Tuberculosis Detection from Chest X-ray images.
Project type: Binary Classification & Image processing.

The image dataset is originally from kaggle: https://www.kaggle.com/datasets/tawsifurrahman/tuberculosis-tb-chest-xray-dataset?resource=download

1. Clone the repository

git clone https://github.com/MMADUs/TBC_Detection.git

2. Install the UV package manager
   UV Installation Guide: https://docs.astral.sh/uv/guides/install-python/

3. Create your own UV Virtual Environment

uv venv

4. Synchronize package from the pyproject.toml in the repository

uv sync

• Load the Data, includes: Image read, Image resize, Normalize & Labeling.
• Split the Data, split into: train, test, & val.
• Data Augmentation
• Handle Class Imbalance

• Build the model using Convolutional Neural Network, followed by dense layer.
• Callbacks & Model Training
• Monitor Training Performance

• Evaluate Loss & Accuracy
• ROC & AUC
• Predicting using best threshold
• Confusion Matrix
• Classification Report, includes recall, precision, & f1score

Result can be found in the Tuberculosis Notebook.

• Brain Tumor Detection using CNN