Multi-Class Image Classification Model for Alzheimer’s MRI Images Using TensorFlow Take 4

Template Credit: Adapted from a template made available by Dr. Jason Brownlee of Machine Learning Mastery.

SUMMARY: This project aims to construct a predictive model using a TensorFlow convolutional neural network (CNN) and document the end-to-end steps using a template. The Alzheimer’s MRI Images dataset is a multi-class classification situation where we attempt to predict one of several (more than two) possible outcomes.

INTRODUCTION: The dataset contains four different classes of Alzheimer’s disease MRI images. The research team collected these images from various websites and manually verified each label. The inspiration behind sharing this dataset is to make highly accurate models for predicting the stages of Alzheimer’s disease.

ANALYSIS: The ResNet50V2 model’s performance achieved an accuracy score of 99.10% after five epochs using the training dataset. When we applied the model to the validation dataset, the model achieved an accuracy score of 66.69%.

CONCLUSION: In this iteration, the TensorFlow ResNet50V2 CNN model appeared suitable for modeling this dataset.

Dataset ML Model: Multi-Class classification with numerical features

Dataset Used: Alzheimer’s Dataset (4 Class of Images)

Dataset Reference:

One source of potential performance benchmarks:

The HTML formatted report can be found here on GitHub.