ISADS - Interactive Search-Assisted Decision Support


The goal of ISADS is to enable doctors to make more informed decisions about a given case by providing a selection of similar annotated cases from a large data repository. The fundamental challenge in developing ISADS systems is the efficient identification of similar cases, not simply in terms of superficial image characteristics, but in a medically-relevant sense. ISADS is a collaborative research effort with Intel, Carnegie Mellon University, Georgia Institute of Technology, University of Pittsburgh and the University of Pittsburgh Medical Center.

Skin Cancer


Melanoma is the most fatal type of skin cancer with an incident rate on the rise. ISADS for Dermatology is a tool that allows a physician to interactively search through a massive, distributed, and annotated repository of skin lesions. The physician can compare a questionable lesion against this repository by searching for similar features within the image itself. The annotated results returned from the repository provides the physician with more information by showing similar cases, which allows them to make more informed decisions.

We are collaborating closely with physicians from the University of Pittsburgh Medical School.

ISADS for Dermatology Video

Researchers


Collaborators


Students


External Links


ISADS wiki