A supervised learning framework for automatic prostate segmentation in trans rectal ultrasound images

  • Authors:

  • Soumya Ghose;Jhimli Mitra;Arnau Oliver;Robert Martí;Xavier Lladó;Jordi Freixenet;Joan C. Vilanova;Josep Comet;Désiré Sidibé;Fabrice Meriaudeau

  • Affiliations:

  • Computer Vision and Robotics Group, University of Girona, Girona, Spain, Laboratoire Le2I - UMR CNRS 5158, Université de Bourgogne, Le Creusot, France;Computer Vision and Robotics Group, University of Girona, Girona, Spain, Laboratoire Le2I - UMR CNRS 5158, Université de Bourgogne, Le Creusot, France;Computer Vision and Robotics Group, University of Girona, Girona, Spain;Computer Vision and Robotics Group, University of Girona, Girona, Spain;Computer Vision and Robotics Group, University of Girona, Girona, Spain;Computer Vision and Robotics Group, University of Girona, Girona, Spain;Girona Magnetic Resonance Imaging Center, Girona, Spain;University Hospital Dr. Josep Trueta, Girona, Spain;Laboratoire Le2I - UMR CNRS 5158, Université de Bourgogne, Le Creusot, France;Laboratoire Le2I - UMR CNRS 5158, Université de Bourgogne, Le Creusot, France

  • Venue:
  • ACIVS'12 Proceedings of the 14th international conference on Advanced Concepts for Intelligent Vision Systems
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Heterogeneous intensity distribution inside the prostate gland, significant variations in prostate shape, size, inter dataset contrast variations, and imaging artifacts like shadow regions and speckle in Trans Rectal Ultrasound (TRUS) images challenge computer aided automatic or semi-automatic segmentation of the prostate. In this paper, we propose a supervised learning schema based on random forest for automatic initialization and propagation of statistical shape and appearance model. Parametric representation of the statistical model of shape and appearance is derived from principal component analysis (PCA) of the probability distribution inside the prostate and PCA of the contour landmarks obtained from the training images. Unlike traditional statistical models of shape and intensity priors, the appearance model in this paper is derived from the posterior probabilities obtained from random forest classification. This probabilistic information is then used for the initialization and propagation of the statistical model. The proposed method achieves mean Dice Similarity Coefficient (DSC) value of 0.96±0.01, with a mean segmentation time of 0.67±0.02 seconds when validated with 24 images from 6 datasets with considerable shape, size, and intensity variations, in a leave-one-patient-out validation framework. The model achieves statistically significant t-test p-value