Search

According to the data of the Turkish Public Health Institution Cancer Department, cancer is seen in 161 thousand people annually in our country. Malignant tumor is called cancer. Brain tumor disease is a common disease in our country. Brain tumors are growing fast. The time to be noticed and, accordingly, to start treatment is important. If there is a tumor in the brain, its type (benign, malignant) should be determined. Early diagnosis is vital. This process, which is determined by experts, can take a long time and there is a possibility of making mistakes. For this reason, by including artificial intelligence methods in the detection process of brain tumors, the time can be shortened and the probability of error can be reduced. For this purpose, a study was conducted using Convolutional Neural Networks, one of the deep learning algorithms. In the study, 6083 MR images were used. The data set was primarily classified according to whether there was a brain tumor and was divided into 70% training and 30% testing. These classified images are binarized in order to train the model comfortably. CNN deep learning model was applied to the pre-processed data set and the accuracy rate was found to be 99%. [ABSTRACT FROM AUTHOR]

Copyright of CISTI (Iberian Conference on Information Systems & Technologies / Conferência Ibérica de Sistemas e Tecnologias de Informação) Proceedings is the property of Conferencia Iberica de Sistemas Tecnologia de Informacao and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Revolution in medical imaging systems generate high-resolution images. This revolution has created new challenges in accessing, sharing, archiving, and protecting medical images. The number of these images has also increased significantly over the past decade, which is create another challenge. Recently, the health care industry has started noticing cloud computing as a solution because of its elasticity and scalability, which contribute to avoiding hardware obsolescence, providing universal access to medical images anywhere and anytime, and increasing their availability. This paper introduces the main characteristics of the cloud-based picture archiving and communication system (PACS) and highlights its technical and nontechnical advantages. Moreover, this paper illustrates challenges in cloud-based medical image exchange, regulation, and interoperability as well as how medical image existence can affect cloud users. Furthermore, the paper concludes with directions for future research in medical imaging. [ABSTRACT FROM AUTHOR]

Copyright of CISTI (Iberian Conference on Information Systems & Technologies / Conferência Ibérica de Sistemas e Tecnologias de Informação) Proceedings is the property of Conferencia Iberica de Sistemas Tecnologia de Informacao and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Revolution in medical imaging systems generate high-resolution images. This revolution has created new challenges in accessing, sharing, archiving, and protecting medical images. The number of these images has also increased significantly over the past decade, which is create another challenge. Recently, the health care industry has started noticing cloud computing as a solution because of its elasticity and scalability, which contribute to avoiding hardware obsolescence, providing universal access to medical images anywhere and anytime, and increasing their availability. This paper introduces the main characteristics of the cloud-based picture archiving and communication system (PACS) and highlights its technical and nontechnical advantages. Moreover, this paper illustrates challenges in cloud-based medical image exchange, regulation, and interoperability as well as how medical image existence can affect cloud users. Furthermore, the paper concludes with directions for future research in medical imaging. [ABSTRACT FROM AUTHOR]

The recent advancements under the umbrella of artificial intelligence (AI) open opportunities to tackle complex problems related to image analysis. Recently, the proliferation of COVID-19 brought multiple challenges to medical practitioners, such as precise analysis and classification of COVID-19 cases. Deep learning (DL) and transfer learning (TL) techniques appear to be attractive solutions. To provide the precise classification of COVID-19 cases, this article presents a customized Deep Convolutional Neural Network (DCNN) and pre-trained TL model approach. Our pipeline accommodated several popular pre-trained TL models, namely DenseNet121, ResNet50, InceptionV3, EfficientNetB0, and VGG16, to classify COVID-19 positive and negative cases. We evaluated and compared the performance of these models with a wide range of measures, including accuracy, precision, recall, and F1 score for classifying COVID-19 cases based on chest X-rays. The results demonstrate that our customized DCNN model performed well with randomly assigned weights, achieving 98.5% recall and 97.0% accuracy. [ABSTRACT FROM AUTHOR]

Clinical image data analysis is an active area of research. Integrating such data in a Clinical Data Warehouse (CDW) implies to unlock the PACS and RIS and to address interoperability and semantics issues. Based on specific functional and technical requirements, our goal was to propose a web service (I4DW) that allows users to query and access pixel data from a CDW by fully integrating and indexing imaging metadata. Here, we present the technical implementation of this workflow as well as the evaluation we carried out using a prostate cancer cohort use case. The query mechanism relies on a Dicom metadata hierarchy dynamically generated during the ETL Process. We evaluated the Dicom data transfer performance of I4DW, and found mean retrieval times of 5.94 seconds and 0.9 seconds to retrieve a complete DICOM series from the PACS and all metadata of a series. We could retrieve all patients and imaging tests of the prostate cancer cohort with a precision of 0.95 and a recall of 1. By leveraging the CMOVE method, our approach based on the Dicom protocol is scalable and domain-neutral. Future improvement will focus on performance optimization and de identification. [ABSTRACT FROM AUTHOR]

In the past few years the main Lithuanian hospitals that provide nuclear medicine services have updated their SPECT/CT systems. The novel SPECT/CT systems allow us to acquire improved image quality, shorter acquisition and new reconstruction algorithms. Systems with CZT detectors provide higher sensitivity, better energy resolution and image contrast. However, due to the different technical approaches used by vendors, image quality may vary, thus the comparison of diagnostic information between the systems is not straightforward. Harmonization of the clinical protocols would allow to minimize an equipment-based images differences and help uniform the follow-up assessments. The purpose of this work was to acquire scintigraphic images of the phantoms with the different manufacturers systems and compare images using the clinical bone scintigraphy protocol reconstructions and identify parameters for scanning protocol harmonization. Images were obtained and reconstructed by three SPECT/CT systems: GE NM/CT 870 CZT, SIEMENS Symbia Intevo Excel, Mediso AnyScan SC. For the evaluation of the different parameters Jaszczak, NEMA IQ phantom and capillary point sources were used. The phantoms were filled with the same activity of 99mTc solution. SPECT and CT scans were acquired for the standard bone SPECT/CT protocol and for unify protocol. Reconstructions of the images were performed using site approved standard parameters, while using various filters and reconstructions algorithms. Investigation of the phantoms revealed the main differences of SPECT/CT systems. Different detection technologies, reconstructions algorithms and concepts of the equipment add some limitations to the harmonization. Nevertheless, new technologies and image post processing algorithms used in all systems allow to decrease acquisition time and administered activity to the patients almost without losing image quality. Subsequently this results in reduced exposure of ionizing radiation to the patients and medical staff. [ABSTRACT FROM AUTHOR]

The paper deals with advances in medical physics during the last 60 years and share some thoughts on the future. Some of today's advances and challenges in medical physics applied to radiation therapy, diagnostic radiology, nuclear medicine, MR-imaging and radiation safety will be discussed. To be prepared for the future, we need continued good undergraduate education, advanced postgraduate courses as well as active research in the different fields of medical physics. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) applications are particularly promising in the field of medical imaging. Especially in radiology, research presents various AI uses cases, highlighting AI applications' potential to improve the quality and efficiency of healthcare. Further, despite numerous research projects of AI applications, an investigation from the realworld, practice-based point of view regarding AI applications is lacking. Consequently, little is known about medical imaging specialists' perspective on AI applications. Following the Grounded Theory Methodology, we conducted 15 semi-structured interviews with medical imaging specialists. We derived four opportunities and five concerns representing medical imaging specialists' perspective on AI applications. [ABSTRACT FROM AUTHOR]

Progress on the development of awearable ultrasonic bladder monitoring device is reported. The device is intended to help in the diagnosis of urinary incontinence of both young and elderly patients.We present all the components of the device - the textile band, electronics, as well as the early results of reconstruction algorithms. [ABSTRACT FROM AUTHOR]

Software engineering involves writing new code or editing existing code. Recent efforts have investigated the neural processes associated with reading and comprehending code -- however, we lack a thorough understanding of the human cognitive processes underlying code writing. While prose reading and writing have been studied thoroughly, that same scrutiny has not been applied to code writing. In this paper, we leverage functional brain imaging to investigate neural representations of code writing in comparison to prose writing. We present the first human study in which participants wrote code and prose while undergoing a functional magnetic resonance imaging (fMRI) brain scan, making use of a full-sized fMRI-safe QWERTY keyboard. We find that code writing and prose writing are significantly dissimilar neural tasks. While prose writing entails significant left hemisphere activity associated with language, code writing involves more activations of the right hemisphere, including regions associated with attention control, working memory, planning and spatial cognition. These findings are unlike existing work in which code and prose comprehension were studied. By contrast, we present the first evidence suggesting that code and prose writing are quite dissimilar at the neural level. [ABSTRACT FROM AUTHOR]

The production of medical imaging data has grown tremendously in the last decades. The proliferation of digital acquisition equipment has enabled even small institutions to produce considerable amounts of studies. Furthermore, the general trend for new imaging modalities is to produce more data per examinations. As a result, the design and implementation of tomorrow's storage and communication systems must deal with Big Data issues. Moreover, new realities such as the outsourcing of medical imaging infrastructures to the Cloud impose additional pressure on these systems. The research on technologies for coping with Big Data issues on large scale medical imaging environments is still in its early stages. This is mostly due to the difficulty of implementing and validating new technological approaches in real environments, without interfering with clinical practice. Therefore, it is crucial to create test bed environments for research purposes. This article proposes a methodology for creating simulated Big Data repositories. The system is able to use a real world repository to collect data from a representative time window and expand it according to research needs. In addition, the solution provides anonymization tools and allows exporting two types of simulated data: a structured file repository containing DICOM objects and a statistical summary of the archive content based on its characteristics, such as the number of produced studies per day, their modality and their associated data volumes. [ABSTRACT FROM AUTHOR]

This work introduces a tool specifically designed to help pathologists in their daily work. The software tool integrates several applications related to different tumoral parameters very useful to analyze and detect tumours. All the proposed algorithms have in common the use of the most suitable colour space in every case in order to isolate the different tissues and therefore, to perform an appropriate segmentation. Results are presented for every single application, showing a great deal of accuracy in most cases, in comparison with that obtained by specialists in a manual way. The tool contributes to a higher level of assurance when estimating the seriousness of a tumour and its subsequent diagnosis. [ABSTRACT FROM AUTHOR]

Medical imaging plays an important role in the field of healthcare industry both in clinical settings and in research and development. It is used in prevention, early detection of disease, in choosing the optimal treatment, during surgical interventions and monitoring of the treatment effects. Despite much advancement in the last few decades, rapid change on its technology development and variety of imaging parameters that differ with the manufacturer restrict its further development. Imaging phantom is a calibrating medium that is scanned or imaged in the field of medical imaging to evaluate, analyze and tune the performance of various imaging devices. A phantom used to evaluate an imaging device should respond in a similar manner to how human tissue and organs would act in that specific imaging modality. There has been many research on the phantom materials; however, there has been no attempt to study on the material that mimics the structure of lung or fibrous tissue. So with the need for development of gel with such structure, we tried to mimic this structure with aerogel. Silica aerogels have unique properties that include low density (0.003g/cm) and mesoporosity (pore size 2-50nm), with a high thermal insulation value (0.005W/mK) and high surface area (500-1200m- 2/g). ] In this study, we cross-linked with di-isocyanate, which is a group in polyurethane to covalently bond the polymer to the surface of silica aerogel to enhance the mechanical properties. By formation of covalent bonds, the structure can be reinforced by widening the interparticle necks while minimally reducing porosity. [ABSTRACT FROM AUTHOR]

Most image reconstruction problems are under-determined: there are far more pixels to be resolved than there are measurements available. This means that the image space has more degrees of freedom than the measurement space. To make headway in such under-determined image reconstruction problems one must either incorporate domain knowledge or regularize. Domain knowledge restricts the size of the image space while regularization introduces bias, e.g., by forcing the reconstructed image to be smooth or have limited support. Both approaches are equivalent and can be interpreted as making the image sparse in some domain. This paper will provide a selective overview of some of the principal methods of sparsity regularized image reconstruction. [ABSTRACT FROM AUTHOR]

The usage paradigm of PACS (Picture Archive and Communications Systems) has been suffering significant alterations throughout the years. Recently, pushed by new services related to Cloud and Web technologies, the usage of PACS in geographically distributed medical environments has promised significant productivity gains as well as increased quality medical services. However, the usage of PACS to support radiology workflows, previously local to institutions, in remote environments still raises great technological and technical challenges to PACS administrators. The following article describes the most common workflows associated with the radiology service and proposes a computer method for their optimization. The proposed method provides an automatic framework for scheduling and performing repetitive tasks without human interaction. Moreover, it was designed to optimize the workflows associated with distributed PACS scenarios by enabling prefetching rules to be applied to medical image studies. The idea is to leverage multiple indicators associated with the radiology workflows in order to predict whether a given study is likely to be requested, and anticipate it's transference procedure so that the study is already available when requested. [ABSTRACT FROM AUTHOR]

There have been many attempts to implement traditional telemedicine across the world especially in the developing countries, but the efforts has been characterized with challenges such as high-cost of sustaining telemedicine solutions and non-availability of medical expertise. Cancerous Skin disease such as melanoma and nevi typically results from environmental factors (such as exposure to sunlight) among other causes. The necessary tools needed for early detection of these diseases are still not a reality in most African communities. In recent years, there have been high expectations for techniques such as Dermoscopy or Epiluminiscence Light Microscopy (ELM) in aiding diagnosis; however evaluation of pigmented skin lesions using ELM is not only non-affordable by most of African communities but also complex and highly subjective, thus motivating researches in diagnosis automation. This study would focus on designing and modeling a system that will collate past Pigmented Skin Lesion (PSL) image results, their analysis, corresponding observations and conclusions by medical experts using prototyping methodology. These wealth of information would be used as a library. A part of the system would use computational intelligence technique to analyze, process, and classify the image library data based on texture and possibly morphological features of the images. Trained medical personnel in a remote location can use mobile data acquisition devices (such as cell phone) to generate images of PSL, supply such images as input to the proposed system, which in turns should intelligently be able to specify the malignancy (life-threatening) or benign (non-threatening) status of the imaged PSL. [ABSTRACT FROM AUTHOR]

Most anthropometrical measurements today are based on using such standard tools as anthropometers, calipers and tape measures. Automatization of measurement process with high speed and accuracy using non-contact scanners can give significant benefit for industry and for customers. The problem of digital surface reconstruction and surface measurement is especially important in medicine: for facial surgery simulation, diagnosis of craniofacial anomalies, trauma to the head, and for reconstructive surgery. Different approaches and equipment have been developed for the solution of this problem; for example, the photogrammetric method based on the principle of rasterstereography [1], a moiré - based light projection system [2], and the 3D reconstruction system [3]. All these methods are based on non-contact measurement principles. The surface digitization system based on a contact method is presented in [4]. The systems described above have many unresolved problems, (such, for example, as a time consuming analysis of the pattern of the object in order to obtain its digital image [1]; a lengthy calibration procedure and intensive computation (off-line processing of data) [2]; huge size and weight, high cost of the system [3]; slow data acquisition and restricted accuracy due to friction of a probe with a surface [4]). Thus the need of a simple, cheap and fast 3D digital surface reconstruction system still exists today. The system presented in this paper allows one to solve these problems. [ABSTRACT FROM AUTHOR]

Prediction markets are forums aimed at predicting the outcome of future events of interest such as election results. People participate in a prediction market by buying contracts on the possible outcomes. They are rewarded after the outcome is known based on the number of contracts purchased for the correct outcome. The Artificial Prediction Market is a novel machine learning method that simulates a prediction market where the participants are trained classifiers instead of people. In this work we present an application of the Artificial Prediction Market to lymph node detection from CT images. An evaluation on 54 CT volumes shows that the detector trained with the Artificial Prediction Market has a detection rate of 81.2% at 3 false positives per volume, while an Adaboost classifier trained on the same features obtains a detection rate of 79.6% at the same false positive rate. [ABSTRACT FROM PUBLISHER]

Radiation protection plays an important role in all applications of ionizing radiation technologies used in medicine, including those applied in imaging modalities based on the use of X-rays and radiopharmaceuticals. In all these applications, ensuring the adequate protection of personnel, patients and the public in accordance with the relevant national and international safety standards is a requirement. The paper deals with some specific aspects of radiation protection associated with the use of ionizing radiation in medical imaging, which is an inherent part of bioengineering techniques. After a short summary of radiation protection principles relevant to bioengineering, the exposure of patients from various radiation imaging procedures is summarized. While the effective dose to personnel is usually well below dose limit levels, there are some modalities, such as the PET, where it has been observed that the equivalent dose to extremities of persons handling some radiopharmaceuticals may exceed the relevant dose limit. [ABSTRACT FROM PUBLISHER]

Skull stripping is the process of isolating brain from non-brain tissues. It supplies major significance in both medical and image processing fields. Nevertheless, the manual process of skull stripping is challenging due to the complexity of images, time consuming and prone to human errors. This paper proposes a qualitative analysis of skull stripping accuracy for Magnetic Resonance Imaging (MRI) brain images. The skull stripping of eighty MRI images is performed using Seed-Based Region Growing (SBRG). The skull stripped images are then presented to three experienced radiographers to visually evaluate the level of skull stripping accuracy. The level of accuracy is divided into five categories which are “over delineation”, “less delineation”, “slightly over delineation”, “slightly less delineation” and “correct delineation”. Primitive statistical methods of mode, mean and standard deviation are calculated to examine the qualitative performances of skull stripping capability. In another note, Fleiss Kappa statistical analysis is used to measure the agreement among the radiographers. The qualitative performances analysis proved that the SBRG is an effective technique for skull stripping. The reliability of agreement significances among the radiographers is found to be substantial. [ABSTRACT FROM PUBLISHER]

During the last decade, medical imaging services have assumed a central role in healthcare institutions, and they are nowadays a decisive factor for the quality of diagnostic and treatments. Health stakeholders and policy makers have been steadily adopting PACS and DICOM standard, simplifying interoperability between distinct equipment and institutions. To assist images' interpretation, several visualization solutions emerged. However, these applications are targeted to specific operating systems, hindering its ubiquitous use, in increasing web-based working environments. In this paper we present a Web-based DICOM viewer that was entirely developed with web technology, namely HTML5 and JavaScript. The result is a visualization station that is already in use in two medical imaging centres and that can be accessed through a common web browser, from any computer, mobile device, or operation system. [ABSTRACT FROM PUBLISHER]

The usage of computational systems in medicine is changing from traditional computers to mobile devices with high performance wireless network connections and high definition touch screen user interface. Medical imaging like other clinical information systems, follow that paradigm. Although Medical thermography is the second oldest modality of medical imaging, it has been disregarded for years. However recent technological improvements and the definition of standard capture protocols raised the interest in its usage in recent years. It is presented in this article the requirements that future medical thermography applications should include to be successful in common clinical practice. [ABSTRACT FROM PUBLISHER]

Nowadays PACS (Picture Archive and Communication System) tends to integrate web-based technologies in processes associated to storage, distribution and visualization of medical images, creating the general abstraction of distributed PACS. Although PACS integration with web-based technologies offer significant advantages to healthcare institutions, it is crucial that information technology based issues do not impose constraints in the medical practice workflow. Therefore, distributed PACS have to deal with performance issues in both storing and retrieving of large amounts of data across distinct systems, possibly hosted on different locations. This paper proposes an approach to reduce data transference footprint in a distributed PACS environment with DICOM-Ready applications. The proposed method provides a high level control of transference parameters, such as, number of connections, number of fragments and size of each fragment. The result was a highly tunable data stream that can be used in any distributed PACS environment. [ABSTRACT FROM AUTHOR]

The Radiology departments are increasingly taking advantage of Information Technologies (IT) to enhance the efficiency and quality of patient care services. These IT systems are normally able to handle huge amounts of digital data and to extract relevant fingerprints useful to improve the quality of clinical practice. However, they provide multiple and heterogeneous databases and informational environments, namely regarding to the information stored in Picture Archiving and Communication Systems (PACS). The heterogeneous of environments make the access to the information a challenge to extract relevant data. This paper presents the deployment and validation process of the Dicoogle system in two health care facilities. This system represents a new approach able to collect and index information from distinct PACS archives, developed on top of Dicoogle, which allow the construction of multiple views over data repositories according to the standard Digital Imaging and Communication in Medicine (DICOM), in a flexible and fast way. The developed methodology can contribute to improve the use of DICOM metadata, stored over disperse PACS of radiology departments, which otherwise not be used in productivity, efficiency and quality initiatives at radiology departments. [ABSTRACT FROM AUTHOR]

Medical devices these days come with very high dynamic range outputs to diagnose various diseases. This high dynamic range images should not only be compressed but also the contrast of the image must be enhanced to preserve the details on common display devices. Such algorithms are usually run off-line on images due to the high cost of implementation. This paper looks into the implementation of Balanced Contrast Limited Adaptive Histogram Equalization (BCLAHE) for Adaptive Dynamic Range Compression (ADRC) of real time medical images. This method is specifically targeted at situations where continuous exposure is required. For example in X-ray, CT-Scan or IR imaging, the real time video of the target is observed until the region of interest (ROI) is identified. The proposed implementation scheme is tested and has shown good results in terms of latency and perceptibility of minute details. [ABSTRACT FROM PUBLISHER]

Automatic segmentation of the retinal vasculature is considered as a first step in computer assisted medical applications related to diagnosis and treatment planning. This paper describes a pixel classification based method of segmenting retinal blood vessels using linear discriminant analysis. The vessel-ness measure of a pixel is defined by the feature vector comprised of a modified multiscale line operator and Gabor filter responses. The sequential forward feature selection scheme is used to identify the optimal scales for the line operator and Gabor filter. The linear discriminant classifier utilizes only two features for pixel classification. The feature vector encodes information to reliably handle normal vessels in addition to vessels with strong light reflexes along their centerline, which is more apparent on retinal arteriolars than venules. The method is evaluated on the three publicly available DRIVE, STARE and MESSIDOR datasets. The method is computationally fast and its performance approximates the 2nd human observer as well as other existing methodologies available in the literature, thus making it a suitable tool for automated retinal image analysis. [ABSTRACT FROM PUBLISHER]

The segmentation of ear structures in computed tomography (CT) and magnetic resonance (MR) images has gained high importance in the last years. In this paper, we present a review on the segmentation algorithms presented in the literature. As such, several algorithms, approaches, related issues and problems are defined and explained. Additionally, their use is illustrated and discussed, and their advantages and disadvantages are pointed out. [ABSTRACT FROM AUTHOR]

Nowadays is common to have health care institutions providing remote assistance, such as, remote diagnosis (telediagnosis) and second opinion from a specialized physicians (teleconsultation), to others medical institutions that do not have specialized human resources, or even for educational propose. The evolution of technology creates opportunities to improve telemedicine services. This article focuses on the improvement of services to support telemedicine in a paradigm "any-time and anywhere" adapting a new emerging computer concept, which is cloud computing. Throughout the paper is presented a software as a service that can be used by radiologist for store, share, visualize and analyse medical images, in compliant with DICOM (Digital Imaging and Communications in Medicine) format, from anywhere. Furthermore, the presented architecture allows to improve real time and asynchronous collaboration. To support collaborative activities and their coordination, we created a computer-supported collaborative work service based on Openfire real time collaboration (RTC) server, that use Extensible Messaging and Presence Protocol (XMPP) for instant messaging and presence. Finally, the platform was deployed on an Internet Cloud provider and some results was presented and discussed. [ABSTRACT FROM AUTHOR]

The usage of information systems has significantly augmented in the last years and healthcare is not an exception. The growing use of computer systems has increased the productivity and quality of services provided by medical institutions. These systems can generate a huge amount of information and it is possible to identify several tools to process and analyze it. However, there are few systems that allow users to aggregate data from various systems, in a centralized manner, and correlate multiple source information. Moreover, there are some sources that usually are not analyzed but their usage could help us to optimize existing resources and ensure the quality of services provided. This paper presents a tool to capture and analyse the information exchanged on a medical imaging network. This sensor colects network packets and enables the user to extract knowledge from them and associate email alerts to certain events [ABSTRACT FROM AUTHOR]

The red blood cell segmentation is an important technology for automatic cell counting, classification and analysis in clinical examination. In this paper, we propose a red blood cell segmentation method based on Active Appearance Models (AAM). The AAM can effectively describe the shape information and texture information of the red blood cell, and separate cells from background precisely. Experimental results show that the AAM can extract cells from background effectively. Besides, compared with many traditional image segmentation methods, the AAM method provides a closed form of the boundary of the cell, so it is no need to perform boundary tracking for cell counting, measurement and analysis. [ABSTRACT FROM PUBLISHER]

This paper describes current state of the art of medical image processing and surgery support system. In it, typical medical image processing processes such as segmentation, registration and enhancement are described as an application of fuzzy logic. Second, orthopedic surgery and surgery support systems are introduced. In it, we meet the fuzzy logic application to ultrasonic system. Third, a bed-side health monitoring system is described. Fuzzy signal processing is employed in this system. Finally, a future direction of medical and health technology are discussed. [ABSTRACT FROM PUBLISHER]

This paper presents work on a PC-based software solution for evaluation of burn wounds, Improvements leading to automatisation of important elements of the evaluation procedure, together with other enhancements requested by the physicians are presented, [ABSTRACT FROM PUBLISHER]

Summarization of echo-Doppler videos allows reducing diagnosis time, improving comparison between videos and making a more efficient storing of them. This paper aims at providing a solution to the static summarization of echo-Doppler videos. A static summary of a video is a collection of keyframes together with a description of them. The selection of keyframes discussed in this paper is based on the analysis of properties of red blobs resulting from Power Doppler technique. The properties of red blobs are extracted by a robust thresholding algorithm in the HSL colour model and via a connected-component labelling algorithm. Keyframes extracted from the echo-Doppler video satisfy specific properties for the red blobs. The work is still in progress and we are now collecting data for the construction of a decision support system to help doctors in their diagnoses. First results are encouraging and future works will bring to an interesting computer-aided system. [ABSTRACT FROM PUBLISHER]

The aim is to measure the color difference between two images of the same object taken before and after a treatment that resulted in color change (such as teeth bleaching i.e. teeth treatment with different whitening products). Image calibration is a necessary component for the comparison of colors between the objects contained in the images. The two aspects of the image calibration process will be presented in this paper: position calibration of objects (studied to ensure that the comparison is performed between the same area of the objects) and color calibration (altered from the acquisition of images). [ABSTRACT FROM PUBLISHER]

To cope with the complexity of programming GPU accelerators for medical imaging computations, we developed a framework to describe image processing kernels in a domain-specific language, which is embedded into C++. The description uses decoupled access/execute metadata, which allow the programmer to specify both execution constraints and memory access patterns of kernels. A source-to-source compiler translates this high-level description into low-level CUDA and Open CL code with automatic support for boundary handling and filter masks. Taking the annotated metadata and the characteristics of the parallel GPU execution model into account, two-layered parallel implementations - utilizing SPMD and MPMD parallelism - are generated. An abstract hardware model of graphics card architectures allows to model GPUs of multiple vendors like AMD and NVIDIA, and to generate device-specific code for multiple targets. It is shown that the generated code is faster than manual implementations and those relying on hardware support for boundary handling. Implementations from Rapid Mind, a commercial framework for GPU programming, are outperformed and similar results achieved compared to the GPU backend of the widely used image processing library Open CV. [ABSTRACT FROM PUBLISHER]

Recent theory of compressed sensing informs us that near-exact recovery of an unknown sparse signal is possible from a very limited number of wavelet samples by solving optimization problems. The significance of compressed sensing theory is not only to make much fuller use of recent limited resource of bandwidth, but to break the traditional sampling model which contents sampling, compressing, transferring, decompressing, leaving the data processing part(decompressing) which is much more difficult to computer terminal with higher computational capabilities. The advantage is that we can solve many problems or strengthen local function in the new system model. In the application of medical imaging, less sampling means less time and less harm, which is a great meaning to patients. This thesis is mainly aimed at an relatively mature algorithm OMP(Orthogonal Matching Pursuit) on the reconstructing to different class or size of images, to analyze and solve the problems in the reconstruction. In the experimental process, for the problems that large luminance difference in some part results in the inferior reconstruction, we propose to improve the reconstruction of the part we are interested by up sampling, while down sampling the rest. By sampling targetedly based on OMP, we improved the PSNR of the reconstruction with no more samples to the whole image. In consideration of the characteristic of medical image that the information is relatively concentrated, the method can be operable and practical in real applications. [ABSTRACT FROM PUBLISHER]

Predicting a CT image or a map of the linear attenuation coefficients from the information provided by magnetic resonance imaging (MRI) is a challenging task. This problem is of significant importance for combined positron emission tomography (PET)/MRI scanners, as quantitative PET image reconstruction requires an attenuation map. In PET/CT this attenuation map is derived from the CT scan or from a rotating source, however, current PET/MR systems can not directly measure attenuation images - and indeed it is desirable to save the patient from the additional radiation exposure. Recent approaches tackle this problem by using MR sequences with ultra-short echo times (UTE). At the price of lower effective image resolution, the UTE image yields signal from bone and therefore provides valuable information for calculating the attenuation map. We propose a novel approach to this problem based on nonnegative blind deconvolution and present the first method that explicitly models the image degradation of the UTE image. Incorporating prior knowledge such as smoothness and a novel orthogonality constraint alleviates the deconvolution process. Due to its probabilistic formulation our approach allows hyperparameter estimation and is therefore parameter-free. [ABSTRACT FROM PUBLISHER]

Geometric or Clifford Algebra (CA) is a powerful mathematical tool that is attracting a growing attention in many research fields such as computer graphics, computer vision, robotics and medical imaging for its natural and intuitive way to represent geometric objects and their transformations. This paper introduces the architecture of CliffordCoreDuo, an embedded dual-core coprocessor that offers direct hardware support to four-dimensional (4D) Clifford algebra operations. A prototype implementation on an FPGA board is detailed. Experimental results show a 1.6x average speedup of CliffordCoreDuo in comparison with the baseline mono-core architecture. A potential cycle speedup of about 40x over Gaigen 2, a geometric algebra software library generator for general-purpose processors, is also demonstrated. [ABSTRACT FROM PUBLISHER]

Texture analysis of color images is one of the challenging and complex problems to solve in order to perform operations like segmentation and classification in digital images. There are several approaches of textural features extraction among which the fractal-based approach is one of the most popular, due to the exhibited properties of invariance to scale and rotation. The fractal dimension and the lacunarity are the two fundamental measures used to describe a fractal set. We present a segmentation technique, which uses the lacunarity and furthermore, lacunarity-derived scalar features, as local texture descriptors. We use this approach for the analysis and segmentation of medical color images of psoriasis skin lesions, in the context of a dermatological application. We comment the results generated on a set of psoriasis images and we conclude the paper. [ABSTRACT FROM PUBLISHER]

An efficient memory bandwidth utilization for GPU accelerators is crucial for memory bound applications. In medical imaging, the performance of many kernels is limited by the available memory bandwidth since only a few operations are performed per pixel. For such kernels only a fraction of the compute power provided by GPU accelerators can be exploited and performance is predetermined by memory bandwidth. As a remedy, this paper investigates the optimal utilization of available memory bandwidth by means of increasing in-flight memory transactions. Instead of doing this manually for different GPU accelerators, the required CUDA and OpenCL code is automatically generated from descriptions in a Domain-Specific Language (DSL) for the considered application domain. Moreover, the DSL is extended to also support global reduction operators. We show that the generated target-specific code improves bandwidth utilization for memory-bound kernels significantly. Moreover, competitive performance compared to the GPU back end of the widely used image processing library OpenCV can be achieved. [ABSTRACT FROM PUBLISHER]

Nowadays is common to have health care institutions providing remote assistance, such as, remote diagnosis (telediagnosis) and second opinion from a specialized physicians (teleconsultation), to others medical institutions that do not have specialized human resources, or even for educational propose. The evolution of technology creates opportunities to improve telemedicine services. This article focuses on the improvement of services to support telemedicine in a paradigm “any-time and anywhere” adapting a new emerging computer concept, which is cloud computing. Throughout the paper is presented a software as a service that can be used by radiologist for store, share, visualize and analyse medical images, in compliant with DICOM (Digital Imaging and Communications in Medicine) format, from anywhere. Furthermore, the presented architecture allows to improve real time and asynchronous collaboration. To support collaborative activities and their coordination, we created a computer-supported collaborative work service based on Openfire real time collaboration (RTC) server, that use Extensible Messaging and Presence Protocol (XMPP) for instant messaging and presence. Finally, the platform was deployed on an Internet Cloud provider and some results was presented and discussed. [ABSTRACT FROM PUBLISHER]

Given that over 230,000 women in the United States alone will contract breast cancer, resulting in over 39,000 deaths and that there will be an estimated 458000 such deaths worldwide, the early detection and management of breast cancer is a significant problem. Currently, mammography provides the dominant front-line screening procedure. To assist in the interpretation of mammograms, a variety of computer aided diagnostic algorithms have been developed. A critical step in most of these algorithms is to remove image artifacts and isolate the breast from the mammogram background. This study explores the use of a biologically inspired model, the Pulse Coupled Neural Network, to form candidate image segments that, when combined with standard image morphology operators, can be used to remove image acquisition artifacts and isolate the breast profile in the mammogram. [ABSTRACT FROM PUBLISHER]

In Healthcare IT-driven revolution the organizations are investing in the latest information technologies with the clear goals of reducing operating costs and improving healthcare outcomes. Cloud computing is emerging as a new trend in computational and storage resource allocation and provisioning technology. The motivation of study is providing DICOM images management on Cloud Computing technology for authorized physicians, healthcare facilities and on demand access to patient's medical images from RIS or PACS. The proposed work is discussed to meet the challenges for DICOM Image Management and the offered cloud service model “Cloud as a Service (CaaS)” for Medical Imaging applications on cloud computing systems. The conceptual design is discussed, how to manage medical imaging solution on cloud, though to provide secure service, anytime & anywhere access to medical images and instant retrieval of digital images data of any modality with a cloud-based image storage and management service using standard DICOM protocol. This paper summarizes the framework model on medical imaging solid foundation with platforms and softwares to power the cloud infrastructure for DICOM Image Management, build and run robust cloud applications, and supply end-user computing as a cloud-based service. [ABSTRACT FROM PUBLISHER]

The 3D reconstruction for freehand 3D ultrasound is a challenging issue because the recorded B-scans are not only sparse, but also non-parallel (actually they may intersect each other). Conventional volume reconstruction methods can't reconstruct sparse data efficiently while not introducing geometrical artifacts, and conventional surface reconstruction methods can't reconstruct surfaces from contours that are arbitrarily oriented in 3D space. We developed a new surface reconstruction method for freehand 3D ultrasound. It is based on variational implicit function which is presented by Greg Turk for shape transformation. In the new method, we first constructed on-& off-surface constraints from the segmented contours of all recorded B-scans, then used a variational interpolation technique to get a single implicit function in 3D. Finally, the implicit function was evaluated to extract the zero-valued surface as reconstruction result. Two experiment was conducted to assess our variational surface reconstruction method, and the experiment results have shown that the new method is capable of reconstructing surface smoothly from sparse contours which can be arbitrarily oriented in 3D space. [ABSTRACT FROM PUBLISHER]

In [1], the authors have approached the sphere-like surfaces using the tensor product of an algebraic cubic spline quasi-interpolant with a 2π-periodic Uniform Algebraic Trigonometric B-splines (UAT B-splines) of order four. In this paper, we improve the results given in [1], by introducing a new quasi-interpolant based on the tensor product of an algebraic cubic spline quasi-interpolant with a periodic cubic spline quasi-interpolant, obtained by the periodization of an algebraic cubic spline quasi-interpolant. Our approach allows us to obtain an approximating surface which is of class C2 and with an approximation order O(h4). We show that this method is particularly well designed to render 3D closed surfaces, and it has been successfully applied to reconstruct human organs such as the left ventricle of the heart. [ABSTRACT FROM PUBLISHER]

OpenSURF is an algorithm to detect point correspondences between two images. OpenSURF is an integral part of computer vision and machine vision. The Algorithm aims is to find important region in images which can found under variety of image transformation. This algorithm can be used for augmented reality object recognition, or medical imaging. This research is to reach maximum performance augmented reality markerless application. Especially on Actual Mobile Guide for Tourist application. OpenSURF doesn't have library for windows phone so we have to porting from C++ to C#. The performance of OpenSURF is not much further than android library, it is 6,666 second(windows phone) versus 8.779 second(android) with 604 × 453 pixel picture. [ABSTRACT FROM PUBLISHER]

With the rise of heterogeneous computing architectures, application developers are confronted with a multitude of hardware platforms and the challenge of identifying the most suitable processing platform for their application. Strong competitors for the acceleration of 3D Ultrasound Computer Tomography, a medical imaging method for early breast cancer diagnosis, are GPU and FPGA devices. In this work, we evaluate processing performance and efficiency metrics for current FPGA and GPU devices. We compare top-notch devices from the 40 nm generation as well as FPGA and GPU devices, which draw the same amount of power. For our two benchmark algorithms, the results show that if power consumption is not considered the GPU and the FPGA give both, a similar processing performance and processing efficiency per transistor. However, if the power budget is limited to a similar value, the FPGA performs between six and eight times better than the GPU. [ABSTRACT FROM PUBLISHER]