My visualization tool for spatial relations of landmarks in volume data sets can now display multiple sets of landmarks within the same window. The sceenshot below shows two sets of landmarks – one in green and the other in red. Most of the colored bubbles relate to the vertebrae of the spine. For each of the vertebrae we illustrate top, bottom, front and backmost points.
click on the image to enlarge
KafkaRCP is the GUI framework behind DynaQ, developed by one of my colleagues at DFKI. With his help I moved the old, multiwindowed GUI of the MEDICO demonstrator into a single application with a common interface.
new KafkaRCP-based GUI
The screenshot also shows the timeline feature (at the bottom) which uses extracted DICOM metadata to create a visual timeline of the patients history. More on that in a forthcoming ESWC paper.
Patrick Ernst, one of our students here at DFKI has implemented a DICOM Metadata Extractor for the Aperture framework. DICOM is the most widely used standard for medical image storage and interchange world wide. Based on the MEDICO DICOM Ontology it can triplify the headers of arbitrary DICOM images.
We have set up a corpus of medical images of about 1.6 GB. Since non-anonymized medical images are a rare good, Leo and I had to work hard to make radiologists take images from us.
We adapted Longwell, a faceted browsing application by MIT, to read RDF data directly from a Sesame triple store and deployed it into a Tomcat server. What came out is a web application demonstrating the features of faceted browsing for DICOM metadata.
click to go to web application
The application can be found here: http://www.dfki.uni-kl.de/medico-longwell-2.5.5/
We are developing an OWL ontology for the MEDICO project. General design considerations and the different subcomponents are described in a paper. Meanwhile, I have set up an AJAX application which allows to browse the ontology online.
click on the screenshot to go to the ontology browser
Acknowledgements for the application go to David Decraene from OntologyOnline.org who has coded the whole thing.
One aim of MEDICO – among several others – is to integrate existing distributed and heterogenous medical data sources. This screencast shows the results of our integration of
For 3. we
For the English synonyms in the FMA this procedure took more than one day resulting in mappings for 84,685 out of 98,320 classes. We did the same procedure for the German synonyms resulting in mappings for 333 out of 357 synonyms.
click on the image to start the screencast
By clicking on an annotation a browser pops up which shows the respecive FMA concept definition page. A small gray icon after a concept name indicates that there is a Wikipedia URL available for this concept. Clicking on this icon brings the user to the respective Wikipedia web page.
I have updated the semantic medical image annotation tool to integrate a couple of new features:
click image to view screencast
I’ve produced a couple of screencasts of the current version of DFKI’s demonstrator for manual semantic annotation of medical images in DICOM format. Annotations are stored in RDF format.
The tool is divided into two main components: An annotation and a retrieval interface.
Annotation Interface #1
Please click on the image to open the screencast in a new window.
The video shows a recent version of the annotation frontend. The loaded DICOM image (currently only 2d is supported) is displayed using ImageJ. There is a schematic drawing of a human which is used to show the body region of the current image.
Below you find the Contrast Windowing component which uses radiodensity annotations for certain tissue types in the MEDICO Ontology to adjust the level and window of the currently loaded image.
The “Toolbar” component is used to choose from a set of different geometric primitives to draw regions of interest (ROIs) in the image. These ROIs can be moved and resized. Currently, we only support rectangles and ovals. We plan to support arbitrary polygons next. The coordinates and parameters of these geometries are saved semantically in the triple store.
After placing a new ROI on the image, it can be added to the list in the ROIManager component and annotated semantically.
Anatomy and disease dimension are annotated separately. The vocabulary is from RadLex (latest version: the FMA fragment of the current body region) and the ICD9. In a newer version of the demonstrator, we also have multi-language support using the synonyms in the FMA (English, German, Spanish, Filipino (!),…). Again, there is search-as-you-type for the comboboxes.
Annotation Interface #2
Please click on the image to open the screencast in a new window.
It shows the annotation of a second image but with different annotations.
Semantic Search Interface
Please click on the image to open the screencast in a new window.
demonstrates the semantic search. None of the images before has been annotated with “thorax” but they are still found and ranked by their “semantic distance”. By clicking on the anatomical annotation “lung zone” of the first hit a browser pops up and displays the respective RadLex page. “Lung zone” is a subclass of “lung” which itself is a subclass of “thorax”. This explains, how it could be found by searching for “thorax”
It is also possible to search for the definition of the ICD9 term by clicking on the respective disease annotation.
The annotations can also be visualized using Prefuse. By clicking on the “Expand” button, the next level in the ontology hierarchy around a concept is expanded and displayed. This is quite handy for an exploration of the ontology.
Finally, by clicking on the image link, the image can be opened.
. Wir wünschen Euch noch...
Grüße aus dem...
Hudson Builds