Distributed Medical Image Analysis and Diagnosis through Crowd-Sourced Games: A Malaria Case Study

In this work we investigate whether the innate visual recognition and learning capabilities of untrained humans can be used in conducting reliable microscopic analysis of biomedical samples toward diagnosis. For this purpose, we designed entertaining digital games that are interfaced with artificial...

Full description

Saved in:
Bibliographic Details
Published in:PloS one Vol. 7; no. 5; p. e37245
Main Authors: Mavandadi, Sam, Dimitrov, Stoyan, Feng, Steve, Yu, Frank, Sikora, Uzair, Yaglidere, Oguzhan, Padmanabhan, Swati, Nielsen, Karin, Ozcan, Aydogan
Format: Journal Article
Language:English
Published: United States Public Library of Science 11.05.2012
Public Library of Science (PLoS)
Subjects:
Algorithms
Artificial Intelligence
Automation
Blood cells
Blood Cells - parasitology
Case studies
Computer & video games
Crowdsourcing
Decisions
Diagnosis
Diagnosis, Computer-Assisted
Electrical engineering
Engineering
Erythrocytes
Experts
Games, Experimental
Humans
Identification
Image analysis
Image Interpretation, Computer-Assisted - methods
Image processing
Information theory
Malaria
Malaria - blood
Malaria - diagnosis
Malaria - parasitology
Medical diagnosis
Medical imaging equipment
Medicine
Microscopic analysis
Microscopy
Parasites
Pattern Recognition, Automated
Pattern Recognition, Visual
Physics
Problem Solving
Social and Behavioral Sciences
Telemedicine
Vector-borne diseases
Vegetables
Video Games
Vision systems
Visual discrimination learning
Los Angeles California
United States > US
California
ISSN:1932-6203, 1932-6203
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this work we investigate whether the innate visual recognition and learning capabilities of untrained humans can be used in conducting reliable microscopic analysis of biomedical samples toward diagnosis. For this purpose, we designed entertaining digital games that are interfaced with artificial learning and processing back-ends to demonstrate that in the case of binary medical diagnostics decisions (e.g., infected vs. uninfected), with the use of crowd-sourced games it is possible to approach the accuracy of medical experts in making such diagnoses. Specifically, using non-expert gamers we report diagnosis of malaria infected red blood cells with an accuracy that is within 1.25% of the diagnostics decisions made by a trained medical professional.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
Wrote the paper: SM AO. Designed and developed the theoretical framework and algorithms; contributed to the overall design of the games and related infrastructure; conducted the analysis and interpretation of the data and results: SM. Contributed to the development and implementation of the games and related infrastructure: SD SF FY. Contributed to the acquisition and compilation of microscopic images: US OY SP. Contributed to the medical implementation of the presented platform: KN. Conceived the idea, supervised the project, and contributed to the overall design of the games, related infrastructure and theory as well as to the analysis and interpretation of the data and the results: AO.
ISSN:1932-6203
1932-6203
DOI:10.1371/journal.pone.0037245