Using a Convolutional Neural Network to Classify the Progression of Alzheimer's Patients MRI's.
CSEF · 2023 Cognitive Science Second Award
Overview
Alzheimer's is the most widespread type of dementia with over 10 million new cases diagnosed yearly. Despite such impact, 20% of very mild, mild, and moderate Alzheimer’s cases are misclassified leading to the progression of the disease. My science fair project is to use a neural network Deep Learning model to more accurately classify these levels of Alzhimers using the patients’ MRI scans. I was aiming for an accuracy of 90-95% compared to the 80% accuracy of the current methods of manually analyzing a skills test. Additionally, the time for accurate detection can be reduced to mere hours, compared to the days and weeks that the current process takes. I spent the majority of my time researching the disease, and the current human and ML methods being applied for diagnosis. I also had to find multiple labeled data for classification.I used a Kaggle dataset posted by Dr.Sourab Shastri and a seed code by Ken Constable, a programmer on Kaggle. My model prediction hit 97% accuracy and 98% precision. The accuracy climbed from an initial 40% with techniques such as combining the rescaling/reformatting of the images, converting the images to color, adding a dropout layer, minimizing the learning rate, and setting the batch and image size in separate runs for the test. In summary, I was able to classify the three most misdiagnosed stages of Alzheimer's accurately and efficiently. Doctors can use this program to receive fast and accurate detection to enable early mitigation.
Source coverage
This record comes from a published award list, not a complete project archive. Its abstract comes from CSEF's public project showcase as archived by the Internet Archive before judging (https://web.archive.org/web/20230401224130/https://ca-csef.zfairs.com/showcase/ShowcaseInfo?f=838e60b7-ea75-46e8-865c-fde4864244b3); the version presented may differ.
Awards (1)
Competition history
- CSEF 2023
Resources
Related projects
ISEF · 2022
A Novel Approach to Analyzing Alzheimer's Disease in MRI Scans Using a Convolutional Neural Network
CSEF · 2019
Implementation and Validation of a Machine Learning Model for the Early Detection of Alzheimer's Disease
CSEF · 2015
Automated Diagnosis of Alzheimer's Using MRI Images
ISEF · 2021
Improving Alzheimer's Disease Diagnosis Using AI-Based Artificial Neural Networks
CSEF · 2018
Early Classification of Alzheimer's Disease Using Machine Learning
ISEF · 2020
Predicting the Onset of Alzheimer's Disease Using Graph Neural Networks and Diffusion Tensor Imaging
AJAS · 2019
Early Diagnosis of Alzheimer's Disease Using Deep Feedforward Neural Networks
ISEF · 2022
A Novel Approach for Early Detection of Alzheimer's Disease: Developing an AlexNet Convolutional Neural Network Enhanced by Class Activation Mapping
Closest projects by meaning, across every fair and year in the corpus.
Browse more like this
Source: California Science & Engineering Fair public projects