View Full Document

Brain Anatomical Structure Segmentation



View the full content.
View Full Document
View Full Document

6 views

Unformatted text preview:

IEEE TRANSACTIONS ON MEDICAL IMAGING VOL 27 NO 4 APRIL 2008 495 Brain Anatomical Structure Segmentation by Hybrid Discriminative Generative Models Zhuowen Tu Katherine L Narr Piotr Doll r Ivo Dinov Paul M Thompson and Arthur W Toga Abstract In this paper a hybrid discriminative generative model for brain anatomical structure segmentation is proposed The learning aspect of the approach is emphasized In the discriminative appearance models various cues such as intensity and curvatures are combined to locally capture the complex appearances of different anatomical structures A probabilistic boosting tree PBT framework is adopted to learn multiclass discriminative models that combine hundreds of features across different scales On the generative model side both global and local shape models are used to capture the shape information about each anatomical structure The parameters to combine the discriminative appearance and generative shape models are also automatically learned Thus low level and high level information is learned and integrated in a hybrid model Segmentations are obtained by minimizing an energy function associated with the proposed hybrid model Finally a grid face structure is designed to explicitly represent the 3 D region topology This representation handles an arbitrary number of regions and facilitates fast surface evolution Our system was trained and tested on a set of 3 D magnetic resonance imaging MRI volumes and the results obtained are encouraging Fig 1 Illustration of an example 3 D MRI volume a Example MRI volume with skull stripped b Manually annotated subcortical structures The goal of this work is to design a system that can automatically create such annotations Index Terms Brain anatomical structures discriminative models generative models probabilistic boosting tree PBT segmentation I INTRODUCTION S EGMENTING subcortical structures from 3 D brain images is of significant practical importance for example in detecting abnormal brain patterns 1 studying various brain diseases 2 and studying brain growth 3 Fig 1 shows an example 3 D magnetic resonance imaging MRI brain volume and subcortical structures delineated by a neuroanatomist This subcortical structure segmentation task is very important but difficult to do even by hand The various anatomical structures have similar intensity patterns see Fig 2 making these structures difficult to separate based solely on intensity Furthermore often there is no clear boundary between the regions Neuroanatomists often develop and use complicated protocols 2 in guiding the manual delineation process and Manuscript received May 4 2007 revised August 31 2007 This work was supported by the National Institutes of Health through the NIH Roadmap for Medical Research under Grant U54 RR021813 entitled Center for Computational Biology CCB Asterisk indicates corresponding author Z Tu K L Narr I Dinov and P M Thompson are with the Laboratory of Neuro Imaging UCLA Medical School Los Angeles CA 90095 USA P Doll r is with the Department of Computer Science University of California San Diego La Jolla CA 92093 USA A W Toga is with the Laboratory of Neuro Imaging UCLA Medical School 635 Charles Young Drive Los Angeles CA 90095 USA Color versions of one or more of the figures in this paper are available online at http ieeexplore ieee org Digital Object Identifier 10 1109 TMI 2007 908121 Fig 2 Intensity histograms of the eight subcortical structures targeted in this paper and of the background regions Note the high degree of overlap between their intensity distributions which makes these structures difficult to separate based solely on intensity those protocols may vary from task to task A considerable amount of work is required to fully delineate even a single 3 D brain volume Designing algorithms to automatically segment brain volumes is challenging in that it is difficult to transfer such protocols into sound mathematical models or frameworks In this paper we use a mathematical model for subcortical segmentation that includes both the appearance voxel intensities and shape geometry of each subcortical region We use a discriminative approach to model appearance and a generative model to describe shape and learn and combine them in a principled manner We apply our system to the segmentation of eight subcortical structures namely the left hippocampus LH the right hippocampus RH the left caudate LC the right caudate RC the left putamen LP the right putamen RP the left ventricle 0278 0062 25 00 2008 IEEE 496 IEEE TRANSACTIONS ON MEDICAL IMAGING VOL 27 NO 4 APRIL 2008 TABLE I COMPARISON OF DIFFERENT 3 D SEGMENTATION ALGORITHMS NOTE THAT ONLY OUR WORK COMBINES A STRONG GENERATIVE SHAPE MODEL WITH A DISCRIMINATIVE APPEARANCE MODEL IN THE ABOVE SVM REFERS TO SUPPORT VECTOR MACHINE LV and the right ventricle RV We obtained encouraging results It is worth mentioning that our system is very adaptive and can be directly used to segment other more structures A Related Work There has been considerable recent work on 3 D segmentation in medical imaging and some representatives include 4 7 15 16 Two systems particularly related to our approach are Fischl et al 4 and Yang et al 5 with which we will compare results The 3 D segmentation problem is usually tackled in a maximize a posterior MAP framework in which both appearance models and shape priors are defined Often either a generative or a discriminative model is used for the appearance model while the shape models are mostly generative based on either local or global geometry Once an overall target function is defined different methods are then applied to find the optimal segmentation Related work can be classified into two broad categories methods that rely primarily on strong shape models and methods that rely more on strong appearance models Table I compares some representative algorithms this is not a complete list for 3 D segmentation based on their appearance models shape models inference methods and specific applications we give detailed descriptions below The first class of methods including 4 8 rely on strong generative shape models to perform 3 D segmentation For the appearance models each of these methods assumes that the voxels are drawn from independent and identically distributed i i d Gaussians distributions Fischl et al 4 proposed a system for whole brain segmentation using Markov random fields MRFs to impose spatial constraints for the voxels of different anatomical structures In


Access the best Study Guides, Lecture Notes and Practice Exams

Loading Unlocking...
Login

Join to view Brain Anatomical Structure Segmentation and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Brain Anatomical Structure Segmentation and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?