3-D Image Based Deep Learning for Dementia Diagnosis

Authors

  • George Liu Johns Creek High School
  • Guillermo Goldsztein Georgia Institute of Technology

DOI:

https://doi.org/10.47611/jsrhs.v12i3.4569

Keywords:

Dementia, MRI, Diagnosis, Machine Learning, Neural Network, Convolutional

Abstract

Dementia is a neurodegenerative disorder that greatly affects memory, thinking, and reasoning, impacting millions of people worldwide. Although dementia diagnosis is challenging and time-consuming, recent studies have shown promising results in using deep learning for dementia diagnosis by analyzing MRI scans. However, these studies are limited by access to data and the depth of analysis. In this study, we developed a deep learning model that utilizes the T1-weighted MRI scans from the Open Access Series of Imaging Studies (OASIS-3) dataset, which contains data from 1378 patients with varying degrees of cognitive decline. The model classified MRI scans into two categories, negative or positive diagnosis of dementia, based on the patients' clinical dementia rating (CDR). A 3-D convolutional neural network (CNN) was constructed with the TensorFlow framework and achieved an accuracy of 76.25%. This study demonstrates the potential that deep learning models have in the future of dementia diagnosis.

Downloads

Download data is not yet available.

Author Biography

Guillermo Goldsztein, Georgia Institute of Technology

Professor Goldsztein is originally from Buenos Aires, Argentina. In 1992 he received his undergraduate degree in mathematics from the University of Buenos Aires and in 1997 a PhD in mathematics from MIT. During the three following years (1997-2000), he was a postdoctoral scholar and lecturer in applied mathematics at CalTech. Since 2000, he has been a faculty member of the School of Mathematics of Georgia Tech, where he is now a full professor. Professor Goldsztein enjoys applying mathematics that can be used in other other fields of science such as computational biology, machine learning, and the intersection between math and physics. Machine learning is among his areas of expertise.

References or Bibliography

Buvari, S., & Pettersson, K. (2020, June 23). A Comparison on Image, Numerical and Hybrid based Deep Learning for Computer-aided AD Diagnostics. Retrieved March 15, 2023, from https://www.diva-portal.org/smash/get/diva2:1463276/FULLTEXT01.pdf.

Chandra, A., Dervenoulas, G., & Politis, M. (2018, August 17). Magnetic Resonance Imaging in alzheimer's disease and mild cognitive impairment - journal of neurology. SpringerLink. Retrieved March 23, 2023, from https://link.springer.com/article/10.1007/s00415-018-9016-3.

Falahati, F., Westman, E., & Simmons, A. (2014). Multivariate data analysis and machine learning in Alzheimer's disease with a focus on structural magnetic resonance imaging. Journal of Alzheimer's disease: JAD, 41(3), 685–708. https://doi.org/10.3233/JAD-131928

Gill, S., Mouches, P., Hu, S., Rajashekar, D., MacMaster, F. P., Smith, E. E., Forkert, N. D., Ismail, Z., & Alzheimer’s Disease Neuroimaging Initiative (2020). Using Machine Learning to Predict Dementia from Neuropsychiatric Symptom and Neuroimaging Data. Journal of Alzheimer's disease : JAD, 75(1), 277–288. https://doi.org/10.3233/JAD-191169

Isensee, F., Schell, M., Pflueger, I., Brugnara, G., Bonekamp, D., Neuberger, U., Wick, A., Schlemmer, H. P., Heiland, S., Wick, W., Bendszus, M., Maier-Hein, K. H., & Kickingereder, P. (2019). Automated brain extraction of multisequence MRI using artificial neural networks. Human brain mapping, 40(17), 4952–4964. https://doi.org/10.1002/hbm.24750

Islam, J., & Zhang, Y. (2018). Brain MRI analysis for Alzheimer's disease diagnosis using an ensemble system of deep convolutional neural networks. Brain informatics, 5(2), 2. https://doi.org/10.1186/s40708-018-0080-3

Khan, T. K. (2016). Clinical dementia rating. Clinical Dementia Rating - an overview | ScienceDirect Topics. Retrieved March 15, 2023, from https://www.sciencedirect.com/topics/medicine-and-dentistry/clinical-dementia-rating#:~:text=The%20CDR%20is%20based%20on,impairment%20(CDR%20%3D%203)

LaMontagne, P. J., Benzinger, T. L. S., Morris, J. C., Keefe, S., Hornbeck, R., Xiong, C., Grant, E., Hassenstab, J., Moulder, K., Vlassenko, A. G., Raichle, M. E., Cruchaga, C., & Marcus, D. (2019, January 1). Oasis-3: Longitudinal neuroimaging, clinical, and cognitive dataset for normal aging and alzheimer disease. medRxiv. Retrieved March 18, 2023, from https://www.medrxiv.org/content/10.1101/2019.12.13.19014902v1.

Lang, N. (2022, October 24). Using convolutional neural network for Image Classification. Medium. Retrieved March 15, 2023, from https://towardsdatascience.com/using-convolutional-neural-network-for-image-classification-5997bfd0ede4#:~:text=The%20Convolutional%20Neural%20Network%20(CNN,suited%20for%20this%20use%20case.

Mayo Clinic. (2022, October 12). Dementia. Mayo Clinic. Retrieved March 17, 2023, from https://www.mayoclinic.org/diseases-conditions/dementia/diagnosis-treatment/drc-20352019.

NHS. (2021, April 8). Is there a cure for dementia? NHS choices. Retrieved March 16, 2023, from https://www.nhs.uk/conditions/dementia/cure/#:~:text=There%20is%20currently%20no%20%22cure,and%20dementia%20with%20Lewy%20bodies.

Stanford Medicine. (2017, September 11). Brain Scans. Stanford Health Care (SHC) - Stanford Medical Center. Retrieved March 23, 2023, from https://stanfordhealthcare.org/medical-conditions/brain-and-nerves/dementia/diagnosis/brain-scans.html.

Sun, X., Shi, L., Luo, Y., Yang, W., Li, H., Liang, P., Li, K., Mok, V. C. T., Chu, W. C. W., & Wang, D. (2015, July 28). Histogram-based normalization technique on human brain magnetic resonance images from different acquisitions - biomedical engineering online. BioMed Central. Retrieved April 3, 2023, from https://biomedical-engineering-online.biomedcentral.com/articles/10.1186/s12938-015-0064-y.

Wada-Isoe, K., Kikuchi, T., Umeda-Kameyama, Y., Mori, T., Akishita, M., Nakamura, Y., & ABC Dementia Scale Research Group (2019). Global Clinical Dementia Rating Score of 0.5 May Not Be an Accurate Criterion to Identify Individuals with Mild Cognitive Impairment. Journal of Alzheimer's disease reports, 3(1), 233–239. https://doi.org/10.3233/ADR-190126

World Health Organization. (2023, March 15). Dementia. World Health Organization. Retrieved March 21, 2023, from https://www.who.int/news-room/fact-sheets/detail/dementia.

Yagis, E., Citi, L., Diciotti, S., Merzi, C., Workalemahu Atnafu, S., & Garcia Seco De Herrera, A. (2020, July 1). 3D convolutional neural networks for diagnosis of alzheimer's disease via structural MRI. Research Repository. Retrieved March 25, 2023, from https://repository.essex.ac.uk/27801/

Zunair, H., Rahman, A., Mohammed, N., & Cohen, J. P. (2020, July 26). Uniformizing techniques to process CT scans with 3D CNNS for tuberculosis prediction. arXiv.org. Retrieved March 22, 2023, from https://arxiv.org/abs/2007.13224.

Published

08-31-2023

How to Cite

Liu, G., & Goldsztein, G. (2023). 3-D Image Based Deep Learning for Dementia Diagnosis. Journal of Student Research, 12(3). https://doi.org/10.47611/jsrhs.v12i3.4569

Issue

Section

HS Research Projects