MedScan is a healthcare project aimed at expediting and enhancing the diagnostic process for various medical conditions using X-ray images. Leveraging state-of-the-art deep learning techniques, particularly the UNet architecture for image segmentation, MedScan enables healthcare professionals to quickly and accurately identify areas of concern within X-ray images, leading to timely diagnosis and intervention, particularly in underserved healthcare settings.

• Deep Learning for Image Segmentation: Utilizes advanced deep learning techniques for precise segmentation of X-ray images.
• Multiple Medical Conditions Supported: Supports diagnosis for a range of medical conditions including Cardiac Catheterization, Brain Tumor Segmentation, Liver Tumor Segmentation, Viral Pneumonia Segmentation, and COVID Segmentation.
• Preprocessing and Training Pipeline: Includes a comprehensive pipeline for data preprocessing and training of the UNet model.
• Integration Options: Supports integration with web or mobile applications for seamless use by healthcare professionals.
• Continuous Improvement: Continuously updated and improved for enhanced accuracy and usability.

To get started with MedScan, follow these steps:

1. Clone the Repository:

git clone https://github.com/yourusername/medscan.git

4. Install Dependencies: Navigate to the project directory and install dependencies using

pip install -r requirements.txt`.

7. Download Datasets: Obtain datasets for training and testing the model. Links to datasets can be found at -
8. cc_model- https://drive.google.com/file/d/1xvttnP2khgOlPqc60uHbugl1gLnHPOiL/view?usp=sharing
9. bt_model- https://drive.google.com/file/d/1Jek98plS1lpkQMNXN-nsup48MeQlO4mB/view?usp=sharing
10. covid_model- https://drive.google.com/file/d/1SSsaLnpi4h3Utc1CP16UGSDugYouxjjH/view?usp=sharing
11. viral_peunomia- https://drive.google.com/file/d/1so8IlfuwQ1NbzIy30VY2l_NVvP6iMf8W/view?usp=sharing
12. liver_model- https://drive.google.com/file/d/1V9EUjh50Yv6ue6Z2lsB2X-8ZhHpE52KV/view?usp=sharing
13. Training the Model: Train the UNet model using the provided preprocessing and training pipeline.
14. Integration: Integrate the trained model into your preferred web or mobile application for diagnostic support.

Check out our demo video to see MedScan in action: https://youtu.be/Mg66Uh-qmLg