Project

Telemedicina SES/SC

Goal: O Sistema Integrado Catarinense de Telemedicina e Telessaúde - STT/SC, com quase cinco milhões de exames realizados em seus 10 primeiros anos (2005 - 2015), possui tecnologia 100% própria e atende todos os 295 municípios catarinenses . Para realizar esta Rede a UFSC concebeu, desenvolveu e implantou para a SES/SC toda uma infraestrutura tecnológica de serviços de Telemedicina e Telessaúde, especialmente projetada para oferecer os serviços de atenção à saúde de altíssima tecnologia no contexto do SUS. Esta tecnologia é foi desenvolvida na íntegra em SC e passível de ser adaptada e estendida, de acordo com as necessidades. Este projeto visa a continuidade e refinamento da proposta inicial focando a expansão na oferta de serviços e desenvolvimento e implantação de novas tecnologias.

Updates
0 new
2
Recommendations
0 new
0
Followers
0 new
22
Reads
1 new
664

Project log

Harley Miguel Wagner
added a research item
Background: Brugada Syndrome is an inherited arrhythmogenic disorder characterized by the presence of specific electrocardiographic features with or without clinical symptoms. The patients present increased risk of sudden death due to ventricular fibrillation. The prevalence of this electrocardiographic pattern differs according to the studied region. However, epidemiological information including the Brazilian population is scarce. Objectives: To assess the prevalence of the electrocardiographic pattern of Brugada syndrome and the epidemiological profile associated with it. Methods: Cross-sectional study that included 846,533 ECG records of 716,973 patients from the electrocardiogram (ECG) database from the Santa Catarina Telemedicine Network over a 4-year period. All tests were 12-lead conventional ECG (without V1 and V2 in high positions). The tests revealing "Brugada Syndrome" diagnosis (Types 1 and 2) were reviewed by a cardiac electrophysiologist. The level of significance was set at p<0.05. Results: In total, 83 patients had a pattern potentially consistent with Brugada-type pattern ECG. Of these, 33 were confirmed having Brugada-type 1, and 22 with type 2 ECG after reevaluation. The prevalence of Brugada-type 1 ECG was 4.6 per 100,000 patients. Brugada-type 1 ECG was associated with the male gender (81.8% vs. 41.5%, p<0.001) and a lower prevalence of obesity diagnosis (9.1% vs. 26.4%, p=0.028). Conclusions: This study showed low prevalence of Brugada-type ECG in Southern Brazil. The presence of Brugada-type 1 ECG was associated with the male gender and lower prevalence of obesity diagnosis comparing to the general population.
Aldo Von Wangenheim
added 6 research items
Oral cancer is a global health problem, afflicting over 350,000 people each year, with 175 deaths in 2018 (BRAY et al. 2018). The high mortality rate is often associated with the advanced disease stage when firstly identified, usually by biopsy. This is a deadly and disfiguring disease that could greatly benefit from early detection approaches (WEIGUM et al., 2010). If early detected, the prognosis for the patients is excellent, improving the survival rate. The early detection of cancer can be achieved by non-invasive methods that preserve vital organ function and physical appearance, resulting in a better quality of life for the patients (SEIWERT; COHEN, 2005). For oral cancer, the surviving rate is 80% when detected in the early stages and 19% when detected in advanced stages (PEKTAȘ et al. 2006). Chromosome Instability has been gaining interest because it is a central process in the de-velopment of cancer cells, helping on early detection. This instability is indicative of the fact that the cell contains an abnormal amount of DNA, resulting in a process known as aneuploidy. This cel-lular abnormality has been associated with tumorigenesis. This ploidy analysis has long been a promising and economically viable solution to facilitate early cancer detection. However, this ap-proach has not been widely adopted in clinical routine (DANIELSEN; PRADHAN; NOVELLI, 2016). Nowadays, the biopsy is the gold standard in the detection of oral cancer/pre-cancer. However, be-cause it is an invasive method, it is recommended to be done in extreme cases only. Techniques like Exfoliative Cytology are non-invasive and painless, making it preferred by patients (CHATTERJEE et al., 2018). The Papanicolaou Staining is a popular staining procedure used in cytological slides and is widely used in medicine, where good results have been achieved on cervical screening exams. However, even with the low cost, it is not widely used on odontology (LUCENA et al., 2011). One of the problems is that this method is predominantly qualitative and exposed to subjectivity (CHAT-TERJEE et al., 2018). This manual evaluation of microscopic images is subject to variations in per-ceptions and level of expertise of the cytologists, making this process prone to human errors. Also, the slow processing time and the inherent subjectivity of manual analysis show be considered as reasons for using computational methods (LI et al., 2017). To overcome this, computer-assisted analysis can be used to measure the cytological alterations and indication of cellular status, helping on early cancer diagnosis (MEHROTRA et al., 2011; SHIN et al., 2010). Advances in optical imaging and image processing are pushing image cytometry forward, helping in the development of this area. However, in some problems like cell segmentation, most of the research relies on algorithms developed on years ago, such as Watershed Algorithm, K-Means Clustering, and even thresholding methods. Since these methods were developed to solve general problems, they have their limitations, showing a limited capability to solve some of the current problems (WANG, 2019). Today’s computational power and a large amount of annotated data pro-vided a way for methods based on neural networks and deep learning finally be applied (GUPTA et al., 2019). Advances in image analysis and machine learning make available more robust algorithms for extracting information from data (KANDEMIR; HAMPRECHT, 2015). Nowadays, Deep learning methods are the state-of-art in image processing. It is related to fundamental concepts in neuroscience and is inspired by the human brain. An artificial neural net-work is an abstracted interconnected network, consisting of neurons grouped into layers (GUPTA et al., 2019). Recently, deep learning methods have achieved good performance in various computa-tional tasks, showing to be effective for extracting the features from data in different settings (LECUN; BENGIO; HINTON, 2015). Recent efforts to use deep learning approaches in genomics and biomedical application show their flexibility for handling complex problems. Therefore, using deep learning methods to analyze cytometry data is a very promising approach (LI et al., 2017).
Cervical cancer is the second most common cancer type in women around the world. In some countries, due to non-existent or inadequate screening, it is often detected at late stages, making standard treatment options often absent or unaffordable. It is a deadly disease that could benefit from early detection approaches. It is usually done by cytological exams which consist of visually inspecting the nuclei searching for morphological alteration. Since it is done by humans, naturally, some subjectivity is introduced. Computational methods could be used to reduce this, where the first stage of the process would be the nuclei segmentation. In this context, we present a complete pipeline for the segmentation of nuclei in Feulgen-stained images using Convolutional Neural Networks. Here we show the entire process of segmentation, since the collection of the samples, passing through pre-processing, training the network, post-processing and results evaluation. We achieved an overall IoU of 0.78, showing the affordability of the approach of nuclei segmentation on Feulgen-stained images. The code is available in: https://github.com/luizbuschetto/feulgen_nuclei_segmentation.
RESUMO: Introdução: As intoxicações por agrotóxicos causam elevada morbimortalidade. A vigilância é necessária da produção até o uso desses produtos. Objetivo: Analisar as intoxicações e os fatores associados à letalidade por agrotóxicos. Método: Trata-se de estudo caso controle baseado nos atendimentos de intoxicação por agrotóxicos realizados em 2017 por centros de informação e assistência toxicológica do Brasil. Pacientes que evoluíram a óbito compuseram o grupo caso, e os sobreviventes, o grupo controle. Calculou-se odds ratio (OR) dos fatores de risco para óbito, com intervalo de confiança (IC) de 95%. Com base no modelo de regressão, desenvolveu-se um modelo preditivo de morte, estratificado por faixa etária, sexo e contexto ocupacional, para investigação do risco dos trabalhadores agropecuários intoxicados por agentes extremamente tóxicos. Resultados: Identificaram-se 3.826 pacientes intoxicados por agrotóxicos, dos quais 146 evoluíram para óbito. Idosos (OR = 4,94; IC95% 2,49-9,80), homens (OR = 1,68; IC95% 1,15-2,46), trabalhadores do setor agropecuário (OR = 2,20; IC95% 1,15-4,24), tentativas de suicídio (OR = 13,27; IC95% 6,48-27,19) e exposição a produtos extremamente tóxicos (OR = 2,77; IC95% 1,84-4,16) apresentaram mais chances de óbito nas intoxicações por agrotóxicos. Conclusão: Em cada 100 intoxicações por agrotóxicos, quatro evoluíram para óbito. Idosos, homens, trabalho no setor agropecuário, tentativas de suicídio e produtos extremamente tóxicos apresentaram mais chances de óbito. Palavras-chave: Praguicidas. Agroquímicos. Intoxicação. Mortalidade. Centros de controle de intoxicações. Estudos de casos e controles. Intoxicações e fatores associados ao óbito por agrotóxicos: estudo caso controle, Brasil, 2017 Poisoning and associated factors to death from pesticides: case-control study, Brazil, 2017
Harley Miguel Wagner
added a research item
The State of Santa Catarina is located in the South of Brazil, covering an area of 95,730 km2, and is divided into 295 municipalities, with an estimated population of 7.164.788 inhabitants. Specialised medical facilities are centralised in urban centres. The State has 39 registered Oral Medicine (OM) specialists (one per 183,700 inhabitants).
Aldo Von Wangenheim
added a research item
Cytology is a low-cost and non-invasive technique where cells are harvested from tissues by aspiration or scraping that is used to diagnose a broad range of pathologies. Although this procedure is performed by clinical consultants extensively trained for that, it is a time consuming and repetitive process where most of the diagnostic criteria are vulnerable to human interpretation and failure. Hence, the use of computer technologies can reduce the chances of misdiagnoses, shorten the time required for the analysis and help on early cancer diagnosis. In order to identify the state-of-art of computer vision techniques applied on cytology images, we conducted a Systematic Literature Review based on the protocols elaborated by Barbara Kitchenham, searching for approaches to cell segmentation, detection, and classification using computer vision on cytology slides images and analyzing papers published in the last years. The initial search was made on March 6th, and resulted in articles that we analyzed based on the inclusion/exclusion criteria, resulting in papers that we used to evaluate the tendencies and main problems present in this research area, highlighting the computer vision methods, staining techniques, evaluation metrics, and the availability of the used datasets. As a result, we found out that the most used methods in the analyzed works are deep learning-based (papers), especially Convolutional Neural Networks (papers), while fewer works use classic computational vision only methods (papers). The most recurrent metric used was the accuracy for classification (papers) and the Dice Similarity Coefficient for segmen-tation and object detection (papers). Regarding staining techniques, Papanicolaou was the most used one (papers), followed by H&E (papers) and Feulgen (papers). Among the datasets used in the papers, 8 of them are publicly available, with ISBI and ISBI being the most used ones. Analyzing the papers found on this review, we concluded that there is a lack of high-quality datasets for some types of stain, most of the works are not ready to be applied on a daily clinical routine, and there is a tendency to adopt deep learning methods in the future.
Aldo Von Wangenheim
added a research item
With the objective to perform a first evaluation of the impact of the integration of a graphic spatial epidemiology tool that allows quasi-realtime georeferenced data visualization into a telemedicine infrastructure, this work presents GISTelemed, an online module specialized on indexing structured and semi-structured data, as well as querying the indexed content using structured and free-text search. We evaluated GISTelemed accordingly to the guidelines published by the US Centers for Disease Control and Prevention and input provided by a questionnaire customized according to AdEQUATE (questionnAire for Evaluation of QUAlity in TElemedicine systems). 39 healthcare professionals from 13 municipalities participated in the evaluation. We analyzed data from questionnaires using descriptive statistics, being Lernability and Comfort the characteristics that received the best evaluation. Quantitative evaluation based upon leprosis cases detected through tele-dermatology showed a sensitivity and PPV of respectively 77.2% and 95.3%. 22.8% of the cases detected were un-notified cases. Results from our case study show a good evaluation regarding the perceived software quality”. We conclude that the integration of spatial epidemiology tools to the STT/SC system, besides enabling visualization of data in maps, allowed users to analyze the evolution of morbidities and their co-occurrences.
Aldo Von Wangenheim
added 2 research items
A structured reporting system is a set of standard-compliant practices that guides the physicians in order to create structured documents. In practice, those systems bring transparency in the handling of medical documents by the user, organizing and simplifying their workload. In spite of this advantages, many physicians still use conventional methods to write their findings, like free-text reports. One main reason for this is the little convention on how to disseminate a structured reporting routine in the report environment, covering technological and scientific needs to achieve such status. This work proposes a systematic approach to migrate a system routine from free-text reports to structured reports, focusing on the DICOM Structured Reporting guidelines. To evaluate this proposal, a structured reporting system was created in the context of the Santa Catarina State Integrated Telemedicine and Telehealth System (STT/SC), in Brazil, and, in a case study covering obstetric ultrasonography reports, was evaluated by a group of experts using the AdEQUATE model, showing a high user perception from the system. The results are a set of defined premises and steps that turns a telemedicine system into a complete structured reporting environment.
Telepathology systems (TPS) can improve and accelerate the process of diagnosis, particularly in those complex cases where the second expert/specialized opinion is required. To support scenarios involving complex cases, a TPS must provide collaborative virtual microscopy and communication between pathologists to accelerate and improve the process of reporting, while guaranteeing a good degree of image quality in order to enable the evaluation of microscopic details. The development of TPSs in large telemedicine environments has not yet been addressed properly. With this problematic in mind, we developed a TPS within the Santa Catarina State Integrated Telemedicine and Telehealth System (STT/SC), that allows pathologists to report pathology cases employing a collaborative environment with audio/video conferencing and that simulates a virtual multi-headed microscopy. To prove the concept of our system we performed a case study with pathologists from different institutions countrywide and applied an evaluation using the AdEQUATE Model. Our system scored good results, especially regarding its effectiveness, learnability, and comfort.
Alexandre Savaris
added a research item
Even with the many advantages of adopting a structured reporting system, there is little convention on how to disseminate this routine into the report environment. This work proposes a systematic approach to migrate a system routine from free-text reports to structured reports, focusing on the DI-COM Structured Reporting guidelines. We evaluated this proposal by creating a reporting module in the context of a telemedicine system, and performing case study covering ultrasonography reports. Using the AdEQUATE model, the evaluation showed a high user perception from the system, directly reflecting the quality of our proposal. The results are a set of defined premises and steps that turns a telemedicine system into a complete structured reporting environment.
Aldo Von Wangenheim
added a research item
The Brazilian Constitution of 1988 defines health as a universal right. O Sistema Únicode Saúde (SUS), is one of the largest public Health systems in the world providing free access to integrated care. SUS is managed and financed by the federation, states and municipalities. It includes primary, sub-acute,acute care, emergency services, dental care, disease prevention, environmental health and medications. Thereare 322 thousand health facilities (74% are private). Of the 6,810 hospitals, 64% are private and contracted to provide services to SUS, including specialist and diagnostic services. Health expenditure is 9% of GDP of which 45% is public sector and 55% is private sector and individual. The private sector services 24.5% of the population. The Family Health Program covers 40,000 primary health facilitiesandis the main plankfor improving the quality of health care and expanding coverage of the population of 220 million people. The program provides multi-professional teams, ideally including a family health practitioner and nurse, and community health workers, a dentist or oral health specialistand mental health worker. Brazilian expenditure on health care per person (2015) in purchasing power terms was 28% of Australia. There are 1.8doctors in Brazil per 1,000 people compared with 3.81 doctors per 1,000 people in Australia. Doctors and services are unevenly distributed over large areas of the country leading to high patient transport costs. The National Telehealth Program aims to improve the quality of primary health care integrated with continuing professional education using information and communications technologies. In 2018 there were 26 telehealth centres active in 24 out of the 27 Brazilian states connected to aUniversity Telemedicine Network (RUTE) that runs more than 50 health related virtual discussion groups. All offerteleconsultation and education services and generation of formative second opinions. Many Telehealth Centres integrate teleconsultations into state wide patient triaging for further treatment, reducing specialist waiting lists and times for radiology reporting, cardiology and electrocardiograms, tele-ophthalmology, tele-stomatology, tele-respiratory, tele-dermatology consultations. Advice may be requested about vaccination campaigns, IT systems, medications and clinical supplies.
Aldo Von Wangenheim
added a research item
Software systems used for healthcare delivery should satisfy the stated and implicit needs of its various stakeholders, in other words, to have a high software quality degree to reduce, for instance, prescription or diagnose errors, and to avoid negative effects on a patient's health status. % In this context, software quality models are developed to measure how a software system is operating with quality. These models decompose the concept of quality into more manageable characteristics and sub-characteristics. However it is not trivial to evaluate the perception of software quality by the end users in Information and Communication Technology (ICT) based healthcare systems -- an umbrella term that encompasses a wide range of remote healthcare delivery domains, like telemedicine (the use of telecommunications for medical diagnosis and patient care) and telehealth (health promotion and disease prevention using ICT).
Aldo Von Wangenheim
added a research item
QUAL É O OBJETIVO DESTE POP? O objetivo deste POP é verificar a situação das filas de eventos relacionadas ao processo de recebimento de exames diretamente no sistema PACS (Picture Archiving and Communication System) da bridge DICOM, bem como ao processo de recebimento de exames pelo serviço de integração com sistemas de informação hospitalar (Hospital Information Systems - HIS). POR QUE EXISTE ESTE POP? Este POP existe para auxiliar na verificação do funcionamento dos serviços relacionados à integração entre sistemas, contemplando dados de agendamento de exames e imagens adquiridas pelos equipamentos conectados à rede dos estabelecimentos de saúde. PARA QUEM SE DESTINA ESTE POP? Este POP se destina a analistas e técnicos de TI responsáveis pela instalação, configuração e manutenção dos serviços de integração de dados ofertados pela bridge DICOM no estabelecimento de saúde. QUANDO ESTE POP DEVE SER SEGUIDO? Este POP deve ser seguido quando forem identificadas diferenças entre os dados enviados e recebidos de/para sistemas HIS, equipamentos e a bridge DICOM.
Aldo Von Wangenheim
added a research item
QUAL É O OBJETIVO DESTE POP? O objetivo deste POP é verificar se os serviços relacionados a banco de dados, conteúdo DICOM, worklist e integração com sistemas de informação hospitalar (Hospital Information Systems - HIS) estão devidamente configurados e funcionando. POR QUE EXISTE ESTE POP? Este POP existe para auxiliar na verificação do funcionamento dos serviços relacionados a dados e imagens médicas disponibilizados pela bridge DICOM. PARA QUEM SE DESTINA ESTE POP? Este POP se destina a analistas e técnicos de TI responsáveis pela instalação, configuração e manutenção dos serviços ofertados pela bridge DICOM no estabelecimento de saúde. QUANDO ESTE POP DEVE SER SEGUIDO? Este POP deve ser seguido quando: 1. equipamentos utilizados na aquisição de imagens acusarem falhas no envio e/ou armazenamento de conteúdo no sistema PACS (Picture Archiving and Communication System); 2. registros de worklist não forem disponibilizados aos equipamentos utilizados na aquisição de imagens; 3. registros de agendamento de exames feitos no HIS e/ou exames executados sem worklist e enviados diretamente ao PACS não estiverem disponíveis no Sistema Integrado Catarinense de Telemedicina e Telessaúde (STT/SC).
Aldo Von Wangenheim
added a research item
QUAL É O OBJETIVO DESTE POP? O objetivo deste POP é verificar se a bridge DICOM está acessível e com os serviços mínimos de rede devidamente configurados e funcionando. A bridge DICOM é responsável por intermediar a comunicação segura entre os equipamentos de seu estabelecimento de saúdel e o Sistema Integrado Catarinense de Telemedicina e Telessaúde - STT, permitindo o envio automático e seguro de exames ao servidor central do sistema. POR QUE EXISTE ESTE POP? Este POP existe para auxiliar na verificação dos requisitos básicos de comunicação necessários ao funcionamento da bridge DICOM. PARA QUEM SE DESTINA ESTE POP? Este POPse destina a analistas e técnicos de TI responsáveis pela instalalação, configuração e manutenção da bridge DICOM no estabelecimento de saúde. QUANDO ESTE POP DEVE SER SEGUIDO? Este POP deve ser seguido quando o suporte da Central Estadual de Telemedicina reportar problemas de acesso remoto à bridge DICOM.
Aldo Von Wangenheim
added an update
Publicado novo relatório técnico sobre a economia de custos diretos e de encaminhamentos que estamos obtendo com a Teledermatologia. Confira aqui:
 
Aldo Von Wangenheim
added a research item
This study is based upon statistics from 83,100 teledermatological examination protocols that were performed at Primary Healthcare Facilities in the context of the STT/SC between January, 2014 and June, 2018 and employed for patient triage. The amount of dermatologic patients with low complexity in reference center brought the need to implement a screening system able to reduce the number of referrals and increase resolution at UBS, was deployed teledermatology. There were no Brazilian studies assessing the economy of this system. Objectives: To analyze the financial impact of the implementation of teledermatology in screening UBS patients. Methods: Cross-sectional observational epidemiological study with teledermatology patients of the state of Santa Catarina.
Aldo Von Wangenheim
added a research item
Abstract. Our initial motivation to study concerning this domain application was consolidated through dif�culty lived for healthcare institutes. The more hospital dif�culty are in the treatment of its information and work�ow management. The implementation of process management systems requires the use of sustainable technologies. In processes management scene in workflow management system, the workflow engine is very important part. This work presents a sustainable model for the implementation of a medical workflow management system engine. Now, our model is in conception, evaluation and validation preliminary phase yet, however we think that us will get excellent results in future.
Aldo Von Wangenheim
added a research item
A specially developed controlled vocabulary, the SBC/CSR Vocabulary, developed fr Telemedicine Network based upon the Guidelines of the Brazilian Cardiology Society.
Alexandre Savaris
added a research item
Este artigo tem como base um estudo em que foram levantados e organizados termos do domínio da radiologia obstétrica e, então, foi identificado se os mesmos estão compreendidos em quatro distintos vocabulários controlados: OntoNeo, RadLex, LOINC e SNOMED. É apresentado o Sistema Integrado Catarinense de Telemedicina e Telessaúde (STT/SC) e o projeto de estruturação de laudos de exames de radiologia obstétrica, bem como o contexto teórico da ciência da informação sobre vocabulários controlados. Foram realizadas uma pesquisa de campo para o levantamento dos termos junto a um especialista da área e uma pesquisa documental para o levantamento estatístico dos termos em vocabulários controlados. Constituiu-se uma hierarquia dos termos levantados e verificou-se a cobertura de cada um dos vocabulários controlados em relação aos termos. O SNOMED é o vocabulário controlado com maior potencial de uso para a indexação de laudos no domínio da radiologia obstétrica.
Aldo Von Wangenheim
added a research item
Objetivo: Descrever o perfil de atendimento de um CIATox. Método: Análise do registro de atendimento no Sistema de DATATOX/BI, ferramenta Open Source: Saiku 2.6, customizado pelo Laboratório de Telemedicina/UFSC. Resultados: No ano de 2015 foram registrados 11.832 atendimentos, de 258 (87,4%) municípios do Estado. Desses 11.229 casos de exposição humana (94,9%), 96 animal (0,8%) e 507 informação sem acidente (4,3%). Foram registrados 25.792 acompanhamentos até o desfecho final. Das 11.229 exposições humanas a maior frequência ocorreu nas residências (72,4%), zona urbana (68,7%), no gênero feminino (51%). Na faixa etária de 1 a 4 anos foram registrados 16% dos atendimentos e 33,5% nos adultos jovens de 20 a 39 anos. A principal circunstância de exposição foi acidental (54,6%), seguida das tentativas de suicídio (23,0%) e do acidente ocupacional (8,3%). Por grupos agentes aparece em primeiro lugar os Animais Peçonhentos com 27,5%, seguido pelos Medicamentos (27,0%), Diagnóstico diferencial (18%), Agrotóxico (8,0%), Produtos Químicos Industriais (4,5%), Domissanitários (4,0%), Drogas de Abuso (2,2%) e Plantas Tóxicas (1,1%). Foram classificados como leves 57,5% dos casos. Foram registrados 64 (0,6%) óbitos desses 51 relacionados à intoxicação e 13 óbitos por outra causa. Os Medicamentos foram responsáveis por 18 (35,3%) óbitos seguidos pelos Agrotóxicos com 14 (27,5%), Drogas de Abuso 8 (15,7%), Produtos Químicos 2 (3,9%), Animais Peçonhentos um (2,0%), Alimentos um (2%) e Associação de Grupos 7 (13,7%). Conclusões: Os Medicamentos a nível mundial são os principais agentes envolvidos nas intoxicações nestes dados além da alta frequência da exposição foram responsáveis pelo maior número de óbitos.
Aldo Von Wangenheim
added 2 research items
For automated astrocytoma grading morphometric parameters are determined by means of an image analysis system and a special Ki-67(MIB1)/Feulgen-staining method allowing the quantification of the essential characteristics of malignant gliomas: growth pattern, cellularity, proliferation index and nucleus pleomorphism. Based upon a cluster analytical approach a grading scale resembling the WHO-scheme is established which is suitable for automatic glioma grading purposes (HOM-scale). For automatic glioma grading backpropagation neural networks are employed. The results are compared with those of a classical multivariate discriminant classificatory analysis. The presented approach can also be employed for automatic grading of other tumour entities.
Aldo Von Wangenheim
added 2 research items
In stereotactically obtained astrocytoma biopsies, four morphometric nuclear parameters were determined with the use of an image analysis system. A special Ki-67 (MIB1)/Feulgen stain made it possible to quantify the essential characteristics of gliomas of the astrocytoma/glioblastoma group: growth pattern, cellularity, proliferation tendency and nucleus pleomorphism. A grading scale based on a cluster analysis resembling the WHO-scheme, which is suitable for automated astrocytoma grading, was developed. Large back propagation neural networks were used and their results compared with those of a classical multivariate discriminant classification analysis. It is possible to show that the neural network technology is superior to the statistical approach for automated astrocytoma grading. Based on the results of our study we believe neural network technology to be useful for tumour grading problems. The presented approach can be generalized for the automated grading of other tumour entities.
Aldo Von Wangenheim
added 4 research items
Introduction We describe a method for the automatical registration of transversal MRI-head-volumes. Under automatical registration we understand the automatical determination of an adequate coordinate system for a specific head volume, which is adapted to this particular head, describing the position, direction and size of the head in the respective MRIvolume. This research was part of the Cyclops-Project 1 at the Artificial Intelligence Institute of the University of Kaiserslautern. The aim of the Cyclops-System [VW96] is to provide a software workbench for the development of knowledgebased image understanding applications, particularly in the field of analysis of MRI-images. The Cyclops-System can act as an image-understanding expert system, which directs the process of analysis of specific images, providing image analysis control knowledge and domain-specific (image contents -s
This is a report on a new integrated system 1 for the automatic analysis of MRI-breast images for the early detection of breast cancer. The system operates on images taken using the method of dynamic contrast-enhanced MRI. Suspicious lesions in the breast are automatically marked with a special colour, thus directing the attention of the physicians towards the critical breast regions. The medical support system is based on a newly invented image-matching algorithm, based on self-organizing maps (SOM), which enable the system to work properly even with image sequences that are strongly deformed by the patient's breathing movements. The system was tested on real data and the results are presented. Motivation The MAMMALYZER 2 presents a diagnosis supporting image processing system, which preprocesses dynamic MR-Mammographs (MRM) for easier and less erroneous analyses by the medical practitioner. The breast images are provided by a special MRI sequence, which is based o...
We present a new data-driven feature-point registration method for image sequences. This method is based on a modified Kohonen network model that performs local non-affine transformations based on a point's neighbourhood context. This new method is ideal for non-real time applications where the situation is too complex to enable an operational modelling of the transformations needed for a point-to-point mapping from one image into another such as in contrast-enhanced sequences of MRI-mammogramms. This new method is compared to existing approaches. The results of tests with different types of grey-value images are discussed.
Aldo Von Wangenheim
added a research item
We present an integrated system for the automatic analysis of MRI-breast images towards the early detection of breast cancer. The system operates on taken images using the method of dynamic contrast-enhanced MRI. Suspicious breast lesions are automatically marked with colours, thus directing the physician’s attention towards the critical regions. The medical support system is based on image-matching algorithms using self organizing maps (SOM) and Monte Carlo methods, which enables the system to work properly even with image sequences that are strongly deformed by the patients breathing movements. The system is tested on real patient data and is now being refined in cooperation with Dr. Buddenbrock, Dr Blasinger, Dr. Benz hospital for Radiology and Nuclear Medicine, Mainz.
Aldo Von Wangenheim
added 2 research items
Most of the digital medical devices used in modern clinics and practice provide data corresponding to the DICOM Standard. Cyclops, a knowledge-based image analysis system developed at the University of Kaiserslautern, was suitable to analyze such images, but we needed a DICOM interface to connect to DICOM databases easily and transfer data to the system. All non-commercial software available were not up to our demands, so we implemented a DICOM network client by our own, which can connect to the ctn image server, based on an SQL database. We attached great value to a neat, object-oriented implementation, because it is easy to expand and we are flexible to future versions of the DICOR/I standard
Aldo Von Wangenheim
added 7 research items
We describe a method for the automatic registration of transversal MRI-head-volumes. Under automatic registration we understand the determination of an adequate coordinate system for a specific head volume, which is adapted to this particular head, describing the position, direction and size of the head in the respective MRI-volume. After determining the coordinate system the specific head volumes are mapped against a model of an anatomical atlas
We describe a method for the automatical registration of transversal MRI-head-volumes. Under automatical registration we understand the automatical determination of an adequate coordinate system for a specific head volume, which is adapted to this particular head, describing the position, direction and size of the head in the respective MRI-volume.
We describe a computational method to assist radiologists in performing better more reliable and simpler diagnosis of neurocysticercosis (NC). Based on this method we implemented a software system that counts and measures the calcifications related to NC in computed tomography (CT) scans, thus reducing errors regarding visual inspection and providing better quantitative data. During computation, the system segments grey scale images obtained by CT scans and resulting segments are submitted to classification using artificial neural networks (ANNs). The system marks NC findings, replacing automatically all areas in the original image classified as NC with specially coloured markings. Afterwards, the system starts correlating NC-findings in different slices and performing a 3D reconstruction based on NC-classified areas belonging to the same finding. As a final step, the system performs a 3D reconstruction of the patient's skull, encephalic mass and findings boundaries, generating a 3D representation of the patient's head and the localisation of NC findings. In this step the volumes of each NC finding are also calculated
Aldo Von Wangenheim
added 4 research items
In this paper we present a workflow component for the knowledge intensive task of reporting radiological images. Our component integrates the current developments in medical standards. It should act as an organizational memory for private radiological hospitals and help to train young physicians. We have build a computer aided methodology to create standard examination protocols and the physician can use an assistant system during his daily work. Our approach helps to save the organizational knowledge of a private hospital.
We present a parallel matching component of an integrated system for the automatic analysis of MRI-breast images towards the early detection of breast cancer. The system operates on images using the method of dynamic contrast-enhanced MRI. Suspicious breast lesions are automatically marked with colours, thus directing the physician's attention towards the critical regions. A proper and careful decision procedure is needed to differentiate between increases of signal intensity triggered by noise and tissue dislocations (motion artifacts) and increases that are triggered by an accumulation of contrast agent in the related breast region. We present our component for image matching using self organising maps (SOM), which enables the system to work properly even with image sequences that are strongly deformed by the patients breathing movements. To reach the time constraint of 15 minutes in medical practice we decide to implement a parallel architecture for the neural network matcher, which works on all computers in the heterogeneous network of our medical partners. The system is tested on real patient data and is now being refined in cooperation with our partner hospital for Radiology and Nuclear Medicine in Mainz
This is a report on a new integrated systemgif for the automatic analysis of MRI-breast images for the early detection of breast cancer. The system operates on images taken using the method of dynamic contrast-enhanced MRI. Suspicious lesions in the breast are automatically marked with a special colour, thus directing the attention of the physicians towards the critical breast regions. The medical support system is based on a newly invented image-matching algorithm, based on self-organizing maps (SOM), which enable the system to work properly even with image sequences that are strongly deformed by the patient's breathing movements. The system was tested on real data and the results are presented.
Aldo Von Wangenheim
added 4 research items
Este artigo apresenta o modelo SIAPDI (Serviço Integrado de Acesso e Processamento Distribuído de Imagens), um ambiente de software que permite equipes médicas radiológicas acessarem banco de imagens em conformidade ao padrão DICOM 3.0 (Digital Image Communications in Medicine) [02], provenientes de equipamentos radiologicos para executar o processamento das imagens para o auxílio ao diagnóstico em vários equipamentos localizados em rede local para distribuir o processamento. Este modelo foi criado devido ao enorme custo computacional de processamento exigido nos computadores. Desta maneira pode-se utilizar equipamentos localizados na rede, independentemente de sistema operacional, para executar o processamento distribuído de imagens, repercutindo em uma redução no tempo dos resultados. Outro tópico importante é onde clinicas e hospitais não possuem estações radiológicas de alto processamento, devido ao alto custo das mesmas, podendo utilizar PCs para tal finalidade.
Aldo Von Wangenheim
added 2 research items
Sala de Laudos Virtual é um ambiente de software que permite equipes médicas radiológicas acessarem banco de imagens em conformidade ao padrão DICOM 3.0 (Digital Image Communications in Medicine) [01][02], provenientes de equipamentos radiologicos, disponibilizar estas imagens com outros médicos localizados geograficamente distantes, utilizando a tecnologia Internet existente para a elaboração conjunta do laudo e diagnóstico dos pacientes, através de um editor de laudos, ferramentas de manipulação de imagens compartilhadas entre os participantes da Sala de Laudos Virtual e um canal de áudio conferência. Este ambiente permite um melhor diagnóstico em casos difíceis, utilizando-se de opiniões de outros especialistas, repercutindo em melhores tratamentos para os pacientes, os médicos não precisam estar fisicamente presentes nas salas de laudos de clinicas e hospitais e a não necessidade de impressão de chapas radiológicas, ocasionado com isto reduções de custos.
Aldo Von Wangenheim
added 4 research items
RESUMO -Neste artigo é apresentada uma metodologia que tem por objetivo auxiliar no planejamento do tratamento cirúrgico endoluminal da doença de aneurisma de aorta abdominal.. Esse método utiliza, entre outras técnicas, o reconhecimento de imagens, em especial da artéria aorta e do aneurisma abdominal. Após o reconhecimento e segmentação dessas estruturas é possível fazer a correta mensuração dos mesmos gerando dados mais confiáveis para a produção de endopróteses necessárias ao tratamento da patologia. Também é possível a reconstrução tridimensional das estruturas anatômicas, tornando a visualização e análise dos dados mais confiável. Este trabalho é parte integrante do Projeto Cyclops [1] de desenvolvimento de ferramentas inteligentes para análise de imagens médicas, realizado em parceria entre a UFSC e a Universidade de Kaiserslautern, Alemanha. Palavras-chave: Análise Inteligente de Imagens, Segmentação, Reconstrução 3D, Rotulação Consistente, Redes Neurais Categoria: Artigo para o Workshop de Informática na Saúde DESENVOLVIMENTO E IMPLEMENTAÇÃO DE TECNOLOGIAS COMPUTACIONAIS PARA MENSURAÇÃO DE ANEURISMAS DE AORTA ABDOMINAL E CONSTRUÇÃO DE PRÓTESES ENDOLUMINAIS PERSONALIZADAS RESUMO -Neste artigo é apresentada uma metodologia que tem por objetivo auxiliar no planejamento do tratamento cirúrgico endoluminal da doença de aneurisma de aorta abdominal.. Esse método utiliza, entre outras técnicas, o reconhecimento de imagens, em especial da artéria aorta e do aneurisma abdominal. Após o reconhecimento e segmentação dessas estruturas é possível fazer a correta mensuração dos mesmos gerando dados mais confiáveis para a produção de endopróteses necessárias ao tratamento da patologia. Também é possível a reconstrução tridimensional das estruturas anatômicas, tornando a visualização e análise dos dados mais confiável. Este trabalho é parte integrante do Projeto Cyclops [1] de desenvolvimento de ferramentas inteligentes para análise de imagens médicas, realizado em parceria entre a UFSC e a Universidade de Kaiserslautern, Alemanha. ABSTRACT -In this article a methodology is presented to aid in the planning of abdominal aortic aneurysms surgeries. This method addresses the image recognition, specially of the aorta artery and abdominal aneurysm. After the recognition and segmentation of those structures it is possible to obtain a correct measurement of the same structures generating more reliable data for manufacturing required endoprotheses for the treatment of the pathology. The three-dimensional reconstruction of the anatomical structures is also possible making the visualization and analysis of the data more reliable. This work is part of the Cyclops Project which intends the development of intelligent tools for the analysis of medical images, accomplished in partnership between UFSC and the University of Kaiserslautern, Germany.
Aldo Von Wangenheim
added 6 research items
In the German-Brazilian cooperation project Cyclops, we are building an integrated solution in order to capture the exponentially growing medical knowledge. The system is being developed in close cooperation with private radiological hospitals in Germany and Brazil. One aim is easy knowledge exchange between the medical partners in both countries. In this paper, we describe POKMAT (Process-oriented Knowledge MAnagement Tool) and its application to medical examination guidelines. We focus on the support of examination processes and automatic report generation in a DICOM environment. In the future, the system will be extended to an organizational memory of the practice
A utilização de PACS (Picture Archiving and Communication Systems) está cada vez mais difundida entre hospitais e clínicas brasileiros. Juntamente com o crescente interesse pela Telemedicina, este cenário proporciona um ambiente favorável ao compartilhamento de estudos e imagens entre clínicas e hospitais. Com isso, torna-se possível um acompanhamento mais efetivo do histórico de saúde de um paciente. Neste trabalho apresentamos um framework, denominado Portal de Teleradiologia, para integração de diferentes e possivelmente heterogêneos bancos de imagens médicas distribuídos em várias de clínicas e hospitais. Através dos serviços deste Portal de Teleradiologia torna-se possível a construção transparente de banco de dados geograficamente distribuído de exames radiológicos. A identificação única de um paciente entre as diversas bases de dados e o acesso e a segurança das informações disponibilizadas foram as principais questões que permearam este trabalho.
Presents the IIADPS (Integrated Image Access and Distributed Processing Service) model, a software environment that allows radiological medical teams to have access to distributed image processing facilities in conformance to the DICOM 3.0 (Digital Image Communications in Medicine) standard. The model allows one to remotely execute distributed image processing for diagnosis tasks on any low-cost equipment located on a local network or high-speed wide area network. The model was developed due to the enormous computational processing requirements normally posted to these tasks. Our approach allows low-cost equipment located in a network to be used, independent of the operating system, to execute distributed image processing, leading to a significant reduction in the processing time. This enables also hospitals which do not have radiological stations of high processing capability to use low-cost PC networks for this purpose
Aldo Von Wangenheim
added 10 research items
Neste manual, você irá aprender como fazer um pedido de TFD (Tratamento Fora de Domicílio) dentro do STT (Sistema Catarinense de Telemedicina e telessaúde). Para realizar o pedido é necessário seguir alguns passos: primeiro o profissional com o perfil TFD Técnico faz o pedido e encaminha para o profissional com perfil TFD Agendador, para que este olhe o pedido e se tudo estiver correto, encaminhe para o TFD Estadual. Este olhará o pedido e encaminhará para o TFD Regulador que dará um parecer sobre o pedido. Depois o pedido volta, novamente, para o TFD Estadual, que dependendo da avaliação do regulador poderá: autorizar o pedido, negar, pedir o parecer de um avaliador, devolver por falta de documento ou encaminhar para outro regulador.
Neste manual, você vai aprender como realizar um pedido de requisição, fazer os exames de dermatologia e enviá-lo ao Sistema Catarinense de Telemedicina e Telessaúde (STT). A dermatologia é uma especialidade médica que se concentra no diagnóstico, prevenção e tratamento de doenças relacionadas à pele, pelos, mucosas, cabelo e unhas.
Manual de conduta do help desk para atendimento aos usuário da telerradiologia no estado de Santa Catarina.
Aldo Von Wangenheim
added 2 research items
Neste manual você vai aprender como enviar imagens e os dados clínicos do paciente para o Portal do Sistema de Telessaúde e Telemedicina (STT), onde o exame será laudaddo por um médico especialista. Antes de enviar os arquivos do exame de EEG, é necessário realizar a solicitação de EEG no sistema. Esta solicitação pode ser feita tanto pelo médico solicitante do exame, quanto pelo profissional que realaizar o EEG no paciente. A eletroencefalografia (EEG) é um exame que registra e analisa a atividade elétrica cerebral espontânea, captada através da utilização de eletrodos colocados sobre o couro cabeludo do paciente. O EEG é realizado com auxílio de uma pasta condutora que, além de fixar os eletrodos, permite o registro adequado dos sinais elétricos que constituem a atividade elétrica cerebral. O aparelho permite a realização computadorizada de eletroencefalografias, assim como sua monitoração, registro e arquivamento. O programa gera o resultado do exame em um arquivo digital que pode ser enviado para outros profissionais através da internet.
Neste manual, você vai aprender como tirar suas dúvidas sobre determinado caso clínico, através das Teleconsultorias. Elas podem ser realizadas de maneira Assíncrona ou Síncrona e tudo fica registrado, para que você possa consultar em outro momento.
Harley Miguel Wagner
added 2 research items
Neste manual, você irá aprender como laudar um exame de eletrocardiograma dentro do Sistema de Telemedicina e Telessaúde (STT). O eletrocardiograma (ECG) é um exame que registra a atividade elétrica do coração. Ele é usado para avaliar o ritmo do coração e o número de batimentos por minuto, permitindo ao médico identificar arritmias cardíacas (alterações do ritmo do coração) e distúrbios na condução elétrica deste órgão.
Neste manual, você irá aprender como acessar as webconferência dentro do Sistema de Telemedicina e Telessaúde (STT). Elas vão te ajudar a tirar dúvidas relacionadas a saúde.
Aldo Von Wangenheim
added 4 research items
A methodology is presented in order to aid in the surgical planning of abdominal aortic aneurysms. This method addresses image recognition, especially of the aorta and abdominal aneurysms. After the recognition and segmentation of these structures, it is possible to obtain a correct measurement of the same structures, generating more reliable data for manufacturing the required endoprostheses for the treatment of the pathology. With the 3D reconstruction of the anatomical structures, is also possible to make the visualization and analysis of the data more reliable. This work is part of the Cyclops project, which intends to develop intelligent tools for the analysis of medical images, accomplished as a partnership between the Universidade Federal de Santa Catarina (UFSC) and the University of Kaiserslautern, Germany.
Resumo – A maioria dos sistemas de registro clínico eletrônico, atualmente em funcionamento em instituições de saúde brasileiras, não obedece a padrões para o armazenamento ou transferência de informações médicas. A principal conseqüência desta falta de padronização é que o compartilhamento de dados entre instituições se torna difícil. DICOM Structured Report é um padrão internacional para armazenamento e transmissão de laudos médicos. Este artigo relata o desenvolvimento de um editor de laudos, conforme o padrão DICOM Structured Report, composto de duas ferramentas: um editor de modelos de laudo, que permite que o usuário crie modelos de laudo que podem ser usados para guiar a edição de laudos, e um editor de conteúdo de laudo que permite a criação e edição de laudos no padrão.
The image diagnosis area is the biggest medical field in telemedicine, because it does not obligate a direct contact of the patient with the responsible radiologist during the building of the report. The persistent lack of specialists in places distant from urban centers makes telemedicine an important tool for the improvement of healthcare services. In this paper, we present a framework, called CyclopsDistMedDB (Cyclops Distributed Medical Database), for the integration of distributed DICOM medical record databases over wide areas. The system has a central module that is responsible for receiving the clients' requests about patient data (images, waveforms), performing the querying and retrieval of images, patient records, etc. from the specific DICOM databases containing the data requested, and delivering them to the clients. The data communication protocols adopted are DICOM, for retrieval of objects directly from the DICOM data servers, and CORBA (Common Object Request Broker Architecture), for the delivery of DICOM data to client applications.
Aldo Von Wangenheim
added 2 research items
Abstract — for some years the Brazilian radiological community have been missing good and free software with necessary tools for compliance with DICOM (Digital Imaging and Communication in Medicine) standard. Our solution, the Cyclops Medical Station, is a software for physicians, clinics and hospitals, whose need to access DICOM image databanks and make fast and reliable reports with those images. It has tools for image viewing an editing, printer and mailer tools, telemedicine and teleconference, all of those united for easy and fast usability. In this article we present this new software, the solutions for the existing radiology software problems and improvements, based on market solutions.
This paper presents a method for robust three-dimensional representation and visualization of radiological image volumes, such as computer tomographies and magnetic resonances, taking advantage of the use of a well-known data-structure: the octree.
Alexandre Savaris