Atlas-Based Prostate Segmentation Using an Hybrid Registration

TL;DR

This paper introduces a semi-automatic prostate segmentation method for MRI using hybrid registration of an anatomical atlas, aiming to assist in prostate brachytherapy navigation.

Contribution

The paper presents a novel hybrid registration framework combining intensity-based and point-matching algorithms for atlas-based prostate segmentation.

Findings

Mean error of 3.39 mm compared to expert segmentations

Validated with leave-one-out method on the same dataset

Potential to aid clinicians in routine image analysis

Abstract

Purpose: This paper presents the preliminary results of a semi-automatic method for prostate segmentation of Magnetic Resonance Images (MRI) which aims to be incorporated in a navigation system for prostate brachytherapy. Methods: The method is based on the registration of an anatomical atlas computed from a population of 18 MRI exams onto a patient image. An hybrid registration framework which couples an intensity-based registration with a robust point-matching algorithm is used for both atlas building and atlas registration. Results: The method has been validated on the same dataset that the one used to construct the atlas using the "leave-one-out method". Results gives a mean error of 3.39 mm and a standard deviation of 1.95 mm with respect to expert segmentations. Conclusions: We think that this segmentation tool may be a very valuable help to the clinician for routine quantitative image exploitation.