Text and Image Analysis

Automated Image Retrieval (AIR) - PACS

PACS AIR is a self-service platform which enables Automated Image Retrieval (AIR) from UCSF’s clinical and research picture archiving and communication system (PACS). AIR is capable of automated deidentification of header data, but cannot identify or remove PHI in the pixel data of images. Investigators using this service must arrange for creating discs or transmitting to central repositories on their own and have IRB approval.

CTAKES As-A-Service

  • Natural language processing system for extraction of information from electronic medical record clinical free-text.  Originally developed by Mayo Clinic, and now part of Apache products.

EMERSE

EMERSE is a web-based query tool that allows you to search for 'free-text' in the de-identified 100+ million clinical notes. Once you have been granted access to UCSF de-identified data, you will automatically have access to EMERSE.  If you don't have access to the de-identified data for research yet, you must request and be granted this access first.

  • You must be on the UCSF Network / VPN to access EMERSE
  • Use your MyAccess credentials to log in via emerse.ucsf.edu

Imaging Support Services

Many UCSF cores provide research support in combination with imaging services, in particular:

Hourly Recharge

NLP@UCSF

UCSF's NLP community curates knowledge as participants experiment, learn and implement NLP tools in clinical and biomedical research projects.

  • Slack channel and regular meetups
  • Recommended tools for textual analysis of clinical notes