Computerized Medical Imaging and Graphics RSS feed: Current Issue. The purpose of the journal Computerized Medical Imaging and Graphics is to act as a source for the exchange of information concerning the medical use of new developments in imaging diagnosis, intervention, and follow up. Included in the journal will be articles on new medical scanning techniques, image-guided therapy, computer-aided diagnosis, robotic surgery and imaging, augmented-reality medical visualization, imaging genomics, reports of new advances in imaging modalities, and all other information related to the application of computerized radiology, oncology, and surgery. In addition, information on non-medical modes of imaging that have medical applications such as confocal and multi-photon microscopy, optical microendoscope, photoacoustic imaging, infra-red radiation, and other imaging modalities would be welcomed. The journal is a vehicle for the rapid publication of original research papers and review articles in the field of computerized medical imaging and graphics. Papers published in the journal will be of interest to computer scientists, medical physicists, bioengineers, imaging specialists, medical informaticians, computational biologists, radiologists, oncologists, neurologists, neurosurgeons, surgeons, cardiologists, cardiovascular surgeons, nuclear medicine physicians, pathologists, ophthalmologists, proctologists, nephrologists, gastroenterologists, and internists interested in imaging applications. Please note this Journal accepts neither Case Reports nor preliminary publications. http://www.medicalimagingandgraphics.com/?rss=yesElsevier Inc.en © 2012 Published by Elsevier Inc. All rights reserved. Computerized Medical Imaging and Graphics0895-6111364June 2012 © 2012 Published by Elsevier Inc. All rights reserved. healthpermissions@elsevier.comhttp://www.medicalimagingandgraphics.com/article/PIIS0895611112000523/abstract?rss=yesEditorial Board10.1016/S0895-6111(12)00052-3Computerized Medical Imaging and Graphics 36, 4 (2012)2012-06-01Computerized Medical Imaging and Graphics2012-06-01364S0895-6111(12)X0004-1CO2CO2http://www.medicalimagingandgraphics.com/article/PIIS0895611111001212/abstract?rss=yesAbstract: Fluorescent proteins (FPs) have been widely adopted in cell research for protein trafficking and reporter gene expression studies, as well as to study other biological processes. However, biological tissue has high light scattering and high absorption coefficients of visible light; hence, using FPs in small animal imaging remains a challenge, especially when the FPs are located deep in the tissue. In small animals, fluorescence molecular imaging could potentially address this difficulty. We constructed fluorescence molecular imaging systems that have two modes: a planner mode (projection imaging) and a multimodality mode (fluorescence molecular tomography and micro-CT). The planner mode can provide projection images of a fluorophore in the whole body of a small animal, whereas three-dimensional information can be offered by multimodality mode. The planner imaging system works in the reflection mode and is designed to provide fast imaging. The multimodality imaging system is designed to allow quantification and three-dimensional localization of fluorophores. A nude mouse with a tumour targeted with a far-red FP, which is appropriate for in vivo imaging, was adopted to validate the two systems. The results indicate that the planner imaging system is probably suitable for high throughput molecular imaging, whereas the multimodality imaging system is fit for quantitative research.Molecular imaging of small animals with fluorescent proteins: From projection to multimodalityXiaoquan Yang, Hui Gong, Jianwei Fu, Guotao Quan, Chuan Huang, Qingming Luo10.1016/j.compmedimag.2011.09.002Computerized Medical Imaging and Graphics 36, 4 (2012)2011-10-26Computerized Medical Imaging and Graphics2011-10-26364S0895-6111(12)X0004-1Molecular imaging259263http://www.medicalimagingandgraphics.com/article/PIIS0895611111001248/abstract?rss=yesAbstract: A novel imaging technique can now provide microscopic images of the distal lung in vivo, for which quantitative analysis tools need to be developed. In this paper, we present an image classification system that is able to discriminate between normal and pathological images. Different feature spaces for discrimination are investigated and evaluated using a support vector machine. Best classification rates reach up to 90% and 95% on non-smoker and smoker groups, respectively. A feature selection process is also implemented, that allows us to gain some insight about these images. Whereas further tests on extended databases are needed, these first results indicate that efficient computer based automated classification of normal vs. pathological images of the distal lung is feasible.An SVM-based distal lung image classification using texture descriptorsChesner Désir, Caroline Petitjean, Laurent Heutte, Luc Thiberville, Mathieu Salaün10.1016/j.compmedimag.2011.11.001Computerized Medical Imaging and Graphics 36, 4 (2012)2011-12-19Computerized Medical Imaging and Graphics2011-12-19364S0895-6111(12)X0004-1Microscopy264270http://www.medicalimagingandgraphics.com/article/PIIS0895611111001182/abstract?rss=yesAbstract: Stereoscopic MRA acquires a pair of blood vessel projections at two different viewing angles. Previously, we have developed two algorithms to reconstruct 3-D blood vessels from stereoscopic MRA. The assumption we made was that blood vessels were tilting circular tubes and the shape of the vessel on every cross-section was an ellipse. Since an ellipse can be represented in either algebraic form or parametric form, our previous algorithms reconstructed the ellipses by representing them in these two forms. In this paper, we further improved the accuracy of our previous algorithms by an order through two enhancements. The first improvement we made was a better method to estimate the rotation angle of the major axis of an ellipse. Instead of using the center of two adjacent ellipses to estimate the rotation angle as in our previous method, the new method used the projection lengths of the two views to estimate the angle. The second improvement we made was the equation to describe the relationship between the major/minor axes and the projection lengths. In our experiments, the average estimation error for the parametric algorithm was improved from 0.471 pixels to 0.066 pixels. The average error for the algebraic algorithm was improved from 0.101 pixels to 0.014 pixels.Three-dimensional elliptical reconstruction for stereoscopic magnetic resonance angiographyJan-Ray Liao, Shye-Chorng Kuo10.1016/j.compmedimag.2011.08.003Computerized Medical Imaging and Graphics 36, 4 (2012)2011-09-07Computerized Medical Imaging and Graphics2011-09-07364S0895-6111(12)X0004-1MRA271280http://www.medicalimagingandgraphics.com/article/PIIS0895611111001236/abstract?rss=yesAbstract: In modern epidemiological population-based studies a huge amount of magnetic resonance imaging (MRI) data is analysed. This requires reliable automatic methods for organ extraction. In the current paper, we propose a fast and accurate automatic method for lung segmentation and volumetry. Our approach follows a “coarse-to-fine” segmentation strategy. First, we extract the lungs and trachea excluding the main pulmonary vessels. This step is executed very fast and allows for measuring the volume of both structures. Thereafter, we start a refinement procedure that consists of three main stages: trachea extraction, lung separation, and filling the cavities on the final lung masks. After the trachea extraction step the volumes of both lungs without the main vessels can be measured. The final segmentation step results in the volumes of the left and right lungs including the vessels. The method has been tested by processing MR datasets from ten healthy participants. We compare our results with manually produced masks and obtain high agreement between the expert reading and our method: the True Positive Volume Fraction is more than 95%. The proposed automatic approach is fast and accurate enough to be applied in clinical routine for processing of thousands of participants.A fast and accurate automatic lung segmentation and volumetry method for MR data used in epidemiological studiesTetyana Ivanovska, Katrin Hegenscheid, Rene Laqua, Jens-P. Kühn, Sven Gläser, Ralf Ewert, Norbert Hosten, Ralf Puls, Henry Völzke10.1016/j.compmedimag.2011.10.001Computerized Medical Imaging and Graphics 36, 4 (2012)2011-11-14Computerized Medical Imaging and Graphics2011-11-14364S0895-6111(12)X0004-1MRI281293http://www.medicalimagingandgraphics.com/article/PIIS0895611111001480/abstract?rss=yesAbstract: We designed a generic method for segmenting the aneurismal sac of an abdominal aortic aneurysm (AAA) both from multi-slice MR and CT-scan examinations. It is a semi-automatic method requiring little human intervention and based on graph cut theory to segment the lumen interface and the aortic wall of AAAs. Our segmentation method works independently on MRI and CT-scan volumes and has been tested on a 44 patient dataset and 10 synthetic images. Segmentation and maximum diameter estimation were compared to manual tracing from 4 experts. An inter-observer study was performed in order to measure the variability range of a human observer. Based on three metrics (the maximum aortic diameter, the volume overlap and the Hausdorff distance) the variability of the results obtained by our method is shown to be similar to that of a human operator, both for the lumen interface and the aortic wall. As will be shown, the average distance obtained with our method is less than one standard deviation away from each expert, both for healthy subjects and for patients with AAA. Our semi-automatic method provides reliable contours of the abdominal aorta from CT-scan or MRI, allowing rapid and reproducible evaluations of AAA.3D segmentation of abdominal aorta from CT-scan and MR imagesAnthony Adam Duquette, Pierre-Marc Jodoin, Olivier Bouchot, Alain Lalande10.1016/j.compmedimag.2011.12.001Computerized Medical Imaging and Graphics 36, 4 (2012)2012-01-18Computerized Medical Imaging and Graphics2012-01-18364S0895-6111(12)X0004-1CT/MRI294303http://www.medicalimagingandgraphics.com/article/PIIS089561111200002X/abstract?rss=yesAbstract: Purpose: Organ segmentation is an essential step in the development of computer-aided diagnosis/surgery systems based on computed tomography (CT) images. A universal segmentation approach/scheme that can adapt to different organ segmentations can substantially increase the efficiency and robustness of such computer-aided systems. However, this is a very challenging problem. An initial determination of the approximate position and range of a target organ in CT images is prerequisite for precise organ segmentations. In this study, we have proposed a universal approach that enables automatic localization of the approximate position and range of different solid organs in the torso region on three-dimensional (3D) CT scans.Methods: The location of a target organ in a 3D CT scan is presented as a 3D rectangle that bounds the organ region tightly and accurately. Our goal was to automatically and effectively detect such a target organ-specific 3D rectangle. In our proposed approach, multiple 2D detectors are trained using ensemble learning and their outputs are combined using a collaborative majority voting in 3D to accomplish the robust organ localizations.Results: We applied this approach to localize the heart, liver, spleen, left-kidney, and right-kidney regions independently using a CT image database that includes 660 torso CT scans. In the experiment, we manually labeled the abovementioned target organs from 101 3D CT scans as training samples and used our proposed approach to localize the 5 kinds of target organs separately on the remaining 559 torso CT scans. The localization results of each organ were evaluated quantitatively by comparing with the corresponding ground truths obtained from the target organs that were manually labeled by human operators. Experimental results showed that success rates of such organ localizations were distributed from 99% to 75% of the 559 test CT scans. We compared the performance of our approach with an atlas-based approach. The errors of the detected organ-center-positions in the successful CT scans by our approach had a mean value of 5.14 voxels, and those errors were much smaller than the results (mean value about 25 voxels) from the atlas-based approach. The potential usefulness of the proposed organ localization was also shown in a preliminary investigation of left kidney segmentation in non-contrast CT images.Conclusions: We proposed an approach to accomplish automatic localizations of major solid organs on torso CT scans. The accuracy of localizations, flexibility of localizations of different organs, robustness to contrast and non-contrast CT images, and normal and abnormal patient cases, and computing efficiency were validated on the basis of a large number of torso CT scans.Automatic localization of solid organs on 3D CT images by a collaborative majority voting decision based on ensemble learningXiangrong Zhou, Song Wang, Huayue Chen, Takeshi Hara, Ryujiro Yokoyama, Masayuki Kanematsu, Hiroshi Fujita10.1016/j.compmedimag.2011.12.004Computerized Medical Imaging and Graphics 36, 4 (2012)2012-03-15Computerized Medical Imaging and Graphics2012-03-15364S0895-6111(12)X0004-1CT304313http://www.medicalimagingandgraphics.com/article/PIIS0895611112000316/abstract?rss=yesAbstract: Positron Emission Tomography (PET) offers the possibility to quantitatively measure the radiotracer distribution in tissues. In order to obtain images of these tissues, the detection probability matrix (DPM) must be accurately determined. Usually, DPM is analytically calculated. However, this approach does not take into account the whole probabilistic interactions of the photons. On the other hand, Monte Carlo simulations (MC) are more accurate to calculate the DPM as they selectively consider diverse photon interactions. In this work, MC DPM (MCDPM) and analytically calculated DPM (ACDPM) were compared in terms of image quality. The results showed that the images obtained from the MCDPM were qualitatively better resolved and provided a significant improvement of the signal-to-noise ratio (SNR). The MCDPM yielded to an increase of up to 40% in SNR and up to 25% in contrast in comparison with ACDPM. On the other hands, MCDPM enhanced the counts distribution by more than 12% with respect to ACDPM.A comparison of a Monte Carlo-based detection probability matrix with analytical probability matrix for small animal PET scannersOtman Sarrhini, M’hamed Bentourkia10.1016/j.compmedimag.2012.02.001Computerized Medical Imaging and Graphics 36, 4 (2012)2012-03-06Computerized Medical Imaging and Graphics2012-03-06364S0895-6111(12)X0004-1PET314324http://www.medicalimagingandgraphics.com/article/PIIS089561111200033X/abstract?rss=yesAbstract: Vessel segmentation in photographies of the retina is needed in a set of computer-supported medical applications related to diagnosis and surgery planning. Considering each pixel in an image as a point in a feature space, segmentation is a binary classification problem where pixels need to be assigned to one of two classes: object and background. We describe a paradigm of hysteresis-classifier design that we apply to the problem of vessel segmentation. Before classification, a multidimensional feature vector is computed for each pixel, such that in the corresponding feature space, vessels and background are more separable than in the original image space. Several classifiers that stem from the hysteresis-classifier design paradigm are tested with this feature space on publicly available databases. These classifiers are very fast and achieve results that are comparable or even superior to known dedicated methods. Hysteresis-based classifiers represent a fast and accurate solution for the retinal-vessel segmentation problem.Segmentation of retinal vessels with a hysteresis binary-classification paradigmAlexandru Paul Condurache, Alfred Mertins10.1016/j.compmedimag.2012.02.002Computerized Medical Imaging and Graphics 36, 4 (2012)2012-03-15Computerized Medical Imaging and Graphics2012-03-15364S0895-6111(12)X0004-1Retinal vessels325335http://www.medicalimagingandgraphics.com/article/PIIS0895611112000328/abstract?rss=yesAbstract: Objective: Segmentation is a necessary step when creating realistic three-dimensional (3D) models. In order to build 3D models of whole body structures and have a wider lateral application, the thin sectional anatomical images of the Chinese Visible Human (CVH) dataset should be segmented. The more detailed structures are segmented to provide greater potential for wider application of the segmented images.Materials and methods: All the images based on the CVH male and female dataset were segmented semi-automatically using PHOTOSHOP software. This research lasted about 7 years.Result: In this study, 869 structures of CVH male and 860 structures of CVH female were semi-automatically segmented, and the formats for the segmented color-filled image data were PSD and PNG. In these segmented structures, nearly all skeletal muscles included muscle belly and tendon, and hollow organs included their organ walls and their lumen. Most nerve trunks, small arteries, lymph nodes, and lymph ducts were also segmented. Many surface-rendering and volume-rendering organ models were created using these segmented images.Conclusion: The CVH male and female images represent the normal Asian population. After segmentation, the images can be reconstructed directly in 3D and greatly facilitate the biological modeling of physical and physiological information, a great help in improving medical and biological science in China.Creation of a female and male segmentation dataset based on Chinese Visible Human (CVH)Yi Wu, Li-Wen Tan, Ying Li, Bin-Ji Fang, Bing Xie, Tong-Ning Wu, Qi-Yu Li, Ming-Guo Qiu, Guang-Jiu Liu, Kai Li, Hao-Tong Xu, Na Luo, Shao-Xiang Zhang10.1016/j.compmedimag.2012.01.003Computerized Medical Imaging and Graphics 36, 4 (2012)2012-03-05Computerized Medical Imaging and Graphics2012-03-05364S0895-6111(12)X0004-1Cryosection anatomical images336342http://www.medicalimagingandgraphics.com/article/PIIS0895611112000298/abstract?rss=yesThe author would like to draw the readers’ attention to the following: This is a short correction note to the article titled “Nonparametric joint shape learning for customized shape modeling” . In the article, the following references to previous works and their referencing points in the text are updated to better reflect the segmentation literature.Corrigendum to “Nonparametric joint shape learning for customized shape modeling” [Comput. Med. Imaging Graph. 34 (2010) 298–307]Gozde Unal10.1016/j.compmedimag.2012.01.001Computerized Medical Imaging and Graphics 36, 4 (2012)2012-02-15Computerized Medical Imaging and Graphics2012-02-15364S0895-6111(12)X0004-1Corrigendum343343http://www.medicalimagingandgraphics.com/article/PIIS0895611112000560/abstract?rss=yesEditorial Board10.1016/S0895-6111(12)00056-0Computerized Medical Imaging and Graphics 36, 4 (2012)2012-06-01Computerized Medical Imaging and Graphics2012-06-01364S0895-6111(12)X0004-1II