Annotation and Image Markup: Accessing and Interoperating with the Semantic Content in Medical Imaging

Rubin, Daniel L.; Mongkolwat, Pattanasak; Kleper, Vladimir; Supekar, Kaustubh; Channin, David S.

doi:10.1109/mis.2009.3

Cited by 33 publications

(18 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This plug-in also provides a structured data entry template that enables users to describe the features of lesions according to 12 categories comprising 161 possible descriptors ( Table ) selected from the RadLex controlled terminology ( 8 ) and augmented for this study with additional terms after consultation with an abdominal imaging radiologist. Once all entries have been made and validated against the controlled terminology of the annotation device, the annotations are saved in a fi le compliant with the Annotation and Image Mark-up standard ( 19,20 ), established by the National Cancer Institute's Cancer Bioinformatics Grid.…”

Section: Technical Developments: Automated Retrieval Of Ct Imagesmentioning

confidence: 99%

Automated Retrieval of CT Images of Liver Lesions on the Basis of Image Similarity: Method and Preliminary Results

Napel¹,

Beaulieu²,

Rodriguez³

et al. 2010

Radiology

Self Cite

View full text Add to dashboard Cite

Purpose:To develop a system to facilitate the retrieval of radiologic images that contain similar-appearing lesions and to perform a preliminary evaluation of this system with a database of computed tomographic (CT) images of the liver and an external standard of image similarity. Materials and Methods:Institutional review board approval was obtained for retrospective analysis of deidentifi ed patient images. Thereafter, 30 portal venous phase CT images of the liver exhibiting one of three types of liver lesions (13 cysts, seven hemangiomas, 10 metastases) were selected. A radiologist used a controlled lexicon and a tool developed for complete and standardized description of lesions to identify and annotate each lesion with semantic features. In addition, this software automatically computed image features on the basis of image texture and boundary sharpness. Semantic and computer-generated features were weighted and combined into a feature vector representing each image. An independent reference standard was created for pairwise image similarity. This was used in a leaveone-out cross-validation to train weights that optimized the rankings of images in the database in terms of similarity to query images. Performance was evaluated by using precisionrecall curves and normalized discounted cumulative gain (NDCG), a common measure for the usefulness of information retrieval. Results:When used individually, groups of semantic, texture, and boundary features resulted in various levels of performance in retrieving relevant lesions. However, combining all features produced the best overall results. Mean precision was greater than 90% at all values of recall, and mean, best, and worst case retrieval accuracy was greater than 95%, 100%, and greater than 78%, respectively, with NDCG. Conclusion:Preliminary assessment of this approach shows excellent retrieval results for three types of liver lesions visible on portal venous CT images, warranting continued development and validation in a larger and more comprehensive database.q RSNA, 2010

show abstract

Section: Technical Developments: Automated Retrieval Of Ct Imagesmentioning

confidence: 99%

Automated Retrieval of CT Images of Liver Lesions on the Basis of Image Similarity: Method and Preliminary Results

Napel¹,

Beaulieu²,

Rodriguez³

et al. 2010

Radiology

Self Cite

View full text Add to dashboard Cite

show abstract

“…The Annotation and Image Markup (AIM) standard [66] is developed for storing descriptive and quantitative clinical image markup data in DICOM-SR, HL7 CDA, or XML formats to facilitate the communication of image annotations and markup data in a standard manner. However, at this stage, such standard is mainly limited to 2D/ 3D images, and no state-of-the-art solution applies to patient-specific 3D model.…”

Section: Key Challenges Towards a Comprehensive Integrationmentioning

confidence: 99%

Combination of visual and symbolic knowledge: A survey in anatomy

Banerjee

Patan

Spagnuolo

2017

Computers in Biology and Medicine

View full text Add to dashboard Cite

“…A criação de metadados é uma das principais técnicas usadas para anotar documentos. Os metadados podem ser atribuídos a uma ampla variedade de documentos, pode ser expressa em diversas linguagens e vocabulários (CORCHO, 2006), e pode ser feita de forma manual, automática ou semiautomática (UREN et al, 2006).…”

Section: Anotação Semântica De Imagensunclassified

“…Por outro lado, os metadados com conteúdo descritivo podem ser proporcionados a dois níveis de especificidade: i) conteúdo descritivo associado à imagem completa (SCHREIBER et al, 2001) e ii) segmentação da imagem com vinculação do conteúdo descritivo em cada região da imagem (HSU et al, 2009;RUBIN et al, 2009).…”

Section: Anotação Semântica De Imagensunclassified

Um modelo para a visualização do conhecimento baseado em arquétipos visuais

2012

View full text Add to dashboard Cite

RESUMO.Neste artigo apresenta-se um modelo que visa facilitar a visualização do conhecimento armazenado em repositórios digitais usando arquétipos visuais. Os arquétipos são estruturas que contêm representações visuais do mundo real que a priori são conhecidas pelo grupo-alvo, e possuem estruturas semânticas que permitem identificar os conceitos do domínio representados em cada região. O modelo proposto apoia-se no framework para visualização do conhecimento proposto por Burkhard e descreve as interações dos usuários com os arquétipos visuais. O usuário por meio dos arquétipos pode recuperar e visualizar o conhecimento relacionado aos conceitos representados nas imagens dos arquétipos. Um protótipo foi desenvolvido para demonstrar a viabilidade do modelo usando arquétipos no domínio da anatomia, a Foundational Model of Anatomy e a Unified Medical Language System como conhecimento do domínio e o banco de dados da Scientific Electronic Library Online como repositório de documento. O uso das representações visuais nos arquétipos facilita a divulgação do conhecimento já que ao fazer parte da visão do mundo dos usuários, podem facilmente ser associadas a conhecimentos prévios. As representações visuais são processadas rapidamente no cérebro requerendo menos esforço que o processamento de informação textual.Palavras-chave: visualização do conhecimento, recuperação do conhecimento, anotação semântica, ontologia. A model for knowledge visualization based on visual archetypesABSTRACT. This paper presents a model that aims to facilitate the visualization of the knowledge stored in digital repositories using visual archetypes. Archetypes are structures that contain visual representations of the real world that are known a priori by the target group, and which have semantic structures for identifying the entities of the domain represented in each region. The proposed model is supported by the framework for knowledge visualization proposed by Burkhard and describes the users' interactions with visual archetypes. The user through the archetypes can retrieve and view the knowledge related to the entities represented in the archetypes' images. A prototype was developed to demonstrate the feasibility of the model using archetypes in the biomedical field, the Foundational Model of Anatomy and the Unified Medical Language System as domain knowledge and the Scientific Electronic Library Online database as a document repository. The use of visual representations in archetypes facilitates the dissemination of knowledge, because these are part of the world view of users and can easily be related with prior knowledge. Visual representations are processed quickly in the brain and require less effort than the processing of textual information.

show abstract

Annotation and Image Markup: Accessing and Interoperating with the Semantic Content in Medical Imaging

Cited by 33 publications

References 5 publications

Automated Retrieval of CT Images of Liver Lesions on the Basis of Image Similarity: Method and Preliminary Results

Automated Retrieval of CT Images of Liver Lesions on the Basis of Image Similarity: Method and Preliminary Results

Combination of visual and symbolic knowledge: A survey in anatomy

Um modelo para a visualização do conhecimento baseado em arquétipos visuais

Contact Info

Product

Resources

About