Welcome to the InfoSci Platform
Reference Hub7
Evaluation Challenges for Bridging Semantic Gap: Shape Disagreements on Pulmonary Nodules in the Lung Image Database Consortium

Evaluation Challenges for Bridging Semantic Gap: Shape Disagreements on Pulmonary Nodules in the Lung Image Database Consortium

William H. Horsthemke, Daniela S. Raicu, Jacob D. Furst
Copyright: © 2009 |Volume: 4 |Issue: 1 |Pages: 17
ISSN: 1555-3396|EISSN: 1555-340X|ISSN: 1555-3396|EISBN13: 9781615202904|EISSN: 1555-340X|DOI: 10.4018/jhisi.2009010102
Cite Article Cite Article

MLA

Horsthemke, William H., et al. "Evaluation Challenges for Bridging Semantic Gap: Shape Disagreements on Pulmonary Nodules in the Lung Image Database Consortium." IJHISI vol.4, no.1 2009: pp.17-33. http://doi.org/10.4018/jhisi.2009010102

APA

Horsthemke, W. H., Raicu, D. S., & Furst, J. D. (2009). Evaluation Challenges for Bridging Semantic Gap: Shape Disagreements on Pulmonary Nodules in the Lung Image Database Consortium. International Journal of Healthcare Information Systems and Informatics (IJHISI), 4(1), 17-33. http://doi.org/10.4018/jhisi.2009010102

Chicago

Horsthemke, William H., Daniela S. Raicu, and Jacob D. Furst. "Evaluation Challenges for Bridging Semantic Gap: Shape Disagreements on Pulmonary Nodules in the Lung Image Database Consortium," International Journal of Healthcare Information Systems and Informatics (IJHISI) 4, no.1: 17-33. http://doi.org/10.4018/jhisi.2009010102

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Evaluating the success of prediction and retrieval systems depends upon a reliable reference standard, a ground truth. The ideal gold standard is expected to result from the marking, labeling, and rating of domain experts. However experts disagree and lack of agreement challenges the development and evaluation of image-based feature prediction. This paper addresses the success and limitations in bridging the semantic gap between CT-based pulmonary nodule image features and radiologists’ ratings of diagnostic characteristics. The prediction of diagnostic characteristics promises to automatically annotate images with medically meaningful descriptions usable for indexing and retrieving in content-based image retrieval (CBIR) and computer aided diagnosis (CADx). Successful results in predicting texture characteristics will be contrasted with less successful results for boundary shapes. The two primary differences in agreement between radiologists will be discussed; the first concerns agreement about the existence of a nodule, while the second considers the variability in radiologists’ ratings.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.