A supervised learning framework of statistical shape and probability priors for automatic prostate segmentation in ultrasound images |
| |
Authors: | Soumya Ghose Arnau Oliver Jhimli Mitra Robert Martí Xavier Lladó Jordi Freixenet Désiré Sidibé Joan C Vilanova Josep Comet Fabrice Meriaudeau |
| |
Institution: | 1. Australian e-Health Research Centre, CSIRO, Brisbane, QLD 4029, Australia;2. Le2i-UMR CNRS 6306, Université de Bourgogne, 12 rue de la Fonderie, 71200 Le Creusot, France;3. Computer Vision and Robotics Group, Universitat de Girona, Campus Montilivi, Edifici PIV, s/n, 17071 Girona, Spain;4. Girona Magnetic Resonance Center, 26 Carrer Joan Maragall, 17002 Girona, Spain;5. Hospital Dr. Josep Trueta, Av. França, s/n,17007 Girona, Spain |
| |
Abstract: | Prostate segmentation aids in prostate volume estimation, multi-modal image registration, and to create patient specific anatomical models for surgical planning and image guided biopsies. However, manual segmentation is time consuming and suffers from inter-and intra-observer variabilities. Low contrast images of trans rectal ultrasound and presence of imaging artifacts like speckle, micro-calcifications, and shadow regions hinder computer aided automatic or semi-automatic prostate segmentation. In this paper, we propose a prostate segmentation approach based on building multiple mean parametric models derived from principal component analysis of shape and posterior probabilities in a multi-resolution framework. The model parameters are then modified with the prior knowledge of the optimization space to achieve optimal prostate segmentation. In contrast to traditional statistical models of shape and intensity priors, we use posterior probabilities of the prostate region determined from random forest classification to build our appearance model, initialize and propagate our model. Furthermore, multiple mean models derived from spectral clustering of combined shape and appearance parameters are applied in parallel to improve segmentation accuracies. The proposed method achieves mean Dice similarity coefficient value of 0.91 ± 0.09 for 126 images containing 40 images from the apex, 40 images from the base and 46 images from central regions in a leave-one-patient-out validation framework. The mean segmentation time of the procedure is 0.67 ± 0.02 s. |
| |
Keywords: | Prostate segmentation Statistical shape and appearance model Random forest classification Spectral clustering |
本文献已被 ScienceDirect 等数据库收录! |
|