Automatic evaluation of uterine cervix segmentations

Shelly Lotenberg, Shiri Gordon, Rodney Long, Sameer Antani, Jose Jeronimo, Hayit Greenspan*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

6 Scopus citations

Abstract

In this work we focus on the generation of reliable ground truth data for a large medical repository of digital cervicographic images (cervigrams) collected by the National Cancer Institute (NCI). This work is part of an ongoing effort conducted by NCI together with the National Library of Medicine (NLM) at the National Institutes of Health (NIH) to develop a web-based database of the digitized cervix images in order to study the evolution of lesions related to cervical cancer. As part of this effort, NCI has gathered twenty experts to manually segment a set of 933 cervigrams into regions of medical and anatomical interest. This process yields a set of images with multi-expert segmentations. The objectives of the current work are: 1) generate multi-expert ground truth and assess the difficulty of segmenting an image, 2) analyze observer variability in the multi-expert data, and 3) utilize the multi-expert ground truth to evaluate automatic segmentation algorithms. The work is based on STAPLE (Simultaneous Truth and Performance Level Estimation), which is a well known method to generate ground truth segmentation maps from multiple experts' observations. We have analyzed both intra- and inter-expert variability within the segmentation data. We propose novel measures of "segmentation complexity" by which we can automatically identify cervigrams that were found difficult to segment by the experts, based on their inter-observer variability. Finally, the results are used to assess our own automated algorithm for cervix boundary detection.

Original languageEnglish
Title of host publicationMedical Imaging 2007
Subtitle of host publicationImage Perception, Observer Performance, and Technology Assessment
DOIs
StatePublished - 2007
EventMedical Imaging 2007: Image Perception, Observer Performance, and Technology Assessment - San Diego, CA, United States
Duration: 21 Feb 200722 Feb 2007

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume6515
ISSN (Print)1605-7422

Conference

ConferenceMedical Imaging 2007: Image Perception, Observer Performance, and Technology Assessment
Country/TerritoryUnited States
CitySan Diego, CA
Period21/02/0722/02/07

Keywords

  • Cervical cancer
  • F-measure
  • Image segmentation and indexing
  • Medical image archives
  • Observer performance evaluation
  • STAPLE
  • Technology assessment
  • Uterine cervix

Fingerprint

Dive into the research topics of 'Automatic evaluation of uterine cervix segmentations'. Together they form a unique fingerprint.

Cite this