A fully automated and reproducible level-set segmentation approach for generation of MR-based attenuation correction map of PET images in the brain employing single STE-MR imaging modality

نویسندگان

  • Anahita Fathi Kazerooni
  • Mohammad Hadi Aarabi
  • Mohammadreza Ay
  • Hamidreza Saligheh Rad
چکیده

Quantitative MR Imaging and Spectroscopy Group, Research Center for Cellular and Molecular Imaging, Tehran University of Medical Sciences, Tehran, Iran Generating MR-based attenuation correction map (μ-map) for quantitative reconstruction of PET images still remains a challenge in hybrid PET/MRI systems, mainly because cortical bone structures are indistinguishable from proximal air cavities in conventional MR images. Recently, development of short echo-time (STE) MR imaging sequences, has shown promise in differentiating cortical bone from air. However, on STE-MR images, the bone appears with discontinuous boundaries. Therefore, segmentation techniques based on intensity classification, such as thresholding or fuzzy C-means, fail to homogeneously delineate bone boundaries, especially in the presence of intrinsic noise and intensity inhomogeneity. Consequently, they cannot be fully automatized, must be fine-tuned on the case-by-case basis, and require additional morphological operations for segmentation refinement. To overcome the mentioned problems, in this study, we introduce a new fully automatic and reproducible STE-MR segmentation approach exploiting level-set in a clustering-based intensity inhomogeneity correction framework to reliably delineate bone from soft tissue and air. MR images were acquired on a clinical 1.5T MRI System, MAGNETOM Avanto, using a FLASH 3D pulse sequence with TE=1.1ms, TR=12ms, flip angle=18°, voxel size=1.2×1.2×2mm. For segmentation of the STE-MR images into three regions, consisting of bone, air and soft tissue, a region-based level-set segmentation algorithm was applied. In this technique, k-means clustering is applied to estimate the intensity properties of each region for bias field correction simultaneously with the level-set segmentation. This algorithm incorporates both intensity and spatial information to define continuous boundaries. The quantitative assessment outcomes of the segmentation performance yielded an average of 89%, 82%, 91%, and 73% for the accuracy, sensitivity, specificity and dice scores in bone segmentation, respectively. Kazerooni et al. EJNMMI Physics 2014, 1(Suppl 1):A48 http://www.ejnmmiphys.com/content/1/S1/A48

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Comparison of state-of-the-art atlas-based bone segmentation approaches from brain MR images for MR-only radiation planning and PET/MR attenuation correction

Introduction: Magnetic Resonance (MR) imaging has emerged as a valuable tool in radiation treatment (RT) planning as well as Positron Emission Tomography (PET) imaging owing to its superior soft-tissue contrast. Due to the fact that there is no direct transformation from voxel intensity in MR images into electron density, itchr('39')s crucial to generate a pseudo-CT (Computed Tomography) image ...

متن کامل

A robust MR-based attenuation map generation in short-TE MR images of the head employing hybrid spatial fuzzy C-means clustering and intensity inhomogeneity correction

Quantitative MR Imaging and Spectroscopy Group, Research Center for Cellular and Molecular Imaging, Tehran University of Medical Sciences, Tehran, Iran Deriving an accurate attenuation correction map (μ-map) from magnetic resonance (MR) volumes has become an important problem in hybrid PET/MR imaging. Recently, short echo-time (STE) MR imaging technique incorporating fuzzy C-means (FCM) tissue ...

متن کامل

Quantitative Comparison of SPM, FSL, and Brainsuite for Brain MR Image Segmentation

Background: Accurate brain tissue segmentation from magnetic resonance (MR) images is an important step in analysis of cerebral images. There are software packages which are used for brain segmentation. These packages usually contain a set of skull stripping, intensity non-uniformity (bias) correction and segmentation routines. Thus, assessment of the quality of the segmented gray matter (GM), ...

متن کامل

A Method for Body Fat Composition Analysis in Abdominal Magnetic Resonance Images Via Self-Organizing Map Neural Network

Introduction: The present study aimed to suggest an unsupervised method for the segmentation of visceral adipose tissue (VAT) and subcutaneous adipose tissue (SAT) in axial magnetic resonance (MR) images of the abdomen. Materials and Methods: A self-organizing map (SOM) neural network was designed to segment the adipose tissue from other tissues in the MR images. The segmentation of SAT and VA...

متن کامل

New Pseudo-CT Generation Approach from Magnetic Resonance Imaging using a Local Texture Descriptor

Background: One of the challenges of PET/MRI combined systems is to derive an attenuation map to correct the PET image. For that, the pseudo-CT image could be used to correct the attenuation. Until now, most existing scientific researches construct this pseudo-CT image using the registration techniques. However, these techniques suffer from the local minima of the non-rigid deformation energy f...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره 1  شماره 

صفحات  -

تاریخ انتشار 2014