NEURAL NETWORK MODELING TO DETERMINE THE STAGE OF ALZHEIMER'S DISEASE
Keywords:
recognition, classification, convolutional neural network, dementia, Alzheimer's disease, neural network architectureAbstract
Alzheimer's disease is the most common type of dementia, in which the human brain ceases to perform its functions properly. This disease causes problems with memory, thinking and behavior. The elderly are the most vulnerable to this disease and heredity plays a significant role - if it turns out that there have been cases of such a disease in the family, then the risk of getting sick is very high. Recently, with the breakthrough development and introduction of information technologies and machine learning methods, both in general and especially in medicine, early computer diagnostics of the disease, which uses artificial intelligence, namely neural networks, is gaining popularity. The main task of diagnosing the disease is to correctly determine the stage of the disease, based on the obtained brain images, which are issued by the magnetic resonance imaging device after examination of the patient, taking into account his previous anamnesis and complaints. In this paper, we consider a neural network model for studying the stages of Alzheimer's disease. The role of early diagnosis of the disease with the help of artificial intelligence, in particular neural networks, is considered. The main methods that were used in research to classify the disease were considered. Based on the analysis of literature sources, a convolutional neural network architecture was chosen, which showed greater recognition accuracy among other architectures. A mathematical model of a convolutional neural network was developed: the number of convolutional, fully connected layers, the number of filters in each layer, activation functions for each layer were selected, hyperparameters were also configured to improve the quality of recognition of Alzheimer's disease. The developed mathematical model will be the foundation for the application, which will facilitate the work of a doctor to assess the stage of Alzheimer's disease, will make it possible to make more accurate diagnoses, will reduce a certain burden when performing routine actions of a medical worker. The use of this mathematical model in combination with the developed software will speed up the establishment of the final diagnosis of the patient.
References
Knopman, David & Amieva, Helene & Petersen, Ronald & Chételat, Gäel & Holtzman, David & Hyman, Bradley & Nixon, Ralph & Jones, David. (2021). Alzheimer disease. Nature Reviews Disease Primers. 7. 10.1038/s41572-021-00269-y.
Martinc, Matej & Haider, Fasih & Pollak, Senja & Luz, Saturnino. (2021). Temporal Integration of Text Transcripts and Acoustic Features for Alzheimer's Diagnosis Based on Spontaneous Speech. Frontiers in Aging Neuroscience. 13. 10.3389/fnagi.2021.642647.
Chen, Xiaoxiao & Li, Linghui & Sharma, Ashutosh & Dhiman, Gaurav & Shanmuganthan, Vimal. (2021). The Application of Convolutional Neural Network Model in Diagnosis and Nursing of MR Imaging in Alzheimer's Disease. Interdisciplinary Sciences Computational Life Sciences. 3. 10.1007/s12539-021-00450-7.
Kumar, P & Yung, Yang & Huan, Tracy. (2017). Neural Network Based Decision Trees using Machine Learning for Alzheimer's Diagnosis. International Journal of Computer and Information Sciences. 4. 63-72.
Yiğit, Altuğ & Isik, Zerrin. (2018). Application of artificial neural networks in dementia and alzheimer's diagnosis. 1-4. 10.1109/SIU.2018.8404447.
Janghel, Rekh. (2020). Deep-Learning-Based Classification and Diagnosis of Alzheimer's Disease. 10.4018/978-1-7998-0414-7.ch076.
Chellam, C & Kumar, D & S., Raja. (2021). An automated eeg based pathology and alzheimer detection using deep learning networks. Journal of Engineering and Technology Management. IX. 3143.
Shankar, Dr & Lakshmanaprabu, S.K. & Khanna, Ashish & Tanwar, Sudeep & Rodrigues, Joel & Roy, Nihar. (2019). Alzheimer Detection Using Group Grey Wolf Optimization Based Features with Convolutional Classifier. Computers & Electrical Engineering. 77. 10.1016/j.compeleceng.2019.06.001.
Poirier, James & Tuttle, Michael. (2020). Artificial Neural Network to Detect Alzheimer's in MRI Scans.
Hogan, Ryan & Christoforou, Christoforos. (2021). Alzheimer's Detection through 3D Convolutional Neural Networks.
Ammar, Randa & Benayed, Yassine. (2020). Language-related features for early detection of Alzheimer Disease. Procedia Computer Science. 176. 763-770. 10.1016/j.procs.2020.09.071.
Patil, Adwait. (2021). A Comparative Study of Alzheimer Detection Techniques. International Journal for Research in Applied Science and Engineering Technology. 9. 2877-2883. 10.22214/ijraset.2021.37882.
Ashraf, Abida & Naz, Saeeda & Shirazi, Syed & Razzak, Imran & Parsad, Mukesh. (2021). Deep transfer learning for alzheimer neurological disorder detection. Multimedia Tools and Applications. 80. 10.1007/s11042-020-10331-8.
Salehi, Waleed & Baglat, Preety & Bhushan, Brij & Gupta, Gaurav & Upadhya, Ankita. (2020). A CNN Model: Earlier Diagnosis and Classification of Alzheimer Disease using MRI. 156 - 161. 10.1109/ICOSEC49089.2020.9215402.
Aggarwal, Shilpi & Bhatia, Madhulika & Madaan, Rosy & Pandey, Hari. (2021). Optimized Sequential model for Plant Recognition in Keras. IOP Conference Series: Materials Science and Engineering. 1022. 012118. 10.1088/1757-899X/1022/1/012118.
Ghiasi-Shirazi, Kamaledin. (2019). Generalizing the Convolution Operator in Convolutional Neural Networks. Neural Processing Letters. 10.1007/s11063-019-10043-7.
Płaczek, Stanisław & Płaczek, Aleksander. (2018). Learning algorithm analysis for deep neural network with ReLu activation functions. ITM Web of Conferences. 19. 01009. 10.1051/itmconf/20181901009.
