Anyone— patients, doctor, organization, medical IoT device developer, or researcher— can access in order to make more informed clinical decisions.
We focus more on leveraging pretrained models and architecture and less attention on custom training at the early stage
-
computer vision for medical diagnosis: Computer-aided disease diagnosis. (object detection, image classification, Image segmentation, image tagging, image similarity)
- Systems for diabetics Retinopathy(Segmentation, Grading and Localization) based on an image of the human eye: A system which based on an image of human eye classifies Diabetic Retinopathy disease using image processing and machine learning methods
- Morphological image processing methods are used to extract features like exudates and red lesion which characterise the disease.
- XGBoost and other models are used to classify disease into five categories.
- A Django/flask WebApp for demo
- U-Net architecture for segmentation of lesions, and a ResNet model for disease grading.
- Scanning medical images for abnormalities.
- Cancer diagnosis (Breast cancer etc)
- Diagnosing heart diseases.
- Tumor detection
- Alzheimer's and parkinson's Detection
- Brain Injuries
- Internal bleeding
- Pneumonia
- Systems for diabetics Retinopathy(Segmentation, Grading and Localization) based on an image of the human eye: A system which based on an image of human eye classifies Diabetic Retinopathy disease using image processing and machine learning methods
-
Medical Images and EHR (X-ray, ultrasound, CT or MRI scan) for diagnosing varieties of diseases.
- sourcing training and testing data for medical applications
-
Recommendation systems for personalized treatments
- Using Artificial Intelligence to make dental treatments more efficient, affordable and personalized.
- Precise cancer diagnosis and personalized treatment decisions.