Skip to content

Shrestha-Developer/AI-Medical-Image-Analysis

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

AI-Powered Medical Image Analysis System

Project Overview

This project is an AI-based medical imaging system that analyzes chest X-ray images and detects Pneumonia using Deep Learning.

The system simulates a real-world healthcare AI tool that can assist doctors in diagnosing diseases faster and more accurately.


Objective

  • Build an AI system to analyze medical images
  • Detect diseases (Pneumonia vs Normal)
  • Provide real-time predictions via API & UI
  • Create a portfolio-ready industry-level project

Industry Relevance

AI-powered medical imaging is widely used in:

  • Hospitals
  • Diagnostic labs
  • Radiology centers
  • Health-tech companies

Why it matters:

  • Faster diagnosis
  • Reduced human error
  • Early disease detection
  • AI-assisted decision making

Dataset

This project uses Chest X-ray dataset.

Download from: https://www.kaggle.com/datasets/paultimothymooney/chest-xray-pneumonia

After downloading, place it like:

data/ └── chest_xray/ ├── train/ ├── test/

Tech Stack

Core Technologies:

  • Python
  • TensorFlow / Keras
  • OpenCV
  • NumPy
  • Matplotlib

Backend:

  • Flask API

Frontend:

  • Streamlit (Interactive UI)

Evaluation:

  • Accuracy
  • Confusion Matrix

Project Structure

AI-Medical-Image-Analysis/
│
├── data/                  # Dataset (train/test images)
├── models/                # Trained model (.h5)
├── outputs/               # Saved predictions + history
├── src/
│   ├── model.py           # CNN model
│   ├── train.py           # Training script
│   ├── predict.py         # Local prediction script
│
├── app.py                 # Flask API
├── ui.py                  # Streamlit UI
├── requirements.txt
├── README.md

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors