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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Scopus citations

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.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2010
Subtitle of host publicationImage Perception, Observer Performance, and Technology Assessment
DOIs
StatePublished - 2010
EventMedical Imaging 2010: Image Perception, Observer Performance, and Technology Assessment - San Diego, CA, United States
Duration: Feb 17 2010Feb 18 2010

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume7627
ISSN (Print)1605-7422

Other

OtherMedical Imaging 2010: Image Perception, Observer Performance, and Technology Assessment
Country/TerritoryUnited States
CitySan Diego, CA
Period2/17/102/18/10

Keywords

  • Task-based quantitative evaluation
  • no-gold-standard
  • segmentation algorithms

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Atomic and Molecular Physics, and Optics
  • Radiology Nuclear Medicine and imaging

Fingerprint

Dive into the research topics of 'Evaluating segmentation algorithms for diffusion-weighted MR images: A task-based approach'. Together they form a unique fingerprint.

Cite this