Tuberculosis CNN Model
This repository contains a CNN model for classifying chest X-ray images as Normal or Tuberculosis.
Dataset
- Source: TB Chest Radiography Database
- Input: 256x256 grayscale images
- Classes: Normal, Tuberculosis
- Accuracy: ~93%
Usage
from handler import TBClassifier
import cv2
classifier = TBClassifier()
image = cv2.imread("path/to/xray.jpg")
result = classifier.predict(image)
print(f"Prediction: {result['prediction']}, Confidence: {result['confidence']:.4f}")
Model Details
- Framework: TensorFlow 2.17.0
- Format: SavedModel
- Preprocessing: Grayscale, 256x256, normalized
Medical Disclaimer
For educational use only. Consult healthcare professionals.
Tags
Medical Imaging, Deep Learning, TensorFlow, Tuberculosis