Automated and interactive lesion detection and segmentation in uterine cervix images

Amir Alush*, Hayit Greenspan, Jacob Goldberger

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

39 Scopus citations


This paper presents a procedure for automatic extraction and segmentation of a class-specific object (or region) by learning class-specific boundaries. We describe and evaluate the method with a specific focus on the detection of lesion regions in uterine cervix images. The watershed segmentation map of the input image is modeled using a Markov random field (MRF) in which watershed regions correspond to binary random variables indicating whether the region is part of the lesion tissue or not. The local pairwise factors on the arcs of the watershed map indicate whether the arc is part of the object boundary. The factors are based on supervised learning of a visual word distribution. The final lesion region segmentation is obtained using a loopy belief propagation applied to the watershed arc-level MRF. Experimental results on real data show state-of-the-art segmentation results on this very challenging task that, if necessary, can be interactively enhanced.

Original languageEnglish
Article number5405644
Pages (from-to)488-501
Number of pages14
JournalIEEE Transactions on Medical Imaging
Issue number2
StatePublished - Feb 2010


  • Belief-propagation
  • Cervigrams
  • Lesion detection
  • Lesion segmentation
  • Markov random field (MRF)
  • Uterine cervix
  • Visual words
  • Watershed map


Dive into the research topics of 'Automated and interactive lesion detection and segmentation in uterine cervix images'. Together they form a unique fingerprint.

Cite this