Medical information for Radiologists
The objectives of this use case were:
- better understanding of the current image (2D, 3D, 4D, multimodality) search behavior of clinicians and particularly radiologists;
- limiting the information overload of radiologists and other clinicians caused by an increasing number of images and an increasing complexity of radiological protocols by explaining the data viewed in a better way, including the use of past cases and recent publications;
- indexing databases of medical images of a realistic size and structure through the PACS dumps of two hospitals;
- understanding problems of real life patient data in terms of data quality, anonymization, and pre-treatment;
- performing a large scale user test with radiologists in Vienna and Geneva on visual data search from the PACS and external data sources using the developed prototypes;
- data reduction when storing 3D and 4D datasets and their visual features through concentrating features on regions different from healthy models.
Requirements
Results of surveys and analyses on the use of search for medical information by radiologists are in Deliverable 9.1.
Prototype
Khresmoi Radiology: A search engine with advanced image search capabilities for radiologists. Watch the videos showing the prototypes for 3D image search and 2D image search. It is described in Deliverable 2.6.
Evaluation
The results of the first round of user-centred evaluation of the radiology prototype are in Deliverable 10.2.