Computerized Medical Imaging and Graphics This is an RSS file. You can use it to subscribe to this data in your favourite RSS reader or to display this data on your own website or blog.

A dynamic tree-based registration could handle possible large deformations among MR brain images
(Source: Computerized Medical Imaging and Graphics)
Source: Computerized Medical Imaging and Graphics - May 13, 2016 Category: Radiology Authors: Pei Zhang, Guorong Wu, Yaozong Gao, Pew-Thian Yap, Dinggang Shen Source Type: research

Stacking denoising auto-encoders in a deep network to segment the brainstem on MRI in brain cancer patients: a clinical study
Cancer is a leading cause of death and disability worldwide, accounting for 14.1 million of new cancer cases and 8.2 million deaths in 2012 [1]. Among available techniques to treat brain tumors, radiotherapy and radio surgery have often become the selected treatment, especially when others techniques such as surgery or chemotherapy might not be applicable. To constrain the risk of severe toxicity of critical brain structures, i.e. the organs at risk (OARs), the volume measurements and the localization of these structures are required. (Source: Computerized Medical Imaging and Graphics)
Source: Computerized Medical Imaging and Graphics - May 11, 2016 Category: Radiology Authors: Jose Dolz, Nacim Betrouni, Mathilde Quidet, Dris Kharroubi, Henri A. Leroy, Nicolas Reyns, Laurent Massoptier, Maximilien Vermandel Source Type: research

WITHDRAWN: Adaptive Swarm Balancing Algorithms for rare-event prediction in imbalanced healthcare data
This article has been withdrawn at the request of the author(s) and/or editor. The Publisher apologizes for any inconvenience this may cause.The full Elsevier Policy on Article Withdrawal can be found at http://www.elsevier.com/locate/withdrawalpolicy. (Source: Computerized Medical Imaging and Graphics)
Source: Computerized Medical Imaging and Graphics - May 9, 2016 Category: Radiology Authors: Jinyan Li, Lian-sheng Liu, Simon Fong, Raymond K. Wong, Sabah Mohammed, Jinan Fiaidhi, Yunsick Sung, Kelvin K.L. Wong Source Type: research

Adaptive Swarm Balancing Algorithms for rare-event prediction in imbalanced healthcare data
Big Data in medical fields, such as hospital informatization construction, the progress of treatments, and the extensive use of high-throughput equipment, have caused a geometric growth of attentions. It has been desirable to improve the efficiency, accuracy and quality of medical data processing (Jee and Kim, 2013). The sources of health data include clinical medical treatments, pharmaceutical companies, medical research, medical assistance application, and more. Existing datasets bring in important medical and health information for research topics, such as understanding of the human genetic and disease systems (Joyce an...
Source: Computerized Medical Imaging and Graphics - May 9, 2016 Category: Radiology Authors: Jinyan Li, Lian-sheng Liu, Simon Fong, Raymond K. Wong, Sabah Mohammed, Jinan Fiaidhi, Yunsick Sung, Kelvin K.L. Wong Source Type: research

Adaptive Swarm Balancing Algorithms for Rare-event Prediction in Imbalanced Healthcare Data
(Source: Computerized Medical Imaging and Graphics)
Source: Computerized Medical Imaging and Graphics - May 9, 2016 Category: Radiology Authors: Jinyan Li, Lian-sheng Liu, Simon Fong, Raymond K. Wong, Sabah Mohammed, Jinan Fiaidhi, Yunsick Sung, Kelvin K.L. Wong Source Type: research

Skin Lesion Image Segmentation Using Delaunay Triangulation for Melanoma Detection
Melanoma is one of the most aggressive tumors in humans [1] and it can be lethal, if not diagnosed on time. The incidence of melanoma among all dermatologic cancers is 4%, while melanoma-induced mortality accounts for about 80% of deaths from skin cancer; only 14% of patients with metastatic melanoma survive for five years [2]. Moreover, malignant melanoma has a cure rate of more than 95% if detected at an early stage [3]. The above statistics demonstrate that there is an urgent need to develop innovative strategies able to increase the diagnostic accuracy and to help dermatologists making early diagnosis. (Source: Compute...
Source: Computerized Medical Imaging and Graphics - May 6, 2016 Category: Radiology Authors: Andrea Pennisi, Domenico D. Bloisi, Daniele Nardi, Anna Rita Giampetruzzi, Chiara Mondino, Antonio Facchiano Source Type: research

Comparison of algebraic and analytical approaches to the formulation of the statistical model-based reconstruction problem for x-ray computed tomography
This paper is closely related to a basic medical imaging technique which is called Computed Tomography (CT). In particular, it is concerned with the problem of formulating image reconstruction from projections algorithms, which are the most important things for the development of this technique. When considering the reconstruction methods used in this type of medical imaging, the highly destructive effects of the x-ray radiation used in CT must be taken into account. It is argued that this kind of radiation is harmful to the health of patients being examined because it can lead to many serious illnesses, and this therefore...
Source: Computerized Medical Imaging and Graphics - May 5, 2016 Category: Radiology Authors: Robert Cierniak, Anna Lorent Source Type: research

Network-Based Classification of ADHD Patients Using Discriminative Subnetwork Selection and Graph Kernel PCA
As one of the most prevalent behavioral disorders, attention deficit hyperactivity disorder (ADHD) is diagnosed in nearly 5% of children and 2-4% of adults [1,2]. For patients with ADHD, it is difficult to control their behaviors and focus their attentions, which adversely affect their social function and academic performance [3,4]. Meanwhile, nowadays diagnosis of ADHD is very challenging in clinic and the misdiagnose rate is usually high [5]. Therefore, developing more accurate and automatic diagnostic methods for ADHD is of great importance. (Source: Computerized Medical Imaging and Graphics)
Source: Computerized Medical Imaging and Graphics - April 22, 2016 Category: Radiology Authors: Junqiang Du, Lipeng Wang, Biao Jie, Daoqiang Zhang Source Type: research

Efficient visibility-driven medical image visualisation via adaptive binned visibility histogram
The advent of efficient volume rendering algorithms and powerful graphical processing units (GPUs) has enabled the introduction of direct volume rendering (DVR) visualisation that provides three-dimensional (3D) views and interactive navigation. DVR has been broadly applied to medical images in clinical diagnosis (Kim et al., 2004), planning for surgery/radiotherapy (Kruger et al., 2008), and training (Georgii et al., 2007). In DVR, transfer functions (TF) are used to control the optical properties of data value (intensity) in a volume and play an important role in defining a satisfactory visualisation. (Source: Computeriz...
Source: Computerized Medical Imaging and Graphics - April 18, 2016 Category: Radiology Authors: Younhyun Jung, Jinman Kim, Ashnil Kumar, David Dagan Feng, Michael Fulham Source Type: research

Atlas-based Rib-Bone Detection in Chest X-rays
The National Library of Medicine has developed a portable chest X-ray (CXR) screening system to automatically detect the lung abnormalities in countries where health resources are constrained  [1–3]. The system extracts the texture and shape properties of lung regions from CXR images, and identifies the abnormality using image processing and machine learning algorithms. On a typical CXR, the bone structures overlap with the lung tissue due to the 2D projection of the chest. The rib-cage causes a cross-hatching pattern on the lung region, which misleads the texture analysis  [4–7]. (Source: Computerized Medical Imaging and Graphics)
Source: Computerized Medical Imaging and Graphics - April 12, 2016 Category: Radiology Authors: Sema Candemir, Stefan Jaeger, Sameer Antani, Ulas Bagci, Les R. Folio, Ziyue Xu, George Thoma Source Type: research

Multi-Modal Vertebrae Recognition using Transformed Deep Convolution Network
Magnetic resonance imaging (MR) and computed tomography (CT) are two main imaging methods that are intensively and interchangeably used by spine physicians. The longitudianl/differential diagnoses today are often conducted in large MR/CT dataset which makes manual identification of vertebrae a tedious and time-consuming task. Automatic locate-and-name system of spine MR/CT images which supports quantitative measurement is thus highly demanded for orthopaedics, neurology, and oncology. Automatic vertebra recognition, particularly the identification of vertebra location, naming, and pose (orientation+scale), is a challenging...
Source: Computerized Medical Imaging and Graphics - April 7, 2016 Category: Radiology Authors: Yunliang Cai, Mark Landis, David T.Laidley, Anat Kornecki, Andrea Lum, Shuo Li Source Type: research

A novel methodology for personalized simulations of ventricular hemodynamics from noninvasive imaging data
Cardiac pathologies often show a high interindividual variability in both the anatomy and the response to treatment, making population-based metrics less effective in defining therapy. A patient-specific approach is therefore crucial for successfully evaluating the pump function in the diseased heart and customizing treatment to the patient’s pathophysiology. Recent developments in clinical imaging have underpinned the value of personalized medicine as a powerful alternative to traditional healthcare. (Source: Computerized Medical Imaging and Graphics)
Source: Computerized Medical Imaging and Graphics - April 1, 2016 Category: Radiology Authors: A. de Vecchi, A. Gomez, K. Pushparajah, T. Schaeffter, J.M. Simpson, R. Razavi, G.P. Penney, N.P. Smith, D.A. Nordsletten Source Type: research

Quantitative normal thoracic anatomy at CT
The detection of abnormalities on any imaging examination is made possible by first having a thorough knowledge of the normal anatomy and/or function of an organ system under study (i.e., an understanding of what is considered to be normal), and then by characterizing deviations from this normal. In clinical practice, radiological examinations are typically performed in a descriptive and qualitative manner. Although this approach may be useful to describe pertinent findings and to provide an overview of a patient's status, it is imprecise, subjective, and insensitive to small deviations from normal. (Source: Computerized M...
Source: Computerized Medical Imaging and Graphics - March 31, 2016 Category: Radiology Authors: Monica M.S. Matsumoto, Jayaram K. Udupa, Yubing Tong, Babak Saboury, Drew A. Torigian Source Type: research

Scatter to Volume Registration for Model-free Respiratory Motion Estimation from Dynamic MRIs
Geometric uncertainties caused by respiratory motion remain a significant source of errors in a wide range of image acquisition applications and image-guided interventions. For example, in radiotherapy treatments in the thorax and upper abdomen, respiration complicates the precision of tumor localization and causes healthy tissues to be radiated. In 3-D imaging with a long acquisition time (such as Positron Emission Tomography (PET)), respiratory motion degrades the image quality and cause motion artifacts. (Source: Computerized Medical Imaging and Graphics)
Source: Computerized Medical Imaging and Graphics - March 19, 2016 Category: Radiology Authors: S. Miao, Z.J. Wang, L. Pan, J. Butler, G. Moran, R. Liao Source Type: research

Statistical shape analysis of subcortical structures using spectral matching
Quantifying groupwise neuroanatomical shape differences has become an important topic in neuroscience as well as in neuroimaging studies, since brain morphometry has been hypothesized to be linked to various neurological disorders [1]. Recent advances in medical image analysis have led to several morphological studies on different pathologies including schizophrenia [2] and Alzheimer's disease [3]. Early studies on brain morphology were based on volumetric analysis, which had the advantage of simplicity [3,4]. (Source: Computerized Medical Imaging and Graphics)
Source: Computerized Medical Imaging and Graphics - March 15, 2016 Category: Radiology Authors: Mahsa Shakeri, Herve Lombaert, Alexandre N. Datta, Nadine Oser, Laurent Létourneau-Guillon, Laurence Vincent Lapointe, Florence Martin, Domitille Malfait, Alan Tucholka, Sarah Lippé, Samuel Kadoury, for the Alzheimer's Disease Neuroimaging Initiative Source Type: research