Random walks with statistical shape prior for cochlea and inner ear segmentation in micro-CT images

Esmeralda Ruiz Pujadas, Gemma Piella, Hans Martin Kjer, Miguel Angel González Ballester

Research output: Contribution to journalJournal articleResearchpeer-review

351 Downloads (Pure)


A cochlear implant is an electronic device which can restore sound to completely or partially deaf patients. For surgical planning, a patient-specific model of the inner ear must be built using high-resolution images accurately segmented. We propose a new framework for segmentation of micro-CT cochlear images using random walks, where a region term estimated by a Gaussian mixture model is combined with a shape prior initially obtained by a statistical shape model (SSM). The region term can then take advantage of the high contrast between the background and foreground, while the shape prior guides the segmentation to the exterior of the cochlea and to less contrasted regions inside the cochlea. The prior is obtained via a non-rigid registration regularized by a statistical shape model. The SSM constrains the inner parts of the cochlea and ensures valid output shapes of the inner ear.
Original languageEnglish
JournalMachine Vision & Applications
Pages (from-to)1-10
Number of pages10
Publication statusPublished - 2017


  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Computer Science Applications
  • Inner ear segmentation for micro-CT images
  • Random walks segmentation
  • Statistical non-rigid registration
  • Statistical shape prior
  • Cochlear implants
  • Gaussian distribution
  • Image segmentation
  • Random processes
  • Statistics
  • Gaussian Mixture Model
  • High resolution image
  • Micro CT
  • Nonrigid registration
  • Patient specific model
  • Random Walk
  • Statistical shape model
  • Statistical shapes
  • Computerized tomography


Dive into the research topics of 'Random walks with statistical shape prior for cochlea and inner ear segmentation in micro-CT images'. Together they form a unique fingerprint.

Cite this