Skip to content

README.md

Latest commit

 

History

History
57 lines (41 loc) · 1.6 KB

README.md

File metadata and controls

57 lines (41 loc) · 1.6 KB

Tuberculosis (TB) Detection

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

Dataset Source

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

Requirements

  1. Clone the repository
git clone https://github.com/MMADUs/TBC_Detection.git

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

  2. Create your own UV Virtual Environment

uv venv
  1. Synchronize package from the pyproject.toml in the repository
uv sync

End to End Workflow

1. Data Preparation & Preprocessing

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

2. Building The Model

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

3. Evaluation Metrics

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

Model Architecture

Model Architecture

Result can be found in the Tuberculosis Notebook.

References