TY - GEN
T1 - Evaluating segmentation algorithms for diffusion-weighted MR images
T2 - Medical Imaging 2010: Image Perception, Observer Performance, and Technology Assessment
AU - Jha, Abhinav K.
AU - Kupinski, Matthew A.
AU - Rodríguez, Jeffrey J.
AU - Stephen, Renu M.
AU - Stopeck, Alison T.
PY - 2010
Y1 - 2010
N2 - 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.
AB - 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.
KW - Task-based quantitative evaluation
KW - no-gold-standard
KW - segmentation algorithms
UR - http://www.scopus.com/inward/record.url?scp=79551708024&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=79551708024&partnerID=8YFLogxK
U2 - 10.1117/12.845515
DO - 10.1117/12.845515
M3 - Conference contribution
AN - SCOPUS:79551708024
SN - 9780819480286
T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE
BT - Medical Imaging 2010
Y2 - 17 February 2010 through 18 February 2010
ER -