Evaluating segmentation algorithms for diffusion-weighted MR images: a task-based approach

Abhinav K. Jha; Matthew A. Kupinski; Jeffrey J. Rodríguez; Renu M. Stephen; Alison T. Stopeck

doi:10.1117/12.845515

27 February 2010 Evaluating segmentation algorithms for diffusion-weighted MR images: a task-based approach

Abhinav K. Jha, Matthew A. Kupinski, Jeffrey J. Rodríguez, Renu M. Stephen, Alison T. Stopeck

Proceedings Volume 7627, Medical Imaging 2010: Image Perception, Observer Performance, and Technology Assessment; 76270L (2010) https://doi.org/10.1117/12.845515
Event: SPIE Medical Imaging, 2010, San Diego, California, United States

Abstract

Apparent Diffusion Coefficient (ADC) of lesions obtained from Diffusion Weighted Magnetic Resonance Imaging is an emerging biomarker for evaluating anti-cancer therapy response. To compute the lesion's ADC, accurate lesion segmentation must be performed. To quantitatively compare these lesion segmentation algorithms, standard methods are used currently. However, the end task from these images is accurate ADC estimation, and these standard methods don't evaluate the segmentation algorithms on this task-based measure. Moreover, standard methods rely on the highly unlikely scenario of there being perfectly manually segmented lesions. In this paper, we present two methods for quantitatively comparing segmentation algorithms on the above task-based measure; the first method compares them given good manual segmentations from a radiologist, the second compares them even in absence of good manual segmentations.

Citation Download Citation

Abhinav K. Jha, Matthew A. Kupinski, Jeffrey J. Rodríguez, Renu M. Stephen, and Alison T. Stopeck "Evaluating segmentation algorithms for diffusion-weighted MR images: a task-based approach", Proc. SPIE 7627, Medical Imaging 2010: Image Perception, Observer Performance, and Technology Assessment, 76270L (27 February 2010); https://doi.org/10.1117/12.845515

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available