October 24 - 28, 2011
Building 10 & Natcher Conference Center
- General Schedule of Events
- Opening Plenary Session
- Concurrent Symposia Sessions
- Improving Workplace Dynamics
- FARE Award Ceremony
- Poster Sessions
- Special Exhibits on Resources for Intramural Research
- TSA Research Festival Exhibit Show
- Research Festival Committees
- Past Research Festivals
2011 program
Download the 2011 Research Festival Program Book
PDF documents require the free Adobe Reader
Fusion of machine intelligence and human intelligence for colonic polyp detection in CT colonography
| Wednesday, October 26, 2011 — Poster Session III | |||
|---|---|---|---|
10:00 a.m. – Noon |
Natcher Conference Center |
CC |
IMAG-36 |
Authors
- S Wang
- V Anugu
- T Nguyen
- N Rose
- J Burns
- M McKenna
- N Petrick
- R Summers
Abstract
In this paper, we proposed a novel method to improve colonic polyp detection in computed tomographic (CT) colonography. Utilizing the human knowledge workers via the Amazon Mechanical Turk (MTurk) webservice, we distributed polyp detections from a computer-aided detection system (CAD) to anonymous online knowledge workers and asked them to distinguish true and false polyp candidates. We combined decisions from the CAD system (machine intelligence) and the MTurk workers (human intelligence) using alpha-integration. Preliminary experimental results indicated that the combined decisions were superior to either alone, with area under the receiver operating characteristic curve improving by 5.8% and 7.0% compared with CAD and MTurk workers alone, respectively.
