Biomedical Visual-Language Processing (BioViL)
BioViL is a machine learning model trained on biomedical vision and language datasets at scale. It does not require manual annotations and can leverage historical raw clinical image acquisitions and clinical notes.
AIMI Symposium 2020 – Session 1: Democratizing Healthcare with AI
Session 1 focuses on the democratization of clinical knowledge via AI enabled diagnostics including use cases, advantages, pitfalls, and future directions. 00:00 – Session Overview Daniel Rubin, Professor of Biomedical Data Science & Radiology, Director…
Biomedical Research Platform Terra Now Available on Microsoft Azure
We stand at the threshold of a new era of precision medicine, where health and life sciences data hold the potential to dramatically propel and expand our understanding and treatment of human disease. One of…
SmartKC: A Low-cost, Smartphone-based Corneal Topographer
Microsoft Research India, in collaboration with the Sankara Eye Hospital, developed SmartKC, a low-cost, smartphone-based corneal topographer that can diagnose keratoconus. In a pilot clinical study, SmartKC achieved a sensitivity of 94.1% and a specificity…
Hybrid model approach in data mining
Tongue-Gesture Recognition in Head-Mounted Displays
Head mounted displays are often used in many situations where the hands of an user may be occupied or otherwise unusable due to situational or permanent movement impairments. Hands-free interaction is critical for making mixed…