Medical image analysis
-
Medical image analysis · Feb 2017
Comparative StudyComparison of atlas-based techniques for whole-body bone segmentation.
We evaluate the accuracy of whole-body bone extraction from whole-body MR images using a number of atlas-based segmentation methods. The motivation behind this work is to find the most promising approach for the purpose of MRI-guided derivation of PET attenuation maps in whole-body PET/MRI. To this end, a variety of atlas-based segmentation strategies commonly used in medical image segmentation and pseudo-CT generation were implemented and evaluated in terms of whole-body bone segmentation accuracy. ⋯ Finding the optimum parameters for implementation of the atlas fusion approach, such as weighting factors and image similarity patch size, have great impact on the performance of atlas-based segmentation approaches. The voxel-wise atlas fusion approach exhibited excellent performance in terms of cancelling out the non-systematic registration errors leading to accurate and reliable segmentation results. Denoising and normalization of MR images together with optimization of the involved parameters play a key role in improving bone extraction accuracy.
-
Medical image analysis · Oct 2016
EditorialPersonalized, relevance-based Multimodal Robotic Imaging and augmented reality for Computer Assisted Interventions.
In the last decade, many researchers in medical image computing and computer assisted interventions across the world focused on the development of the Virtual Physiological Human (VPH), aiming at changing the practice of medicine from classification and treatment of diseases to that of modeling and treating patients. These projects resulted in major advancements in segmentation, registration, morphological, physiological and biomechanical modeling based on state of art medical imaging as well as other sensory data. ⋯ In this paper, we discuss the personalization of imaging and visualization process with particular focus on satisfying the challenging requirements of computer assisted interventions. We discuss such requirements and review a series of scientific contributions made by our research team to tackle some of these major challenges.
-
Medical image analysis · Jul 2016
Magnetic resonance imaging-guided attenuation correction in whole-body PET/MRI using a sorted atlas approach.
Quantitative whole-body PET/MR imaging is challenged by the lack of accurate and robust strategies for attenuation correction. In this work, a new pseudo-CT generation approach, referred to as sorted atlas pseudo-CT (SAP), is proposed for accurate extraction of bones and estimation of lung attenuation properties. This approach improves the Gaussian process regression (GPR) kernel proposed by Hofmann et al. which relies on the information provided by a co-registered atlas (CT and MRI) using a GPR kernel to predict the distribution of attenuation coefficients. ⋯ This was reduced on average to 15.8 ± 8.6% and 8.0 ± 3.8% when using Hofmann's and SAP techniques, respectively. The SAP technique resulted in better overall PET quantification accuracy than both Hofmann's and the three-class approaches owing to the more accurate extraction of bones and better prediction of lung attenuation coefficients. Further improvement of the technique and reduction of the computational time are still required.
-
Medical image analysis · May 2016
A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI.
Segmentation of the left ventricle (LV) from cardiac magnetic resonance imaging (MRI) datasets is an essential step for calculation of clinical indices such as ventricular volume and ejection fraction. In this work, we employ deep learning algorithms combined with deformable models to develop and evaluate a fully automatic LV segmentation tool from short-axis cardiac MRI datasets. The method employs deep learning algorithms to learn the segmentation task from the ground true data. ⋯ We validated our method using 45 cardiac MR datasets from the MICCAI 2009 LV segmentation challenge and showed that it outperforms the state-of-the art methods. Excellent agreement with the ground truth was achieved. Validation metrics, percentage of good contours, Dice metric, average perpendicular distance and conformity, were computed as 96.69%, 0.94, 1.81 mm and 0.86, versus those of 79.2-95.62%, 0.87-0.9, 1.76-2.97 mm and 0.67-0.78, obtained by other methods, respectively.
-
Diffusion-weighted (DW) magnetic resonance imaging (MRI) is a noninvasive imaging method, which can be used to investigate neural tracts in the white matter (WM) of the brain. However, the voxel sizes used in DW-MRI are relatively large, making DW-MRI prone to significant partial volume effects (PVE). These PVEs can be caused both by complex (e.g. crossing) WM fiber configurations and non-WM tissue, such as gray matter (GM) and cerebrospinal fluid. ⋯ Results from simulation and in-vivo bootstrapping experiments demonstrate a significant improvement in the precision of the identified fiber orientations and in the number of false peaks detected under GM PVEs. Probabilistic whole brain tractography shows fiber density is increased in the major WM tracts and decreased in subcortical GM regions. The iCSD method significantly improves the fiber orientation estimation at the WM-GM interface, which is especially important in connectomics, where the connectivity between GM regions is analyzed.