Share Email Print

Journal of Medical Imaging

Impact of lesion segmentation metrics on computer-aided diagnosis/detection in breast computed tomography
Author(s): Hsien-Chi Kuo; Maryellen L. Giger; Ingrid S. Reiser; Karen Drukker; John M. Boone; Karen K. Lindfors; Kai Yang; Alexandra V. Edwards
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

Evaluation of segmentation algorithms usually involves comparisons of segmentations to gold-standard delineations without regard to the ultimate medical decision-making task. We compare two segmentation evaluations methods—a Dice similarity coefficient (DSC) evaluation and a diagnostic classification task–based evaluation method using lesions from breast computed tomography. In our investigation, we use results from two previously developed lesion-segmentation algorithms [a global active contour model (GAC) and a global with local aspects active contour model]. Although similar DSC values were obtained (0.80 versus 0.77), we show that the global + local active contour (GLAC) model, as compared with the GAC model, is able to yield significantly improved classification performance in terms of area under the receivers operating characteristic (ROC) curve in the task of distinguishing malignant from benign lesions. [Area under the ROC curve (AUC)=0.78 compared to 0.63, p0.001]. This is mainly because the GLAC model yields better detailed information required in the calculation of morphological features. Based on our findings, we conclude that the DSC metric alone is not sufficient for evaluating segmentation lesions in computer-aided diagnosis tasks.

Paper Details

Date Published: 24 December 2014
PDF: 5 pages
J. Med. Imag. 1(3) 031012 doi: 10.1117/1.JMI.1.3.031012
Published in: Journal of Medical Imaging Volume 1, Issue 3
Show Author Affiliations
Hsien-Chi Kuo, The Univ. of Chicago (United States)
Maryellen L. Giger, The Univ. of Chicago (United States)
Ingrid S. Reiser, The Univ. of Chicago (United States)
Karen Drukker, The Univ. of Chicago (United States)
John M. Boone, UC Davis Medical Ctr. (United States)
Karen K. Lindfors, UC Davis Medical Ctr. (United States)
Kai Yang, The Univ. of Oklahoma Health Sciences Ctr. (United States)
Alexandra V. Edwards, The Univ. of Chicago (United States)

© SPIE. Terms of Use
Back to Top