This PDF file contains the front matter associated with SPIE Proceedings Volume 8319, including the Title Page, Copyright information, Table of Contents, and the Conference Committee listing.

Dicom images of patients will necessarily been stored in Clouds. However, ethical constraints must apply. In this paper, a method which provides the two following conditions is presented: 1) the medical information is not readable by the cloud owner since it is distributed along several clouds 2) the medical information can be retrieved from any sufficient subset of clouds In order to obtain this result in a real time processing, the Mojette transform is used. This paper reviews the interesting features of the Mojette transform in terms of information theory. Since only portions of the original Dicom files are stored into each cloud, their contents are not reachable. For instance, we use 4 different public clouds to save 4 different projections of each file, with the additional condition that any 3 over 4 projections are enough to reconstruct the original file. Thus, even if a cloud is unavailable when the user wants to load a Dicom file, the other 3 are giving enough information for real time reconstruction. The paper presents an implementation on 3 actual clouds. For ethical reasons, we use a Dicom image spreaded over 3 public clouds to show the obtained confidentiality and possible real time recovery.

Many widely used digital medical image collections have been established but these are generally used as raw data sources without related image analysis toolsets. Providing associated functionality to allow specific types of operations to be performed on these images has proved beneficial in some cases (e.g. brain image registration and atlases). However, toolset development to provide generic image analysis functions on medical images has tended to be ad hoc, with Open Source options proliferating (e.g. ITK). Our Automated Medical Image Collection Annotation (AMICA) system is both an image repository, to which the research community can contribute image datasets, and a search/retrieval system that uses automated image annotation. AMICA was designed for the Windows Azure platform to leverage the flexibility and scalability of the cloud. It is intended that AMICA will expand beyond its initial pilot implementation (for brain CT, MR images) to accommodate a wide range of modalities and anatomical regions. This initiative aims to contribute to advances in clinical research by permitting a broader use and reuse of medical image data than is currently attainable. For example, cohort studies for cases with particular physiological or phenotypical profiles will be able to source and include enough cases to provide high statistical power, allowing more individualised risk factors to be assessed and thus allowing screening and staging processes to be optimised. Also, education, training and credentialing of clinicians in image interpretation, will be more effective because it will be possible to select instances of images with specific visual aspects, or correspond to types of cases where reading performance improvement is desirable.

IPad devices have become very popular also in the healthcare community. There is an ever growing demand to use tablets for displaying and reviewing of medical images. However, a major problem is the lack of calibration and quality assurance of the IPad display. Medical displays used for review and diagnosis of medical images need to be calibrated to the DICOM GSDF standard to ensure sufficient image quality and reproducibility. This paper presents a convenient and reliable solution. An optimized visual calibration algorithm to calibrate and perform quality assurance tests on IPad devices has been developed. The algorithm allows a user to quickly calibrate an IPad in only a few minutes while a follow-up visual QA test to verify calibration status takes less than a minute. In the calibration phase, the user needs to change position of a slider until a pattern barely becomes visible, and this for a small number of grey levels. In the QA test phase, the user needs detect subtle patterns of varying size, contrast and average luminance level. It is extremely important to accurately quantify performance of the algorithm. For this purpose extensive tests have been performed. Multiple devices have been evaluated for various lighting conditions and viewing angles. The group of test user consisted of both non-clinical and clinical people. Results show that the algorithm consistently is able to calibrate an IPad device to DICOM GSDF with an average deviation smaller than 5% for indoor use and smaller than 12% for outdoor use. Tests have also shown that the algorithm is very reproducible and that there is little difference in performance between users.

Biomarkers captured by medical images are increasingly used as indicators for the efficacy or safety of a certain drug or treatment for clinical trials. For example, medical images such as CT or MR are often used for extracting quantitative measurements for the assessment of tumor treatment response while evaluating a chemotherapy drug for therapeutic cancer trials. Quality assurance is defined as "All those planned and systematic actions that are established to ensure that the trial is performed and the data are generated, documented (recorded), and reported in compliance with good clinical practice (GCP) and the applicable regulatory requirement(s)" [1]. Our objective is to build a generalized and an automated framework for quality assurance within the clinical trials workflow. In order to reach this goal, a set of standardized software tools have been developed for quality assurance. Furthermore, we outline some guidelines as recommendations for the users handling the image data within the research workflow. The software tools developed include tools for image selection, image pseudonymization and image quality conformance check. The export tools are developed based on the specifications of the Integrating the Healthcare Enterprise (IHE) Teaching and Clinical Trial Export (TCE) profile. A DICOM-based quality conformance approach has been developed by validating the DICOM header attributes required for a certain imaging application (e.g. CAD, MPR, 3D) and comparing imaging acquisition parameters against the protocol specification. A formal description language is used to represent such quality requirements. For evaluation, imaging data collected from a clinical trial site were validated against Multi-Planar Reconstruction (MPR). We found that out of 60 studies, about 30% of image series volumes failed the MPR check for some common reasons.

Searching for similar image regions in medical databases yields valuable information for diagnosis. However, most of the current approaches are restricted to special cases or they are only available for rather small data stores. In this paper, we propose a fast query pipeline for 3D similarity queries on large databases of computed tomography (CT) scans consisting of minimum bounding box annotations. As these box annotations also contain background information which is not part of the item that was actually annotated, we employ approximate segmentation approaches for distinguishing between within-object texture and background texture in order to correctly describe the annotated objects. Our method allows a compact form of object description. In our framework, we exploit this advantage for enabling very fast query times. We have validated our method on data sets of 111 and 1293 bounding box lesion annotations within the liver and other organs. Our experiments show a significant performance improvement over previous approaches in both runtime and precision.

RADIANCE extracts CT dose parameters from dose sheets using optical character recognition and stores the data in a relational database. To facilitate validation of RADIANCE's performance, a simple user interface was initially implemented and about 300 records were evaluated. Here, we extend this interface to achieve a wider variety of functions and perform a larger-scale validation. The validator uses some data from the RADIANCE database to prepopulate quality-testing fields, such as correspondence between calculated and reported total dose-length product. The interface also displays relevant parameters from the DICOM headers. A total of 5,098 dose sheets were used to test the performance accuracy of RADIANCE in dose data extraction. Several search criteria were implemented. All records were searchable by accession number, study date, or dose parameters beyond chosen thresholds. Validated records were searchable according to additional criteria from validation inputs. An error rate of 0.303% was demonstrated in the validation. Dose monitoring is increasingly important and RADIANCE provides an open-source solution with a high level of accuracy. The RADIANCE validator has been updated to enable users to test the integrity of their installation and verify that their dose monitoring is accurate and effective.

Improved access to DICOM studies to both physicians and patients is changing the ways medical imaging studies are visualized and interpreted beyond the confines of radiologists' PACS workstations. While radiologists are trained for viewing and image interpretation, a non-radiologist physician relies on the radiologists' reports. Consequently, patients historically have been typically informed about their imaging findings via oral communication with their physicians, even though clinical studies have shown that patients respond to physician's advice significantly better when the individual patients are shown their own actual data. Our previous work on automated semantic annotation of DICOM Computed Tomography (CT) images allows us to further link radiology report with the corresponding images, enabling us to bridge the gap between image data with the human interpreted textual description of the corresponding imaging studies. The mapping of radiology text is facilitated by natural language processing (NLP) based search application. When combined with our automated semantic annotation of images, it enables navigation in large DICOM studies by clicking hyperlinked text in the radiology reports. An added advantage of using semantic annotation is the ability to render the organs to their default window level setting thus eliminating another barrier to image sharing and distribution. We believe such approaches would potentially enable the consumer to have access to their imaging data and navigate them in an informed manner.

Compared to a retrieval using global image features, features extracted from regions of interest (ROIs) that reflect distribution patterns of abnormalities would benefit more for content-based medical image retrieval (CBMIR) systems. Currently, most CBMIR systems have been designed for 2D ROIs, which cannot reflect 3D anatomical features and region distribution of lesions comprehensively. To further improve the accuracy of image retrieval, we proposed a retrieval method with 3D features including both geometric features such as Shape Index (SI) and Curvedness (CV) and texture features derived from 3D Gray Level Co-occurrence Matrix, which were extracted from 3D ROIs, based on our previous 2D medical images retrieval system. The system was evaluated with 20 volume CT datasets for colon polyp detection. Preliminary experiments indicated that the integration of morphological features with texture features could improve retrieval performance greatly. The retrieval result using features extracted from 3D ROIs accorded better with the diagnosis from optical colonoscopy than that based on features from 2D ROIs. With the test database of images, the average accuracy rate for 3D retrieval method was 76.6%, indicating its potential value in clinical application.

The biomedical literature published regularly has increased strongly in past years and keeping updated even in narrow domains is difficult. Images represent essential information of their articles and can help to quicker browse through large volumes of articles in connection with keyword search. Content-based image retrieval is helping the retrieval of visual content. To facilitate retrieval of visual information, image categorisation can be an important first step. To represent scientific articles visually, medical images need to be separated from general images such as flowcharts or graphs to facilitate browsing, as graphs contain little information. Medical modality classification is a second step to focus search. The techniques described in this article first classify images into broad categories. In a second step the images are further classified into the exact medical modalities. The system combines the Scale-Invariant Feature Transform (SIFT) and density-based clustering (DENCLUE). Visual words are first created globally to differentiate broad categories and then within each category a new visual vocabulary is created for modality classification. The results show the difficulties to differentiate between some modalities by visual means alone. On the other hand the improvement of the accuracy of the two-step approach shows the usefulness of the method. The system is currently being integrated into the Goldminer image search engine of the ARRS (American Roentgen Ray Society) as a web service, allowing concentrating image search onto clinically relevant images automatically.

Multiple sclerosis (MS) is a demyelinating disease in the central nervous system. Genetics have been considered as a leading factor in the prevalence and disease course of MS. We have presented an informatics-based eFolder system for integrating patients' clinical data with MR images and lesion quantification results. The completed eFolder system has been designed and developed in aiding to evaluate disease manifestation differences in Hispanic and Caucasian MS patients. MS lesion data, as shown in MRI, can be extracted by the 3-D automatic lesion detection tool in the eFolder, and data storing and mining tools in eFolder is able to extract and compare data from individual patients. The computer-aided detection (CAD) algorithm has been modified and enhanced to include spatial information as detection criteria. For this study, 36 Caucasian MS patients and 36 matched Hispanic patients have been selected. Most recent MR images of the patients are collected, and images are evaluated both by the CAD tool in the eFolder and radiologists. The results are compared between Caucasian and Hispanic patients and statistically evaluated to see if the two populations have significant difference in lesion presentations. The results can be used to evaluate differences in the two groups of patients and to evaluate the new CAD algorithm's performance with radiologists' contours. Significant findings can further evaluate effectiveness of MS eFolder in MS-related research.

Precise image acquisition is an integral part of modern patient care and medical imaging research. Periodic quality control using standardized protocols and phantoms ensures that scanners are operating according to specifications, yet such procedures do not ensure that individual datasets are free from corruption; for example due to patient motion, transient interference, or physiological variability. If unacceptable artifacts are noticed during scanning, a technologist can repeat a procedure. Yet, substantial delays may be incurred if a problematic scan is not noticed until a radiologist reads the scans or an automated algorithm fails. Given scores of slices in typical three-dimensional scans and widevariety of potential use cases, a technologist cannot practically be expected inspect all images. In large-scale research, automated pipeline systems have had great success in achieving high throughput. However, clinical and institutional workflows are largely based on DICOM and PACS technologies; these systems are not readily compatible with research systems due to security and privacy restrictions. Hence, quantitative quality control has been relegated to individual investigators and too often neglected. Herein, we propose a scalable system, the Vanderbilt Image Processing Enterprise Resource (VIPER) to integrate modular quality control and image analysis routines with a standard PACS configuration. This server unifies image processing routines across an institutional level and provides a simple interface so that investigators can collaborate to deploy new analysis technologies. VIPER integrates with high performance computing environments has successfully analyzed all standard scans from our institutional research center over the course of the last 18 months.

More and more image informatics researchers and engineers are considering to re-construct imaging and informatics infrastructure or to build new framework to enable multiple disciplines of medical researchers, clinical physicians and biomedical engineers working together in a secured, efficient, and transparent cooperative environment. In this presentation, we show an outline and our preliminary design work of building an e-Science platform for biomedical imaging and informatics research and application in Shanghai. We will present our consideration and strategy on designing this platform, and preliminary results. We also will discuss some challenges and solutions in building this platform.

High-resolution pathology images provide rich information about the morphological and functional characteristics of biological systems, and are transforming the field of pathology into a new era. To facilitate the use of digital pathology imaging for biomedical research and clinical diagnosis, it is essential to manage and query both whole slide images (WSI) and analytical results generated from images, such as annotations made by humans and computed features and classifications made by computer algorithms. There are unique requirements on modeling, managing and querying whole slide images, including compatibility with standards, scalability, support of image queries at multiple granularities, and support of integrated queries between images and derived results from the images. In this paper, we present our work on developing the Pathology Image Database System (PIDB), which is a standard oriented image database to support retrieval of images, tiles, regions and analytical results, image visualization and experiment management through a unified interface and architecture. The system is deployed for managing and querying whole slide images for In Silico brain tumor studies at Emory University. PIDB is generic and open source, and can be easily used to support other biomedical research projects. It has the potential to be integrated into a Picture Archiving and Communications System (PACS) with powerful query capabilities to support pathology imaging.

Comparing several series of images is not always easy as the corresponding slices often need to be selected manually. In times where series contain an ever-increasing number of slices this can mean manual work when moving several series to the corresponding slice. Particularly two situations were identified in this context: (1) patients with a large number of image series over time (such as patients with cancers that are monitored) frequently need to compare the series, for example to compare tumor growth over time. Manually adapting two series is possible but with four or more series this can mean loosing time. Having automatically the closest slice by comparing visual similarity also in older series with differing slice thickness and inter slice distance can save time and synchronize the viewing instantly. (2) analyzing visually similar image series of several patients can profit from being viewed in a synchronized way to compare the cases, so when sliding through the slices in one volume, the corresponding slices in the other volumes are shown. This application could be employed after content-based 3D image retrieval has found similar series, for example. Synchronized viewing can help finding or confirming the most relevant cases quickly. To allow for synchronized viewing of several image volumes, the test image series are first registered applying affine transformation for the global registration of images followed by diffeomorphic image registration. Then corresponding slices in the two volumes are estimated based on a visual similarity. Once the registration is finished, the user can subsequently move inside the slices of one volume (reference volume) and can view the corresponding slices in the other volumes. These corresponding slices are obtained after a correspondence match in the registration procedure. These volumes are synchronized in that the slice closest to the original reference volume is shown even when the slice thicknesses or inter slice distances differ, and this is automatically done by comparing the visual image content of the slices. The tool has the potential to help in a variety of situations and it is currently being made available as a plugin for the popular Osirix image viewer.

The increasing use of technologies such as CT and MRI, along with a continuing improvement in their resolution, has contributed to the explosive growth of digital image data being generated. Medical communities around the world have recognized the need for efficient storage, transmission and display of medical images. For example, the Canadian Association of Radiologists (CAR) has recommended compression ratios for various modalities and anatomical regions to be employed by lossy JPEG and JPEG2000 compression in order to preserve diagnostic quality. Here we investigate the effects of the sharp skull edges present in CT neuro images on JPEG and JPEG2000 lossy compression. We conjecture that this atypical effect is caused by the sharp edges between the skull bone and the background regions as well as between the skull bone and the interior regions. These strong edges create large wavelet coefficients that consume an unnecessarily large number of bits in JPEG2000 compression because of its bitplane coding scheme, and thus result in reduced quality at the interior region, which contains most diagnostic information in the image. To validate the conjecture, we investigate a segmentation based compression algorithm based on simple thresholding and morphological operators. As expected, quality is improved in terms of PSNR as well as the structural similarity (SSIM) image quality measure, and its multiscale (MS-SSIM) and informationweighted (IW-SSIM) versions. This study not only supports our conjecture, but also provides a solution to improve the performance of JPEG and JPEG2000 compression for specific types of CT images.

Traditional content-based image retrieval methods based on learning from examples analyze and attempt to understand high-level semantics of an image as a whole. They typically apply certain case-based reasoning technique to interpret and retrieve images through measuring the semantic similarity or relatedness between example images and search candidate images. The drawback of such a traditional content-based image retrieval paradigm is that the summation of imagery contents in an image tends to lead to tremendous variation from image to image. Hence, semantically related images may only exhibit a small pocket of common elements, if at all. Such variability in image visual composition poses great challenges to content-based image retrieval methods that operate at the granularity of entire images. In this study, we explore a new content-based image retrieval algorithm that mines visual patterns of finer granularities inside a whole image to identify visual instances which can more reliably and generically represent a given search concept. We performed preliminary experiments to validate our new idea for content-based image retrieval and obtained very encouraging results.

Existing literature describes a variety of techniques for semantic annotation of DICOM CT images, i.e. the automatic detection and localization of anatomical structures. Semantic annotation facilitates enhanced image navigation, linkage of DICOM image content and non-image clinical data, content-based image retrieval, and image registration. A key challenge for semantic annotation algorithms is inter-patient variability. However, while the algorithms described in published literature have been shown to cope adequately with the variability in test sets comprising adult CT scans, the problem presented by the even greater variability in pediatric anatomy has received very little attention. Most existing semantic annotation algorithms can only be extended to work on scans of both adult and pediatric patients by adapting parameters heuristically in light of patient size. In contrast, our approach, which uses random regression forests ('RRF'), learns an implicit model of scale variation automatically using training data. In consequence, anatomical structures can be localized accurately in both adult and pediatric CT studies without the need for parameter adaptation or additional information about patient scale. We show how the RRF algorithm is able to learn scale invariance from a combined training set containing a mixture of pediatric and adult scans. Resulting localization accuracy for both adult and pediatric data remains comparable with that obtained using RRFs trained and tested using only adult data.

Similar treatment plans or similar cases in radiotherapy treatment planning (RTP) databases of senior experienced planners could be helpful or educational for treatment planners who have few experiences of stereotactic body radiotherapy (SBRT). The aim of this study was to investigate the feasibility of beam arrangements determined using similar cases in a RTP database including plans designed by experienced treatment planners. Similar cases were automatically selected based on geometrical features and planning evaluation indices from 81 cases with lung cancer who received SBRT. First, the RTP database was searched for the five most similar cases based on geometrical features related to the location, size, and shape of the planning target volume, lung, and spinal cord. Second, the five beam arrangements of an objective case were automatically determined by registering five similar cases to the objective case with respect to lung regions by means of a linear registration technique. For evaluation of the beam arrangements, five plans were designed by applying the beam arrangements determined in the second step to the objective case. The most usable beam arrangement was selected by sorting the five plans based on 11 planning evaluation indices including tumor control probability and normal tissue complication probability. We applied the proposed two-step method to 10 test cases by using an RTP database of 81 cases with lung cancer, and compared the 11 planning evaluation indices between the original plan and the corresponding most usable similar-case-based plan. As a result, there were no statistically significant differences between the original beam arrangements and the most usable similar-case-based beam arrangements (P > 0.05) in terms of the 10 planning evaluation indices. The proposed method suggested usable beam arrangements with little difference from cases in the RTP database, and thus it could be employed as an educational tool for less experienced treatment planners.

Content-based image retrieval (CBIR) from specialized collections has often been proposed for use in such areas as diagnostic aid, clinical decision support, and teaching. The visual retrieval from broad image collections such as teaching files, the medical literature or web images, by contrast, has not yet reached a high maturity level compared to textual information retrieval. Visual image classification into a relatively small number of classes (20-100) on the other hand, has shown to deliver good results in several benchmarks. It is, however, currently underused as a basic technology for retrieval tasks, for example, to limit the search space. Most classification schemes for medical images are focused on specific areas and consider mainly the medical image types (modalities), imaged anatomy, and view, and merge them into a single descriptor or classification hierarchy. Furthermore, they often ignore other important image types such as biological images, statistical figures, flowcharts, and diagrams that frequently occur in the biomedical literature. Most of the current classifications have also been created for radiology images, which are not the only types to be taken into account. With Open Access becoming increasingly widespread particularly in medicine, images from the biomedical literature are more easily available for use. Visual information from these images and knowledge that an image is of a specific type or medical modality could enrich retrieval. This enrichment is hampered by the lack of a commonly agreed image classification scheme. This paper presents a hierarchy for classification of biomedical illustrations with the goal of using it for visual classification and thus as a basis for retrieval. The proposed hierarchy is based on relevant parts of existing terminologies, such as the IRMA-code (Image Retrieval in Medical Applications), ad hoc classifications and hierarchies used in imageCLEF (Image retrieval task at the Cross-Language Evaluation Forum) and NLM's (National Library of Medicine) OpenI. Furtheron, mappings to NLM's MeSH (Medical Subject Headings), RSNA's RadLex (Radiological Society of North America, Radiology Lexicon), and the IRMA code are also attempted for relevant image types. Advantages derived from such hierarchical classification for medical image retrieval are being evaluated through benchmarks such as imageCLEF, and R&D systems such as NLM's OpenI. The goal is to extend this hierarchy progressively and (through adding image types occurring in the biomedical literature) to have a terminology for visual image classification based on image types distinguishable by visual means and occurring in the medical open access literature.

Our goal in this paper is to data mine the wealth of information contained in the dose-volume objects used in external beam radiotherapy treatment planning. In addition, by performing computational pattern recognition on these mined objects, the results may help identify predictors for unsafe dose delivery. This will ultimately enhance current clinical registries by the inclusion of detailed dose-volume data employed in treatments. The most efficient way of including dose-volume information in a registry is through DICOM RT objects. With this in mind, we have built a DICOM RT specific infrastructure, capable of integrating with larger, more general clinical registries, and we will present the results of data mining these sets.

Conducting clinical studies is rather difficult because of the large variety of voluminous datasets, different documentation styles, and various information systems, especially in radiation oncology. In this paper, we describe our development of a web-based documentation system with first approaches of automatic statistical analyses for transnational and multicenter clinical studies in particle therapy. It is possible to have immediate access to all patient information and exchange, store, process, and visualize text data, all types of DICOM images, especially DICOM RT, and any other multimedia data. Accessing the documentation system and submitting clinical data is possible for internal and external users (e.g. referring physicians from abroad, who are seeking the new technique of particle therapy for their patients). Thereby, security and privacy protection is ensured with the encrypted https protocol, client certificates, and an application gateway. Furthermore, all data can be pseudonymized. Integrated into the existing hospital environment, patient data is imported via various interfaces over HL7-messages and DICOM. Several further features replace manual input wherever possible and ensure data quality and entirety. With a form generator, studies can be individually designed to fit specific needs. By including all treated patients (also non-study patients), we gain the possibility for overall large-scale, retrospective analyses. Having recently begun documentation of our first six clinical studies, it has become apparent that the benefits lie in the simplification of research work, better study analyses quality and ultimately, the improvement of treatment concepts by evaluating the effectiveness of particle therapy.

Wheelchair users are at an increased risk of developing shoulder pain. The key to formulating correct wheelchair operating practices is to analyze the movement patterns of a sample set of subjects. Data collected for movement analysis includes videos and force/ motion readings. Our goal is to combine the kinetic/ kinematic data with the trial video by overlaying force vector graphics on the raw video. Furthermore, conversion of the video to a DICOM multiframe object annotated with the force vector could provide a standardized way of encoding and analyzing data across multiple studies and provide a useful tool for data mining.

Peer reviews are needed across all disciplines of medicine to address complex medical challenges in disease care, medical safety, insurance coverage handling, and public safety. Radiation therapy utilizes technologically advanced imaging for treatment planning, often with excellent efficacy. Since planning data requirements are substantial, patients are at risk for repeat diagnostic procedures or suboptimal therapeutic intervention due to a lack of knowledge regarding previous treatments. The Peer Review System (PRS) will make this critical radiation therapy information readily available on demand via Web technology. The PRS system has been developed with current Web technology, .NET framework, and in-house DICOM library. With the advantages of Web server-client architecture, including IIS web server, SOAP Web Services and Silverlight for the client side, the patient data can be visualized through web browser and distributed across multiple locations by the local area network and Internet. This PRS will significantly improve the quality, safety, and accessibility, of treatment plans in cancer therapy. Furthermore, the secure Web-based PRS with DICOM-RT compliance will provide flexible utilities for organization, sorting, and retrieval of imaging studies and treatment plans to optimize the patient treatment and ultimately improve patient safety and treatment quality.

Stroke is a major cause of adult disability. The Interdisciplinary Comprehensive Arm Rehabilitation Evaluation (I-CARE) clinical trial aims to evaluate a therapy for arm rehabilitation after stroke. A primary outcome measure is correlative analysis between stroke lesion characteristics and standard measures of rehabilitation progress, from data collected at seven research facilities across the country. Sharing and communication of brain imaging and behavioral data is thus a challenge for collaboration. A solution is proposed as a web-based system with tools supporting imaging and informatics related data. In this system, users may upload anonymized brain images through a secure internet connection and the system will sort the imaging data for storage in a centralized database. Users may utilize an annotation tool to mark up images. In addition to imaging informatics, electronic data forms, for example, clinical data forms, are also integrated. Clinical information is processed and stored in the database to enable future data mining related development. Tele-consultation is facilitated through the development of a thin-client image viewing application. For convenience, the system supports access through desktop PC, laptops, and iPAD. Thus, clinicians may enter data directly into the system via iPAD while working with participants in the study. Overall, this comprehensive imaging informatics system enables users to collect, organize and analyze stroke cases efficiently.

Stroke is one of the major causes of death and disability in America. After stroke, about 65% of survivors still suffer from severe paresis, while rehabilitation treatment strategy after stroke plays an essential role in recovery. Currently, there is a clinical trial (NIH award #HD065438) to determine the optimal dose of rehabilitation for persistent recovery of arm and hand paresis. For DOSE (Dose Optimization Stroke Evaluation), laboratory-based measurements, such as the Wolf Motor Function test, behavioral questionnaires (e.g. Motor Activity Log-MAL), and MR, DTI, and Transcranial Magnetic Stimulation (TMS) imaging studies are planned. Current data collection processes are tedious and reside in various standalone systems including hardcopy forms. In order to improve the efficiency of this clinical trial and facilitate decision support, a web-based imaging informatics system has been implemented together with utilizing mobile devices (eg, iPAD, tablet PC's, laptops) for collecting input data and integrating all multi-media data into a single system. The system aims to provide clinical imaging informatics management and a platform to develop tools to predict the treatment effect based on the imaging studies and the treatment dosage with mathematical models. Since there is a large amount of information to be recorded within the DOSE project, the system provides clinical data entry through mobile device applications thus allowing users to collect data at the point of patient interaction without typing into a desktop computer, which is inconvenient. Imaging analysis tools will also be developed for structural MRI, DTI, and TMS imaging studies that will be integrated within the system and correlated with the clinical and behavioral data. This system provides a research platform for future development of mathematical models to evaluate the differences between prediction and reality and thus improve and refine the models rapidly and efficiently.

Patients confined to manual wheel-chairs are at an added risk of shoulder injury. There is a need for developing optimal bio-mechanical techniques for wheel-chair propulsion through movement analysis. Data collected is diverse and in need of normalization and integration. Current databases are ad-hoc and do not provide flexibility, extensibility and ease of access. The need for an efficient means to retrieve specific trial data, display it and compare data from multiple trials is unmet through lack of data association and synchronicity. We propose the development of a robust web-based ePR system that will enhance workflow and facilitate efficient data management.

This work presents the creation of a semantic lesion database which will support research into computer-aided lesion detection (CAD) in breast screening MRI. As an adjunct to conventional X-ray mammography, MR-mammography has become a popular screening tool for women with a high risk of breast cancer because of its high sensitivity in detecting malignancy. To address the needs of research and development into CAD for breast MRI an integrated tool has been designed to collect all lesion related information, conduct quantitative analysis, and then present crucial data to clinicians and researchers. A lesion database is an essential component of this system as it provides a link between the DICOM database of MR images and the meta-information contained in the Electronic Patient Record. The patient history, radiology reports from MRI screening visits and pathology reports are all collected, dissected, and stored in a hierarchical structure in the database. Moreover, internal links between pathology specimens and the location of the corresponding lesion in the image are established allowing diagnostic information to be displayed alongside the relevant images. If "ground truth" for an imaging visit can be established either by biopsy or by 2-year follow-up, then the case is labeled as suitable for use in training and testing CAD algorithms. At present a total of 1882 lesions (benign/malignant), 200 pathology specimens over 405 subjects and 1794 screening (455 CAD studies) are included in the database. As well as providing an excellent resource for CAD development this also has potential applications in resident radiologists' training and education.

We have developed the teleradiology network system with a new information security solution that provided with web medical image conference system. In the teleradiology network system, the security of information network is very important subjects. We are studying the secret sharing scheme and the tokenization as a method safely to store or to transmit the confidential medical information used with the teleradiology network system. The confidential medical information is exposed to the risk of the damage and intercept. Secret sharing scheme is a method of dividing the confidential medical information into two or more tallies. Individual medical information cannot be decoded by using one tally at all. Our method has the function of automatic backup. With automatic backup technology, if there is a failure in a single tally, there is redundant data already copied to other tally. Confidential information is preserved at an individual Data Center connected through internet because individual medical information cannot be decoded by using one tally at all. Therefore, even if one of the Data Centers is struck and information is damaged due to the large area disaster like the great earthquake of Japan, the confidential medical information can be decoded by using the tallies preserved at the data center to which it escapes damage. Moreover, by using tokenization, the history information of dividing the confidential medical information into two or more tallies is prevented from lying scattered by replacing the history information with another character string (Make it to powerlessness). As a result, information is available only to those who have rightful access it and the sender of a message and the message itself are verified at the receiving point. We propose a new information transmission method and a new information storage method with a new information security solution.

In designing of e-Science platform for biomedical imaging research and application cross multiple academic institutions and hospitals, it needs to find out the best communication protocol to transmit various kinds of biomedical images acquired from Shanghai Synchrotron Radiation Source (SSRS), micro-PET, Micro-CT which includes both types of DICOM and non-DICOM images. In this presentation, we presented several image communication scenarios required in e-Science platform and several possible image communication protocols, and then tested and evaluated the performance of these image communication protocols in e-Science data flows to find out which protocol is the best candidate to be used in e-Science platform for the purpose for security, communication performance, easy implementation and management.

To have comprehensive and completed understanding healthcare status of a patient, doctors need to search patient medical records from different healthcare information systems, such as PACS, RIS, HIS, USIS, as a reference of diagnosis and treatment decisions for the patient. However, it is time-consuming and tedious to do these procedures. In order to solve this kind of problems, we developed a patient-oriented visual index system (VIS) to use the visual technology to show health status and to retrieve the patients' examination information stored in each system with a 3D human model. In this presentation, we present a new approach about how to extract the semantic and characteristic information from the medical record systems such as RIS/USIS to create the 3D Visual Index. This approach includes following steps: (1) Building a medical characteristic semantic knowledge base; (2) Developing natural language processing (NLP) engine to perform semantic analysis and logical judgment on text-based medical records; (3) Applying the knowledge base and NLP engine on medical records to extract medical characteristics (e.g., the positive focus information), and then mapping extracted information to related organ/parts of 3D human model to create the visual index. We performed the testing procedures on 559 samples of radiological reports which include 853 focuses, and achieved 828 focuses' information. The successful rate of focus extraction is about 97.1%.

As more and more CT/MR studies are scanning with larger volume of data sets, more and more radiologists and clinician would like using PACS WS to display and manipulate these larger data sets of images with 3D rendering features. In this paper, we proposed a design method and implantation strategy to develop 3D image display component not only with normal 3D display functions but also with multi-modal medical image fusion as well as compute-assisted diagnosis of coronary heart diseases. The 3D component has been integrated into the PACS display workstation of Shanghai Huadong Hospital, and the clinical practice showed that it is easy for radiologists and physicians to use these 3D functions such as multi-modalities' (e.g. CT, MRI, PET, SPECT) visualization, registration and fusion, and the lesion quantitative measurements. The users were satisfying with the rendering speeds and quality of 3D reconstruction. The advantages of the component include low requirements for computer hardware, easy integration, reliable performance and comfortable application experience. With this system, the radiologists and the clinicians can manipulate with 3D images easily, and use the advanced visualization tools to facilitate their work with a PACS display workstation at any time.

The availability of low cost Internet connections and specialized hardware, like webcams and headsets, makes possible the development of solutions for remote collaborative work. These solutions can provide advantages compared to presential meetings, such as: availability of experts on remote locations; lower price compared to presential meetings; creation of online didactic material (e.g. video-classes); richer forms of interaction between participants. These technologies are particularly interesting for continent-sized countries where typically there is a short number of skilled people in remote areas. However, the application of these technologies in medical field represents a special challenge due to the more complex requirements of this area, such as: Provide confidentiality (patient de-identification) and integrity of patient data; Guarantee availability of the system; Guarantee authenticity of data and users; Provide simple and effective user interface; Be compliant with medical standards such as DICOM and HL7. In order to satisfy those requirements a prototype called MedCast is under development whose architecture allows the integration of the Hospital Information System (HIS) with a collaborative tool in compliance with the HIPAA rules. Some of the MedCast features are: videoconferencing, chat, recording of the sessions, sharing of documents and reports and still and dynamic images presentation. Its current version allows the remote discussion of clinical cases and the remote ECG evaluation.

Acute Intracranial hemorrhage (AIH) requires urgent diagnosis in the emergency setting to mitigate eventual sequelae. However, experienced radiologists may not always be available to make a timely diagnosis. This is especially true for small AIH, defined as lesion smaller than 10 mm in size. A computer-aided detection (CAD) system for the detection of small AIH would facilitate timely diagnosis. A previously developed 2D algorithm shows high false positive rates in the evaluation based on LAC/USC cases, due to the limitation of setting up correct coordinate system for the knowledge-based classification system. To achieve a higher sensitivity and specificity, a new 3D algorithm is developed. The algorithm utilizes a top-hat transformation and dynamic threshold map to detect small AIH lesions. Several key structures of brain are detected and are used to set up a 3D anatomical coordinate system. A rule-based classification of the lesion detected is applied based on the anatomical coordinate system. For convenient evaluation in clinical environment, the CAD module is integrated with a stand-alone system. The CAD is evaluated by small AIH cases and matched normal collected in LAC/USC. The result of 3D CAD and the previous 2D CAD has been compared.