Cancer Diagnosis Through Image Recognition
Overview
Image recognition is the process of identifying and detecting an object or a feature in a digital image or video.
Over the past few decades, the research on computer vision, image processing and pattern recognition has made significant progress. Also, medical imaging has attracted increasing attention in recent years due to its vital component in healthcare applications.
Since medical analysis has a strong visual component, there is a strong potential for such an approach to help doctors in their diagnostic tasks, as we did in the Kheiron project.
Challenge
Kheiron Medical Technologies challenged EAI to join the development of Mia, a product able to support radiologists and breast screening department as an independent second reader.
London,
United Kingdom
Opportunity
EAI provided artificial intelligence expertise and implemented a deep learning and image recognition solution. We trained the algorithm to identify the probability of containing cancer and the exact location when loading a new mammography.
Impact
The product, Mia has superhuman performance with high sensitivity and specificity in cancer detection tasks.
Kheiron is the first UK company that received CE marking for deep learning technology in radiology.