S, Tofighi G, D’Souza AM, Phillips JM, Javanmardi M. OViTAD: Optimized vision transformer to predict various stages of Alzheimer’s disease using resting-state fMRI and structural MRI data. Brain Sci 2023; 13(2): 260.
• Henschel L, Conjeti S, Estrada S, Diers K, Fischl B, Reuter M. Fastsurfer-a fast and accurate deep learning based neuroimaging pipeline. NeuroImage 2020; 219: 117012.
• Puranik M, Khadidos A, Talukder A, Mohammed MA, Abbas Z, Alsadoon A, Ali S, Kannan A. Intelligent Alzheimer’s detector using deep learning. In: 2018 Second International Conference on Intelligent Computing and Control Systems (ICICCS); 2018; IEEE.
• Ilias L, Askounis D. Explainable identification of dementia from transcripts using transformer networks. IEEE J Biomed Health Inf 2022; 26(8): 4153-4164.
• Jain V, Ha S, Jin K, Lee J, Jeong D. A novel AI-based system for detection and severity prediction of dementia using MRI. IEEE Access 2021; 9: 154324-154346.
• Zhang X, Wang F, Chen X, Jiang T. An explainable 3D residual self-attention deep neural network for joint atrophy localization and Alzheimer’s disease diagnosis using structural MRI. IEEE J Biomed Health Inf 2021; 26(11): 5289-5297.
• Oktavian MW, Yudistira N, Ridok A. Classification of Alzheimer’s Disease Using the Convolutional Neural Network (CNN) with Transfer Learning and Weighted Loss. arXiv preprint arXiv:2207.01584, 2022.
• Ma H, Xu G, Wang J, Zhao Z, Liu Y, Liu X. Classification of Alzheimer’s disease: application of a transfer learning deep Q‐network method. Eur J Neurosci 2024.
• Mujahid M, Khan MA, Hussain T, Ullah A, Shah JH, Naqvi SR, Balakrishnan V, Gwak J. An efficient ensemble approach for Alzheimer’s disease detection using an adaptive synthetic technique and deep learning. Diagnostics 2023; 13(15): 2489.
• Jack Jr CR, Bernstein MA, Fox NC, Thompson P, Alexander G, Harvey D, Borowski B, Britson PJ, Lainhart JE, Ward C, Dale AM. The Alzheimer’s disease neuroimaging initiative (ADNI): MRI methods. J Magn Reson Imaging 2008; 27(4): 685-691.
• Mueller SG, Weiner MW, Thal LJ, Petersen RC, Jack CR, Jagust W, Trojanowski JQ, Toga AW, Beckett L. The Alzheimer’s disease neuroimaging initiative. Neuroimaging Clin 2005; 15(4): 869-877.
• Petersen RC, Aisen PS, Beckett LA, Donohue M, Gamst AC, Harvey DJ, Jack CR, Jagust WJ, Shaw LM, Toga AW, Trojanowski JQ. Alzheimer’s disease neuroimaging initiative (ADNI): clinical characterization. Neurology 2010; 74(3): 201-209.
• Jiang J, Liu T, Xu X, Gao P, Fang Y. Deep learning based mild cognitive impairment diagnosis using structure MR images. Neurosci Lett 2020; 730: 134971.
• Lian C, Liu M, Zhang J, Shen D. Attention-guided hybrid network for dementia diagnosis with structural MR images. IEEE Trans Cybern 2020; 52(4): 1992-2003.
• Theckedath D, Sedamkar R. Detecting affect states using VGG16, ResNet50 and SE-ResNet50 networks. SN Comput Sci 2020; 1: 1-7.
• Yüzgeç E, Muhammed T. Alzheimer ve Parkinson Hastalıklarının Derin Öğrenme Teknikleri Kullanılarak Sınıflandırılması. Fırat Üniversitesi Mühendislik Bilimleri Dergisi 2023; 35(2): 473-482.
• Zoph B, Vasudevan V, Shlens J, Le QV. Learning transferable architectures for scalable image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2018.
• İlhan İ, Balı E, Karaköse M. An Improved DeepFake Detection Approach with NASNetLarge CNN. In: 2022 International Conference on Data Analytics for Business and Industry (ICDABI); 2022. IEEE.
• Pa WP, Nwe TL. Improving Myanmar Image Caption Generation Using NASNetLarge and Bi-directional LSTM. In: 2023 IEEE Conference on Computer Applications (ICCA); 2023. IEEE.
• Xu X, Li W, Duan Q. Transfer learning and SE-ResNet152 networks-based for small-scale unbalanced fish species identification. Comput Electron Agric 2021; 180: 105878.
• He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2016.
• Deepika D, Lakshmi AV. Identification of Breast Cancer Using RESNET152. In: 2022 Fourth International Conference on Cognitive Computing and Information Processing (CCIP); 2022. IEEE.
• Woo S, Kim DK, Lim J, Ghaffar A, Jang B, Han S, Choi J, Park J. Convnext v2: Co-designing and scaling convnets with masked autoencoders. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition; 2023.
• Zhou J, Zhou W, Wei W, Zhu Y. YOLO-CIR: The network based on YOLO and ConvNeXt for infrared object detection. Infrared Phys Technol 2023; 131: 104703.
• Zhang C, Feng C, Li Y, Lu C, Shi L, Wang H. Research on Rolling Bearing Fault Diagnosis Based on Digital Twin Data and Improved ConvNext. Sensors 2023; 23(11): 5334.
• Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł, Polosukhin I. Attention is all you need. Adv Neural Inf Process Syst 2017; 30.
• Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, Uszkoreit J, Houlsby N. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020.
• Touvron H, Cord M, Douze M, Massa F, Sablayrolles A, Jégou H. Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning; 2021. PMLR.
• Wang W, Xie E, Li X, Fan D, Song K, Liang D, Lu T, Luo P, Shao L. Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE/CVF International Conference on Computer Vision;2021.
• Chen CFR, Fan Q, Panda R. Crossvit: Cross-attention multi-scale vision transformer for image classification. In: Proceedings of the IEEE/CVF International Conference on Computer Vision; 2021.