The presented master's thesis deals with the issue of storing and sharing data from medical imaging systems. This thesis, inter alia, consists of organizational and informatics aspects of medical imaging systems data in multicentric studies containing MRI brain images. This thesis also includes technical design of a web-based application for image data sharing including a web interface suitable for manipulation with the image data stored in a database.

This Thesis deals with the problems of medical image data management. It analyzes a metadata extraction problem from medical format DICOM and their efficient saving. System is designed as a client-server application. System provides an interface for DICOM data storing, interface for searching, data editing and exporting. System cooperatives with the collaborative system VCE. Implementation was carried out in C++ and PHP language with support of SQLite and MySQL database.

Dans le secteur des soins de santé, les données d'images médicales toujours croissantes, le développement de technologies d'imagerie, la conservation à long terme des données médicales et l'augmentation de la résolution des images entraînent une croissance considérable du volume de données. En outre, la variété des dispositifs d'acquisition et la différence de préférences des médecins ou d'autres professionnels de la santé ont conduit à une grande variété de données. Bien que la norme DICOM (Digital Imaging et Communication in Medicine) soit aujourd'hui largement adoptée pour stocker et transférer les données médicales, les données DICOM ont toujours les caractéristiques 3V du Big Data: volume élevé, grande variété et grande vélocité. En outre, il existe une variété de charges de travail, notamment le traitement transactionnel en ligne (en anglais Online Transaction Processing, abrégé en OLTP), le traitement analytique en ligne (anglais Online Analytical Processing, abrégé en OLAP) et les charges de travail mixtes. Les systèmes existants ont des limites concernant ces caractéristiques des données et des charges de travail. Dans cette thèse, nous proposons de nouvelles méthodes efficaces pour stocker et interroger des données DICOM. Nous proposons un modèle de stockage hybride des magasins de lignes et de colonnes, appelé HYTORMO, ainsi que des stratégies de stockage de données et de traitement des requêtes. Tout d'abord, HYTORMO est conçu et mis en œuvre pour être déployé sur un environnement à grande échelle afin de permettre la gestion de grandes données médicales. Deuxièmement, la stratégie de stockage de données combine l'utilisation du partitionnement vertical et un stockage hybride pour créer des configurations de stockage de données qui peuvent réduire la demande d'espace de stockage et augmenter les performances de la charge de travail. Pour réaliser une telle configuration de stockage de données, l'une des deux approches de conception de stockage de données peut être appliquée: (1) conception basée sur des experts et (2) conception automatisée. Dans la première approche, les experts créent manuellement des configurations de stockage de données en regroupant les attributs des données DICOM et en sélectionnant une disposition de stockage de données appropriée pour chaque groupe de colonnes. Dans la dernière approche, nous proposons un cadre de conception automatisé hybride, appelé HADF. HADF dépend des mesures de similarité (entre attributs) qui prennent en compte les impacts des informations spécifiques à la charge de travail et aux données pour générer automatiquement les configurations de stockage de données: Hybrid Similarity (combinaison pondérée de similarité d'accès d'attribut et de similarité de densité d'attribut) les attributs dans les groupes de colonnes; Inter-Cluster Access Similarity est utilisé pour déterminer si deux groupes de colonnes seront fusionnés ou non (pour réduire le nombre de jointures supplémentaires); et Intra-Cluster Access La similarité est appliquée pour décider si un groupe de colonnes sera stocké dans une ligne ou un magasin de colonnes. Enfin, nous proposons une stratégie de traitement des requêtes adaptée et efficace construite sur HYTORMO. Il considère l'utilisation des jointures internes et des jointures externes gauche pour empêcher la perte de données si vous utilisez uniquement des jointures internes entre des tables partitionnées verticalement. De plus, une intersection de filtres Bloom (intersection of Bloom filters, abrégé en ) est appliqué pour supprimer les données non pertinentes des tables d'entrée des opérations de jointure; cela permet de réduire les coûts d'E / S réseau. (...) / In the health care industry, the ever-increasing medical image data, the development of imaging technologies, the long-term retention of medical data and the increase of image resolution are causing a tremendous growth in data volume. In addition, the variety of acquisition devices and the difference in preferences of physicians or other health-care professionals have led to a high variety in data. Although today DICOM (Digital Imaging and Communication in Medicine) standard has been widely adopted to store and transfer the medical data, DICOM data still has the 3Vs characteristics of Big Data: high volume, high variety and high velocity. Besides, there is a variety of workloads including Online Transaction Processing (OLTP), Online Analytical Processing (OLAP) and mixed workloads. Existing systems have limitations dealing with these characteristics of data and workloads. In this thesis, we propose new efficient methods for storing and querying DICOM data. We propose a hybrid storage model of row and column stores, called HYTORMO, together with data storage and query processing strategies. First, HYTORMO is designed and implemented to be deployed on large-scale environment to make it possible to manage big medical data. Second, the data storage strategy combines the use of vertical partitioning and a hybrid store to create data storage configurations that can reduce storage space demand and increase workload performance. To achieve such a data storage configuration, one of two data storage design approaches can be applied: (1) expert-based design and (2) automated design. In the former approach, experts manually create data storage configurations by grouping attributes and selecting a suitable data layout for each column group. In the latter approach, we propose a hybrid automated design framework, called HADF. HADF depends on similarity measures (between attributes) that can take into consideration the combined impact of both workload- and data-specific information to generate data storage configurations: Hybrid Similarity (a weighted combination of Attribute Access and Density Similarity measures) is used to group the attributes into column groups; Inter-Cluster Access Similarity is used to determine whether two column groups will be merged together or not (to reduce the number of joins); and Intra-Cluster Access Similarity is applied to decide whether a column group will be stored in a row or a column store. Finally, we propose a suitable and efficient query processing strategy built on top of HYTORMO. It considers the use of both inner joins and left-outer joins. Furthermore, an Intersection Bloom filter () is applied to reduce network I/O cost.We provide experimental evaluations to validate the benefits of the proposed methods over real DICOM datasets. Experimental results show that the mixed use of both row and column stores outperforms a pure row store and a pure column store. The combined impact of both workload-and data-specific information is helpful for HADF to be able to produce good data storage configurations. Moreover, the query processing strategy with the use of the can improve the execution time of an experimental query up to 50% when compared to the case where no is applied.

No description available.

Made available in DSpace on 2014-12-17T15:48:05Z (GMT). No. of bitstreams: 1 FabianoP_DISSERT.pdf: 3905877 bytes, checksum: 0721827c114aec9f61c1c690dc27dd1d (MD5) Previous issue date: 2013-04-05 / The visualization of three-dimensional(3D)images is increasigly being sed in the area of medicine, helping physicians diagnose desease. the advances achived in scaners esed for acquisition of these 3d exames, such as computerized tumography(CT) and Magnetic Resonance imaging (MRI), enable the generation of images with higher resolutions, thus, generating files with much larger sizes. Currently, the images of computationally expensive one, and demanding the use of a righ and computer for such task. The direct remote acess of these images thruogh the internet is not efficient also, since all images have to be trasferred to the user?s equipment before the 3D visualization process ca start. with these problems in mind, this work proposes and analyses a solution for the remote redering of 3D medical images, called Remote Rendering (RR3D). In RR3D, the whole hedering process is pefomed a server or a cluster of servers, with high computational power, and only the resulting image is tranferred to the client, still allowing the client to peform operations such as rotations, zoom, etc. the solution was developed using web services written in java and an architecture that uses the scientific visualization packcage paraview, the framework paraviewWeb and the PACS server DCM4CHEE.The solution was tested with two scenarios where the rendering process was performed by a sever with graphics hadwere (GPU) and by a server without GPUs. In the scenarios without GPUs, the soluction was executed in parallel with several number of cores (processing units)dedicated to it. In order to compare our solution to order medical visualization application, a third scenario was esed in the rendering process, was done locally. In all tree scenarios, the solution was tested for different network speeds. The solution solved satisfactorily the problem with the delay in the transfer of the DICOM files, while alowing the use of low and computers as client for visualizing the exams even, tablets and smart phones / A visualiza??o de imagens tridimensionais (3D) est? cada vez mais presente na ?rea da medicina, auxiliando os m?dicos no diagn?stico de doen?as e na emiss?o de laudos. Com o avan?o dos equipamentos que geram imagens tomogr?ficas dos pacientes, como os de Tomografia Computadorizada (TC), est?o sendo geradas imagens cada vez mais n?tidas e, portanto, com resolu??es e tamanhos maiores. Atualmente, as imagens contidas em um exame de TC geralmente ocupam o tamanho de dezenas e centenas de megabytes, tornando o processo de visualiza??o 3D cada vez mais pesado - exigindo do usu?rio um equipamento com bom poder computacional. O acesso remoto ? estas imagens, via internet por exemplo, tamb?m n?o ? muito eficiente, pois todas as imagens precisam ser transferidas para o equipamento do usu?rio antes que o processo de visualiza??o 3D seja iniciado. Diante destes problemas (tamanho das imagens e acesso remoto), este trabalho envolve a cria??o e an?lise de um servi?o web para renderiza??o remota de imagens m?dicas 3D, denominado RR3D. Nele, todo o processo de renderiza??o volum?trica ser? realizado por um servidor, ou cluster de servidores, com alto poder computacional e somente a imagem 3D resultante ser? enviada ao cliente, permitindo que este ainda possa fazer opera??es como rota??o, zoom etc. O servi?o web ser? desenvolvido utilizando a linguagem Java e na arquitetura do projeto ser?o utilizados o programa de visualiza??o cient?fica Paraview, o framework ParaviewWeb e o servidor DCM4CHEE

[ES] La explotación de datos de salud ha demostrado ser de creciente interés en la comunidad científica, especialmente para la creación y uso de sistemas de ayuda a la decisión clínica (SADC). Para abordar este problema, tradicionalmente se ha investigado por separado en materia de modelos de información, modelos de dominio y SADC. En lo que se refiere a modelos de información, las propuestas presentan limitaciones semánticas y no tienen en cuenta la interacción con los modelos de dominio, que pretenden proporcionar una comprensión formal y compartida del conocimiento clínico, ni con los SADC, cuya finalidad es proporcionar apoyo a la toma de decisión clínica a partir de la historia clínica electrónica (HCE). La finalidad de esta tesis se enmarca dentro del objetivo general de enriquecer sistemas de HCE con resultados de SADC y modelos de dominio representados mediante datos enlazados abiertos. Para ello, se investiga la combinación y explotación conjunta de las tecnologías más avanzadas para modelos de información, modelos de dominio y SADC. La principal contribución de esta tesis es el desarrollo de metodologías y herramientas para enriquecer la HCE con resultados de SADC y datos enlazados abiertos. Las contribuciones específicas son las siguientes: * Definición conceptual y metodológica de la HCE aumentada con información potencialmente relevante de la web semántica. * Definición conceptual y metodológica del informe radiológico estructurado (IRE), enriquecido con resultados de SADC basados en reglas, visión por computación y modelos de aprendizaje automático. * Caso de uso de HCE aumentada, consistente en enriquecer la HCE resumida del Sistema Nacional de Salud de España con datos enlazados abiertos sobre interacciones farmacológicas y tratamientos recomendados para los episodios activos del paciente. * Sistema de IRE enriquecido con resultados de SADC. Incluye el desarrollo de plantillas de IRE y mecanismos para el enriquecimiento de las mismas con resultados de SADC basados en reglas, cuantificación de imagen médica y redes neuronales. Nuestro objetivo es mejorar el grado de interoperabilidad en las integraciones de sistemas de HCE con SADC y datos enlazados abiertos, mediante estrategias basadas en los tres pilares de la interoperabilidad semántica: modelos de información, de arquetipos y de dominio. Esto tiene el potencial de repercutir positivamente sobre la salud y el cuidado del paciente, especialmente en el paradigma de la medicina personalizada. / [CA] L'explotació de dades de salut ha demostrat ser de creixent interés en la comunitat científica, especialment per a la creació i ús de sistemes d'ajuda a la decisió clínica (SADC). Per a abordar aquest problema, tradicionalment s'ha investigat per separat en matèria de models d'informació, models de domini i SADC. Pel que fa a models d'informació, les propostes presenten limitacions semàntiques i no tenen en compte la interacció amb els models de domini, que pretenen proporcionar una comprensió formal i compartida del coneixement clínic, ni amb els SADC, la finalitat dels quals és proporcionar suport a la presa de decisió clínica partint de la història clínica electrònica (HCE). La finalitat d'aquesta tesi s'emmarca dins de l'objectiu general d'enriquir sistemes de HCE amb resultats de SADC i models de domini representats mitjançant dades enllaçades obertes. Per a això, s'investiga la combinació i explotació conjunta de les tecnologies més avançades per a models d'informació, models de domini i SADC. La principal contribució d'aquesta tesi és el desenvolupament de metodologies i eines per a enriquir la HCE amb resultats de SADC i dades enllaçades obertes. Les contribucions específiques són les següents: * Definició conceptual i metodològica de la HCE augmentada amb informació potencialment rellevant de la web semàntica. * Definició conceptual i metodològica de l'informe radiològic estructurat (IRE), enriquit amb resultats de SADC basats en regles, visió per computació i models d'aprenentatge automàtic. * Cas d'ús de HCE augmentada, consistent a enriquir la HCE resumida del Sistema Nacional de Salut d'Espanya amb dades enllaçades obertes sobre interaccions farmacològiques i tractaments recomanats per als episodis actius del pacient. * Sistema de IRE enriquit amb resultats de SADC. Inclou el desenvolupament de plantilles de IRE i mecanismes per a l'enriquiment de les mateixes amb resultats de SADC basats en regles, quantificació d'imatge mèdica i xarxes neuronals. El nostre objectiu és millorar el grau d'interoperabilitat en les integracions de sistemes de HCE amb SADC i dades enllaçades obertes, mitjançant estratègies basades en els tres pilars de la interoperabilitat semàntica: models d'informació, d'arquetips i de domini. Això té el potencial de repercutir positivament sobre la salut i la cura del pacient, especialment en el paradigma de la medicina personalitzada. / [EN] The exploitation of health data has proven to be of increasing interest in the scientific community, especially for the creation and use of clinical decision support systems (CDSS). To address this problem, separate research has traditionally been done on information models, domain models and CDSS. Regarding information models, the proposals present semantic limitations and do not consider the interaction with domain models, which aim to provide a formal and shared understanding of clinical knowledge, nor with CDSS, whose purpose is to provide clinical decision support from the electronic health record (EHR). The aim of this thesis is framed within the general goal of enriching EHR systems with SADC results and domain models represented by open linked data. For this purpose, the combination and joint exploitation of state-of-the-art technologies for information models, domain models and SADC is investigated. The main contribution of this thesis is the development of methodologies and tools to enrich EHR with SADC results and open linked data. Specific contributions are: * Conceptual and methodological definition of EHR augmented with potentially relevant information from the semantic web. * Conceptual and methodological definition of the structured radiology report (SRR), enriched with CDSS results based on logical rules, computer vision and machine learning models. * Augmented EHR use case, consisting of enriching the summarized EHR of the Spanish National Health System with linked open data on pharmacological interactions and recommended treatments for active patient episodes. * SRR system enriched with CDSS results. Includes the development of SRR templates and mechanisms for enriching them with SADC results based on logical rules, medical image quantification and neural networks. Our goal is to improve the degree of interoperability in EHR system integrations with CDSS results and linked open data, through strategies based on the three pillars of semantic interoperability: information, archetype and domain models. This has the potential to positively impact health and patient care, especially in the personalized medicine paradigm. / Mañas García, A. (2022). Enriquecimiento de la historia clínica electrónica con información de sistemas de ayuda a la decisión clínica y datos enlazados abiertos [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/187730 / TESIS

Abstract The purpose of this study was to investigate the quality of displays at radiology departments and healthcare centers, viewing conditions, quality control practices and user experiences of viewing radiological images from displays during 2007. The study aimed to provide guidelines to improving the quality of image viewing from displays and viewing conditions in healthcare. The data was gathered from radiology departments at university hospitals in Finland and healthcare centers in the treatment area of responsibility of the Oulu University Hospital. Display technology, quality control practices and users experiences of viewing were determined using questionnaires. Technical measurements were performed in order to acquire information on displays performance and viewing conditions. In addition, observation was used to evaluate viewing conditions. Almost all displays at radiological departments were applicable for diagnostics. At healthcare centers all displays were inapplicable for diagnostics. Both organization groups had displays using obsolete cathode ray tube technology and these displays did not pass current acceptance criteria. Most radiology departments had viewing conditions which were compatible with existing guidelines, whereas at healthcare centers lighting conditions were too bright for viewing radiological images from displays. Acceptance testing was done only for few of the displays and quality control was not performed regularly. Personnel responsible for quality assurance felt they were provided with inadequate resources for performing display quality control. Clinicians at healthcare centers did not identify the poor performance of displays. Radiologists and clinicians at healthcare centers rarely performed quality assurance for displays. The quality of displays, viewing conditions and the assessment of display performance at healthcare organizations was not at the level required by the existing guidelines. Both the cathode ray tube displays and uncalibrated liquid crystal displays should either be replaced with new ones or calibrated. Lighting and positioning of displays ought to be rearranged in order to diminish reflections. Furthermore, doctors ought to be able to rearrange lighting conditions with ease. More resources ought to be directed to display quality control and different quality control practices should be unified. Both the users and the quality control personnel should also be provided with more training in display quality control. Regular display quality control should be extended to all healthcare organizations. Clinicians working at healthcare centers should be provided with adequate training in the use of image viewing software. / Tiivistelmä Tämän tutkimuksen tarkoituksena oli selvittää vuoden 2007 aikana radiologisten yksiköiden ja terveyskeskusten radiologisten kuvien katseluun tarkoitettujen näyttöjen laatu, kuvankatseluolosuhteet ja laadunvalvontakäytännöt sekä käyttäjien kokemuksia röntgenkuvien katselusta näytöiltä. Tutkimuksen tavoitteena oli antaa toimenpide-ehdotuksia kuvankatselun ja kuvankatseluolosuhteiden kehittämiseksi terveydenhuollossa. Aineisto muodostui otoksesta viiden yliopistollisen sairaalan radiologisista yksiköistä ja Oulun yliopistollisen sairaalan erityisvastuualueen terveyskeskuksista. Näyttöjen laitekanta, laadunvalvontakäytännöt ja lääkäreiden kokemuksia näyttötyöskentelystä selvitettiin kyselyllä. Mittausten ja havainnoinnin avulla saatiin tietoa näyttöjen suorituskyvystä ja kuvankatselutilojen valaistusolosuhteista. Radiologisten yksiköiden näytöt olivat teknisesti pääosin radiologisista kuvista tehtävään diagnostiikkaan soveltuvia. Terveyskeskuksissa käytettiin näyttöjä, jotka eivät soveltuneet diagnostiikkaan. Molemmissa ryhmissä poistuvaan katodisadeputkitekniikkaan perustuvia näyttöjä oli vielä käytössä, eikä yksikään mitatuista näytöistä saavuttanut hyväksyttävyyskriteereitä kaikkien suorituskyvyn mittaustulosten osalta. Suurimmassa osassa radiologisten yksiköiden työpisteissä huoneen valaistus oli suositusten mukainen, kun taas terveyskeskuksissa huoneiden valaistus oli liian voimakas radiologisten kuvien katseluun käytetyillä näytöillä. Vastaanottotarkastus oli tehty vain pienelle osalle näytöistä ja säännöllistä laadunvalvontaa tehtiin näytöille vähän. Laadunvalvojat kokivat resurssit riittämättömiksi näyttöjen laadunvalvontaan. Terveyskeskuslääkärit eivät itse tunnistaneet näytön huonoa suorituskykyä. Radiologit ja terveyskeskuslääkärit tekivät laadunvalvontaa käyttämilleen näytöille hyvin vähän. Tutkimuksen kohteena olleissa radiologisissa yksiköissä ja terveyskeskuksissa röntgenkuvien katseluun tarkoitettujen näyttöjen laatu, valaistusolosuhteet ja laadunvalvonta eivät vastanneet suosituksia. Katodisädeputkinäytöt ja kalibroimattomat nestekidenäytöt tulisi vaihtaa uusiin tai kalibroida. Valaistusta ja näyttöjen sijoittelua tulisi muuttaa heijastusten vähentämiseksi. Lisäksi lääkärillä tulisi olla mahdollisuus muuttaa valaistusta helposti. Näyttöjen laadunvalvontaan tulisi saada enemmän resursseja, laadunvalvontakäytännöt tulisi yhtenäistää ja käyttäjille sekä laadunvalvojille tulisi antaa lisää koulutusta näyttöjen laadunvalvontaan. Säännöllinen näyttöjen laadunvalvonta tulisi ulottaa kaikkiin terveydenhuollon organisaatioihin. Terveyskeskuslääkäreille tulisi antaa koulutusta kuvankatseluohjelmien käyttöön.