Development of an open-source annotation collection framework in javascript to accelerate the use of artificial intelligence in cancer diagnosis
Iain Carmichael, Professor
Statistics
Closed. This professor is continuing with Fall 2024 apprentices on this project; no new apprentices needed for Spring 2025.
There is an expanding effort to improve patient care and accelerate biomedical research through the development of artificial intelligence (AI) algorithms that analyze high-resolution images of cancerous tissue biopsies. As in all AI applications, data is the critical ingredient; our ability to develop clinically deployable algorithms is dependent on our capacity to collect image annotations (e.g. the outline of every cell or of cancerous regions in a biopsy).
To address the data collection bottleneck we are putting together a modern, open-source image annotation framework for clinical Pathology images based on https://kaibu.org/#/app and https://imjoy.io/#/. We are looking for people who have experience writing applications in Javascript to join the team. This project will involve close collaboration with our interdisciplinary team of data scientists from Berkeley and the KTH Royal Institute of Technology as well as clinicians from UCSF.
Role: Possible tasks may include working with our team to
- Develop of browser based image annotation platform
- Integrate AI assisted annotation technologies into the platform
- Work closely with clinicians to optimize the annotation platform for usability
- Help write papers
Qualifications: - (Necessary) Experience with Javascript, especially front end web app development
- Experience implementing design in CSS and front end design frameworks
- Knowledge of python
Hours: 12 or more hours
Digital Humanities and Data Science Mathematical and Physical Sciences