This repository contains code and models for diagnosing Alzheimer's Disease using deep learning techniques. The project utilizes advanced convolutional neural networks (CNNs) to classify Alzheimer's Disease stages based on brain MRI images. We implemented and fine-tuned two state-of-the-art architectures: DenseNet169 and ResNet50, leveraging their capabilities for high accuracy in medical image classification.
Models
-
alzheimer-classification-densenet169: Implements the DenseNet169 architecture for classifying Alzheimer's Disease stages. DenseNet169 is known for its efficiency and accuracy in deep neural network designs by promoting feature reuse through dense connections.
-
alzheimer-classification-resnet50: Implements the ResNet50 architecture, a widely-used deep residual network known for its effectiveness in overcoming the vanishing gradient problem, making it highly suitable for complex image classification tasks.
Python 3.10: The project is developed using Python 3.10, taking advantage of its new features and improvements for enhanced performance and developer experience.
TensorFlow/Keras: Used for building, training, and evaluating the deep learning models.
NumPy: For efficient numerical computations.
Pandas: For data manipulation and analysis.
Matplotlib: For visualizing the training process and results.
First approach
- Download the given Python Notebooks
- Download the Dataset
- Upload the code files and dataset into your google colaboratory and just execute each file.
Second Approach
- Install the Python 3.x
- Install the PyCharm
- Download the dataset and load files including data into the PyCharm notebook