Team Leader Email - madhavkumar1523@gmail.com
The proposed idea is to develop a medical image processing application using ChexNet and SYCL for parallel computing, to predict the presence of chest diseases in medical images and generate a heatmap for interpretation. The application aims to offer faster and more accurate medical image processing than existing applications.
Some of the features of the application are:
- Chest disease prediction: The application uses ChexNet, a deep learning model for chest x-ray image analysis, to accurately predict the presence of 14 different chest diseases from medical images.
- Faster processing times: The application is designed to take advantage of parallel computing using SYCL, which can potentially lead to faster processing times compared to existing medical imaging applications.
- Heatmap generation: The application generates a heatmap on the original medical image to aid in interpretation and make the results more actionable for healthcare professionals.
- User-friendly interface: The application can be designed with a user-friendly interface that is easy to navigate and use, to make it accessible for healthcare professionals with varying levels of technical expertise.
- Python
- C++
- Intel oneAPI AI Toolkit
- Intel oneAPI oneDNN
- Intel oneAPI DPC++
- Intel Neural Compressor
This Section must contain set of instructions required to clone and run the prototype, so that it can be tested and deeply analysed Link of the GitHub repository will be given to the participants in their hackathon dashboard
Write about the biggest learning you had while developing the prototype