Showing papers in "Computerized Medical Imaging and Graphics in 2010"

TL;DR: A focused literature survey on recent neural network developments in computer-aided diagnosis, medical image segmentation and edge detection towards visual content analysis, and medical image registration for its pre-processing and post-processing is provided to increase awareness of how neural networks can be applied to these areas.

TL;DR: The proposed algorithm for vessel segmentation and network extraction in retinal images is compared with widely used supervised and unsupervised methods and evaluated in noisy conditions, giving higher average sensitivity rate in the same range of specificity and accuracy, and showing robustness in the presence of additive Salt&Pepper or Gaussian white noise.

TL;DR: This work presents a new method based on mathematical morphology for detecting exudates in color eye fundus images that potentially can obtain better exudate detection results in terms of sensitivity and specificity.

TL;DR: This work simulates volumetric images of vascular trees and generates the corresponding ground-truth segmentations, bifurcation locations, branch properties, and tree hierarchy from 3D medical images.

TL;DR: The method takes advantage of the random forest algorithm and offers a structure for a hybrid random forest based lung nodule classification aided by clustering and a high receiver operating characteristic (ROC) A(z) of 0.9786 has been achieved.

TL;DR: The experimental results indicate that curvelet transformation is a promising tool for analysis and classification of digital mammograms.

TL;DR: A novel approach to WCE reading time reduction by unsupervised mining of video frames is proposed, based on a data reduction algorithm applied according to a novel scheme for the extraction of representative video frames from a full length WCE video.

TL;DR: A software system to provide intuitive navigation for MRI-guided robotic transperineal prostate therapy is presented and performance tests show that the registration error of the system was 2.6mm within the prostate volume.

TL;DR: Key technical considerations of tissue deformation tracking, 3D reconstruction, subject-specific modeling, image guidance and augmented reality for robotic assisted minimally invasive surgery are described.

TL;DR: Results indicate the proposed method, which consisted of a rule-based method, a level set method, and a support vector machine, would be useful for assisting neuroradiologists in assessing the MS in clinical practice.

TL;DR: An automatic algorithm for coronary artery segmentation from 3D X-ray data sequences of a cardiac cycle is proposed, using discrete geometric tools to fit on the artery shape independently from any perturbation of the data.

TL;DR: An automatic hybrid image segmentation model that integrates the statistical expectation maximization (EM) model and the spatial pulse coupled neural network (PCNN) for brain magnetic resonance imaging (MRI) segmentation yields the best results for gray matter and brain parenchyma segmentation.

TL;DR: Computer-aided methods for automatically measuring anatomical deformities of long bones of the lower limb using a three-dimensional bone model reconstructed from CT scan data of the patient is used as input.

TL;DR: An empirical stopping criterion for the 2D-maximum-likelihood expectation-maximization iterative image reconstruction algorithm in positron emission tomography (PET) has been proposed and applied the MLEM algorithm on Monte Carlo generated noise-free projection data and studied the properties of the pixel updating coefficients (PUC) in the reconstructed images.

TL;DR: It is suggested that the needle insertion manipulator and the physical liver model developed and validated in this work are effective for accurate needle insertion.

TL;DR: This work proposes a novel method that can perform this task in a totally automatic fashion, based on a multiresolution binary level set method, to identify various types of intracranial hematomas for patients with neurological emergencies.

TL;DR: A fast and automatic mosaicing algorithm applied to cystoscopic video sequences, where perspective geometric transformations link successive image pairs, to be able to do a dynamic selection of image pairs.

TL;DR: It is hoped that the augmented view can improve the efficiency of TECAB surgery and reduce the conversion rate to more conventional procedures.

TL;DR: The cardiac physiome model tailored for medical image analysis is presented with its detailed 3D implementation using the meshfree methods, which is more adaptive to different cardiac geometries and thus beneficial to individualized analysis.

TL;DR: A comparison of two different semi-automated methods, viz., level set and marker controlled watershed methods that perform an accurate and fast segmentation of tumor is made.

TL;DR: An algorithm that forms a retinal vessel graph by analysing the potential connectivity of segmented retinal vessels and resolving the configuration of local sets of segment ends determines the network connectivity.

TL;DR: This paper presents a joint serial image registration and segmentation algorithm that can tolerate larger or discontinuous temporal changes that often appear during image-guided therapy.

TL;DR: A universal representation for upward and downward vessel cross-sectional profiles with varying boundary sharpness is defined to define a new scheme of vessel detection based on symmetry and asymmetry in the Fourier domain.

TL;DR: A new technique for segmenting airways with proper topology is described and applied to an image volume generated by magnetic resonance imaging of a silicone cast created from an excised monkey lung.

TL;DR: A precision-guided surgical navigation system for minimally invasive surgery that combines a laser guidance technique with a three-dimensional (3D) autostereoscopic image overlay technique to improve the placement accuracy of surgical instruments and better visualization of patient's internal structure is described.

TL;DR: In this article, seven texture measurement methods (two wavelet, two model and three statistical based) were applied to investigate their susceptibility to subtle noise caused by acquisition and reconstruction deficiencies in computed tomography (CT) images.

TL;DR: This work presents a new method for motion estimation of tagged cardiac magnetic resonance sequences based on variational techniques, improved by adding a new term in the optical flow equation that incorporates tracking points with high stability of phase.

TL;DR: A semi-automatic method for sequentially reconstructing coronary arterial skeletons from a pair of CAG sequences covering one or several cardiac cycles acquired from different views based on snake model, where the snake curve deforms directly in 3D through minimizing a predefined energy function and ultimately stops at the global optimum with the minimal energy.

TL;DR: Experimental results reveal that UDLA segments a multi-spectral MR image much more effectively than either FMRIB's Automated Segmentation Tool (FAST) or Fuzzy C-means (FC).

TL;DR: A fully automated morphology-based technique able to perform accurate nuclear segmentations in images with heterogeneous staining and multiple tissue layers is presented and an alternate semi-automated method based on a well established segmentation approach, namely active contours is compared.