Suzan Uskudarli

General Overview of ImageCLEF at the CLEF 2015 Labs

This paper presents an overview of the ImageCLEF 2015 evaluation campaign, an event that was organized as part of the CLEF labs 2015. ImageCLEF is an ongoing initiative that promotes the evaluation of technologies for annotation, indexing and retrieval for providing information access to databases of images in various usage scenarios and domains. In 2015, the 13th edition of ImageCLEF, four main tasks were proposed: 1 automatic concept annotation, localization and sentence description generation for general images; 2 identification, multi-label classification and separation of compound figures from biomedical literature; 3 clustering of x-rays from all over the body; and 4 prediction of missing radiological annotations in reports of liver CT images. The x-ray task was the only fully novel task this year, although the other three tasks introduced modifications to keep up relevancy of the proposed challenges. The participation was considerably positive in this edition of the lab, receiving almost twice the number of submitted working notes papers as compared to previous years.

ImageCLEF 2014: Overview and Analysis of the Results

This paper presents an overview of the ImageCLEF 2014 evaluation lab. Since its first edition in 2003, ImageCLEF has become one of the key initiatives promoting the benchmark evaluation of algorithms for the annotation and retrieval of images in various domains, such as public and personal images, to data acquired by mobile robot platforms and medical archives. Over the years, by providing new data collections and challenging tasks to the community of interest, the ImageCLEF lab has achieved an unique position in the image annotation and retrieval research landscape. The 2014 edition consists of four tasks: domain adaptation, scalable concept image annotation, liver CT image annotation and robot vision. This paper describes the tasks and the 2014 competition, giving a unifying perspective of the present activities of the lab while discussing future challenges and opportunities.

Generating visual editors for formally specified languages

We discuss the generation of structured visual editors for formally specified languages. We use the term structured visual editor to refer to a structure-oriented editor which provides language specific behavior and supports the interactive construction of programs. This paper describes how such a visual editor can be generated from a formal language specification including the languages visual syntax. A simple visual expression editor is presented in order to demonstrate our approach. Our prototype implementation is discussed at the end of the paper.<<ETX>>We discuss the generation of structured visual editors for formally speciied languages. We use the term structured visual editor to refer to a structure{ oriented editor which provides language speciic behavior and supports the interactive construction of programs. This paper describes how such a visual editor can be generated from a formal language speciication including the languages visual syntax. A simple visual expression editor is presented in order to demonstrate our approach. Our prototype implementation is discussed at the end of the paper.

Semantic Description of Liver CT Images: An Ontological Approach

Radiologists inspect CT scans and record their observations in reports to communicate with physicians. These reports may suffer from ambiguous language and inconsistencies resulting from subjective reporting styles, which present challenges in interpretation. Standardization efforts, such as the lexicon RadLex for radiology terms, aim to address this issue by developing standard vocabularies. While such vocabularies handle consistent annotation, they fall short in sufficiently processing reports for intelligent applications. To support such applications, the semantics of the concepts as well as their relationships must be modeled, for which, ontologies are effective. They enable the software to make inferences beyond what is present in the reports. This paper presents the open-source ontology ONLIRA (Ontology of the Liver for Radiology), which is developed to support such intelligent applications, such as identifying and ranking similar liver patient cases. ONLIRA is introduced in terms of its concepts, properties, and relations. Examples of real liver patient cases are provided for illustration purposes. The ontology is evaluated in terms of its ability to express real liver patient cases and address semantic queries.

Semantic TagPrint - Tagging and Indexing Content for Semantic Search and Content Management

Existing search and content management technology is facing a challenge of locating desired content with the exponentially growing volume of documents. An approach for mitigating this issue is to make use of user-generated tags. However, the improvements are limited because tags are (1) free from context and form, (2) user generated, (3) used for purposes other than description, and (4) often ambiguous. Since tagging is a voluntary action, some documents are not tagged at all. Furthermore, the interpretation of the tags associated with tagged documents also remains a challenge. To overcome these challenges, semantic web resources and technologies can be utilized to automatically generate semantic tags. Semantic tags not only reflect document content more accurately, they also enable better search results. Ontology coverage, ontology mapping and weighting significant ontological entities within a context are key challenges in semantic tagging systems. To address these challenges, this paper presents a semantic tagging system - Semantic TagPrint - to map a text document to semantic tags defined as entities in an ontology. Semantic TagPrint uses a linear time lexical chaining Word Sense Disambiguation (WSD) algorithm for real time concept mapping. In addition, it utilizes statistical metrics and ontological features of the ontology for weighting and recommending the semantic tags. A comparative evaluation shows that our mapping algorithm is fairly accurate and our tag recommendation algorithm performs better than other systems and algorithms.

Identifying Topics in Microblogs Using Wikipedia.

Twitter is an extremely high volume platform for user generated contributions regarding any topic. The wealth of content created at real-time in massive quantities calls for automated approaches to identify the topics of the contributions. Such topics can be utilized in numerous ways, such as public opinion mining, marketing, entertainment, and disaster management. Towards this end, approaches to relate single or partial posts to knowledge base items have been proposed. However, in microblogging systems like Twitter, topics emerge from the culmination of a large number of contributions. Therefore, identifying topics based on collections of posts, where individual posts contribute to some aspect of the greater topic is necessary. Models, such as Latent Dirichlet Allocation (LDA), propose algorithms for relating collections of posts to sets of keywords that represent underlying topics. In these approaches, figuring out what the specific topic(s) the keyword sets represent remains as a separate task. Another issue in topic detection is the scope, which is often limited to specific domain, such as health. This work proposes an approach for identifying domain-independent specific topics related to sets of posts. In this approach, individual posts are processed and then aggregated to identify key tokens, which are then mapped to specific topics. Wikipedia article titles are selected to represent topics, since they are up to date, user-generated, sophisticated articles that span topics of human interest. This paper describes the proposed approach, a prototype implementation, and a case study based on data gathered during the heavily contributed periods corresponding to the four US election debates in 2012. The manually evaluated results (0.96 precision) and other observations from the study are discussed in detail.

Clinical experience sharing by similar case retrieval

Clinical experience sharing (CES) is a useful concept for both medical treatment and medical education purposes. One way of implementing CES is through the use of content based case retrieval (CBCR), where database of medical cases is browsed for case instances that are similar to the input query case. In this study, we introduce a new project called case retrieval in radiology (CaReRa), which aims at implementing CES for liver cases. We particularly focus on 3D liver images acquired by computed tomography (CT) and lay the foundations of a conceptual system outputting a ranked list of results for a given query case, formulated in this work as a liver lesion. A list of CT image features serves as computer generated descriptors together with user expressed annotations collected using a novel ontology of liver for radiology (ONLIRA). A two stage approach is proposed to utilize these two types of descriptors in cascade, namely semantic framing and similarity ranking. Initial retrieval performance results confirm the importance of ontology based descriptors, while also highlights the foci of future work needed to overcome the weaknesses.

Towards an ontology-driven clinical experience sharing ecosystem: Demonstration with liver cases

Abstract Past medical cases, hence clinical experience, are invaluable resources in supporting clinical practice, research, and education. Medical professionals need to be able to exchange information about patient cases and explore them from subjective perspectives. This requires a systematic and flexible methodology to case representation for supporting the exchange of processable patient information. We present an ontology based approach to modeling patient cases and use patients with liver disease conditions as an example. To this end a novel ontology, l i co , that utilizes well known medical standards is proposed to represent liver patient cases. The utility of the proposed approach is demonstrated with semantic queries and reasoning using data collected from real patients. The preliminary results are promising in regards to the potentials of ontology based medical case representation for building case-based search and retrieval systems, paving the way towards a Clinical Experience Sharing platform for comparative diagnosis, research, and education.

DRENAJ: Distributed social media data collection system

Social media has become important for signal processing research due to the interesting content consisting of status updates and relations which give clues about social ties. Thus, it is important to lower the barrier to access this kind of data for researchers of natural language processing, social graph analysis and machine learning. However, accessing this data can usually be tricky and may pose difficulties. This work describes a distributed system for collecting, storing and serving social media data using the computing resources shared by its own volunteer users. We used the system extensively and saw promising results in terms of time and space efficiency.