【摘 要】
：
Purpose: The accurate segmentation of the specific tissues in encephalic image is necessary for the treatment and research of many diseases.Such tasks are usually accomplished by manual contouring,whi
【机 构】
：
Image Processing Center,Beihang University,Beijing 100191,China
【出 处】
：
The 15th Asia-Oceania Congress of Medical Physics (AOCMP2015
论文部分内容阅读
Purpose: The accurate segmentation of the specific tissues in encephalic image is necessary for the treatment and research of many diseases.Such tasks are usually accomplished by manual contouring,which is time-consuming and unrepeatable.In order to segment the encephalic tissues efficiently and accurately,we study a multi-atlas based segmentation method in this work.Methods: The multi-atlas based segmentation is composed of atlas registration and label fusion.Given the target image to be segmented and a group of atlas images,at the first step,each atlas image is registered to the target image using a deformable registration method.The registration method use cubic B-spline transformation to the model the difference between images and normalized mutual information as similarity metric.At the second step,the transformed segmentations,obtained from the first step,are fused to obtain an estimate segmentation of the target image.The label fusion method use STAPLE(Simultaneous Truth and Performance Level Estimation)to estimate the weight of each atlas through the Expectation Maximum iterating algorithm.And an error correction classifier is trained using corrective learning method to further improve the segmentation results.Results: We applied the proposed method on the 2012 MICCAI Multi-Atlas Labeling Challenge brain image dataset.The result of this method is comparable to other state-of-the-art algorithms.The segmentation get a mean Dice overlap of 0.916590 for 11 target images each with 14 labels.Conclusions: We study a multi-atlas based method to automatically segment encephalic tissues,which features the combination of STAPLE and corrective learning algorithms.It proves to be an effective method.
其他文献
Introduction:Polymer gels are 3-dimensional(3D) dosimetric tools used to evaluate radiation dose-relatedradiation-induced polymerization.When using a polymer gel as a phantom,it is possible to measure
Purpose: Segmental scanning protocol of Multi-energy computed tomography(MECT)is an easy-to-implement and no-extra dose induced way realized in conventiaonal CT,but the reconstruced image was degraded
INTRODUCTION The artifacts due to physiologic motion when using the Cartesian strategy of magnetic resonance imaging are well known [1] and many techniques of reducing the motion artifacts were presen
Purpose:Head motion in PET/CT leads to artifacts due to the mismatch of PET and CT images.This work aims at reducing motion artifacts in PET image reconstruction.Methods:The correction method for head
Purpose:It has been known that images reconstructed with filtered back projection(FBP) techniques areoften inadequate in CT.Iterative reconstruction(IR) has the potential to allow reducing dose whilem
Purpose:Digital breast tomosynthesis(DBT) has been considered as an innovative imaging modalitybecause it can solve the problem of poor depth resolution in conventional digital mammography by utilizin
Purpose: PET/CT images fusion accuracy may suffer from respiratory motion of body.To get better clinical images,it is necessary to correct PET data for motion artifacts.Methods: A novel high performan
Purpose:The photon counting detectors have been considered as a promising technology.These detectorsprovide spectral information and energy of each photon with single exposure.The contrast enhancement
Purpose:Algorithm development for chest digital tomosynthesis(CDT) is challenging in that a limitednumber of projections are acquired over a limited angular range.
In X-ray computed tomography(CT)for limited-view reconstruction,there are great challenges for accurate reconstruction as complete projections cannot be obtained.Iterative image reconstruction(IIR)wit