Computer Vision

CareCam is a Singapore-based A*STAR spinoff that develops machine vision technology for the healthcare industry. Their flagship product is CareCam 3D-Gait, an iOS mobile app that uses computer vision and AI to assess and measure the risk of medical disorders by analyzing gait. CareCam 3D-Gait is used to identify mobility deficiencies quickly and provide quantitative gait metrics against normative data in real-time. The app leverages on the integration of AI models for detection, tracking, phase segmentation, pose estimation and kinematics analysis for on-board processing and assessment. This information can be used by healthcare professionals to improve patient care and prevent injuries.

3D recognition is a key technique that has wide applications in vision guided robotics (VGR), e.g., autonomous vehicles, navigation, surveillance and beyond. This project aims to improve the accuracy and robustness of 3D recognition models with minimum extra costs. For accuracy, we propose to exploit different sorts of unlabelled data which are cheap to obtain. For robustness, we focus on the open-set generalization challenge and propose to learn few-shot learning models to endow models the ability of generalizing to novel objects with only a few labelled examples.

Coronary artery disease (CAD), a blockage of the blood vessels, affects 6% of the general population and up to 20% of those over 65 years of age. CAD is a leading cause of cardiac mortality in Singapore and worldwide, with 19% of deaths in Singapore due to CAD (MOH website). Numbers of CAD cases are growing rapidly due to ageing and higher prevalence of diabetes.

Computed Tomography Coronary Angiography (CTCA) is the first-line investigation for CAD as indicated by updated National Institute for Clinical Excellence (NICE) guidelines. CTCA increases diagnostic certainty, improves efficiency of triage to invasive catheterization and reduces radiation exposure when compared with functional stress testing. Current practice of CAD report generation requires 3-6 hours of a CT specialist’s time for annotating the scans, and with inter-observer variability of 20%. In addition, there is no effective toolkit to analyse Agatston scores (a measure of calcified CAD), severity of stenosis, and plaque characterisation. These problems have strongly and severely constrained the effectiveness of CTCA as a diagnostic and research tool.

We plan to build upon Singapore’s competitive advantages in artificial intelligence (AI) to provide a solution to these gaps. Here, our overall aim is to build an AI-driven CT Coronary Angiography platform for automated anonymization, reporting, Agatston scoring and plaque quantification in CAD. It is a “one-stop” platform spanning from diagnosis to clinical, management and prognosis, and aid in predicting therapy response in the pharmaceutical industries.