Alexandra La Cruz

An automatic method for the enrichment of DICOM metadata using biomedical ontologies

This work is a novel contribution for enriching medical images using semantic annotations with a strategy for unifying different ontologies and instances of DICOM medical files. We present the L-MOM library (Library for Mapping of Ontological Metadata) as a tool for making an automatic mapping between instances of DICOM medical files and different medical ontologies (e.g., FMA, RadLex, MeSH). The main contributions are: i) the domain independent L-MOM library which is able to integrate DICOM metadata with ontologies from different domains; ii) a strategy to automatically annotate DICOM data with universally accepted medical ontologies, and provide values of similarity between ontologies and DICOM metadata; and iii) a framework to traverse ontological concepts that characterized clinical studies of patients registered in the framework catalog.

RDF-ization of DICOM medical images towards linked health data cloud

This paper proposes a novel strategy for semantifying DICOM medical images (RDF-ization) automatically. We define an architecture that involves processes for extracting, anonymizing, and serializing metadata comprised in DICOM medical images into RDF/XML. These processes allow for semantically enriching and sharing the metadata of DICOM medical files through the Linked Health Data cloud. Thereby providing enhanced query capabilities with respect to the ones offered by current PACS environments, while exploiting all advantages of the Linking Open Data (LOD) cloud and SemanticWeb technologies.

SemVisM: semantic visualizer for medical image

SemVisM is a toolbox that combines medical informatics and computer graphics tools for reducing the semantic gap between low-level features and high-level semantic concepts/terms in the images. This paper presents a novel strategy for visualizing medical data annotated semantically, combining rendering techniques, and segmentation algorithms. SemVisM comprises two main components: i) AMORE (A Modest vOlume REgister) to handle input data (RAW, DAT or DICOM) and to initially annotate the images using terms defined on medical ontologies (e.g., MesH, FMA or RadLex), and ii) VOLPROB (VOlume PRObability Builder) for generating the annotated volumetric data containing the classified voxels that belong to a particular tissue. SemVisM is built on top of the semantic visualizer ANISE.1

Level set algorithms comparison for multi-slice CT left ventricle segmentation

The comparison of several Level Set algorithms is performed with respect to 2D left ventricle segmentation in Multi-Slice CT images. Five algorithms are compared by calculating the Dice coefficient between the resulting segmentation contour and a reference contour traced by a cardiologist. The algorithms are also tested on images contaminated with Gaussian noise for several values of PSNR. Additionally an algorithm for providing the initialization shape is proposed. This algorithm is based on a combination of mathematical morphology tools with watershed and region growing algorithms. Results on the set of test images are promising and suggest the extension to 3{D MSCT database segmentation.

Grid platform for medical federated queries supporting semantic and visual annotations

Grid computing has been successfully applied on teleradiology, leading to the creation of important platforms such as MEDICUS, VirtualPACS and mantisGRID, among others. These platforms are studied on the basis of their available documentation in order to compare and discuss differences and similarities, advantages and disadvantages between them. Then, a grid platform architecture is proposed, based on the best features of the surveyed platforms with an additional emphasis on general federated queries involving CBIR (Content-Based Image Retrieval) and Semantic Annotations.

WebMedSA: a web-based framework for segmenting and annotating medical images using biomedical ontologies

Advances in medical imaging have fostered medical diagnosis based on digital images. Consequently, the number of studies by medical images diagnosis increases, thus, collaborative work and tele-radiology systems are required to effectively scale up to this diagnosis trend. We tackle the problem of the collaborative access of medical images, and present WebMedSA, a framework to manage large datasets of medical images. WebMedSA relies on a PACS and supports the ontological annotation, as well as segmentation and visualization of the images based on their semantic description. Ontological annotations can be performed directly on the volumetric image or at different image planes (e.g., axial, coronal, or sagittal); furthermore, annotations can be complemented after applying a segmentation technique. WebMedSA is based on three main steps: (1) RDF-ization process for extracting, anonymizing, and serializing metadata comprised in DICOM medical images into RDF/XML; (2) Integration of different biomedical ontologies (using L-MOM library), making this approach ontology independent; and (3) segmentation and visualization of annotated data which is further used to generate new annotations according to expert knowledge, and validation. Initial user evaluations suggest that WebMedSA facilitates the exchange of knowledge between radiologists, and provides the basis for collaborative work among them.

Mobile teleradiology system suitable for m-health services supporting content and semantic based image retrieval on a grid infrastructure

Teleradiology systems tackle the problem of transferring radiological images between medical image workstations for facilitating different medical activities, e.g., diagnosis, treatment and follow up a patient, medical training, or consulting second opinion. Nowadays, m-Health (aka mobile health) is becoming popular because of high quality of mobile displays, although remains a work in progress. In this paper a mobile teleradiology system is reported, which main contribution is the development of a platform: (1) supported by a Grid infrastructure, (2) using biomedical ontologies for adding semantic annotations on medical images, and (3) supporting semantic and content-based image retrieval. Images are located physically in different repositories like; hospitals and diagnostic imaging centers. All these features make the system ubiquitous, portable, and suitable for m-Health services.

Video and imaging gastroenterological medical equipment oriented to telemedicine

This paper describes a system for management of clinical information in gastroenterology. The system consists of two blocks (hardware and software), both developed during the investigation. The hardware interface is connected to endoscopy equipment for video and image acquisition. Then, the patient electronic health record (EHR) is created using a software designed for including the relevant images and video sequences selected by the medical staff. The patient EHR is stored locally as well as in a remote server where authorized users can review and eventually edit the information within a telemedicine protocol.