User-oriented evaluation of a medical image retrieval system for radiologists

Abstract

The iterative character of the evaluation helped to obtain diverse and detailed feedback on all system aspects. Radiologists are quickly familiar with the functionalities but have several comments on desired functionalities. The analysis of the results can potentially assist system refinement for future medical information retrieval systems. Moreover, the methodology presented as well as the discussion on the limitations and challenges of such studies can be useful for user-oriented medical image retrieval evaluation, as user-oriented evaluation of interactive system is still only rarely performed. Such interactive evaluations can be limited in effort if done iteratively and can give many insights for developing better systems.

Shangri–La: A medical case–based retrieval tool

“…The number of images per class in the training and test sets of the ImageCLEFmed 2013 classification task varies from fewer than 10 to several hundred. Therefore, a training set expansion to improve the classification accuracy based on the image modalities (García Seco de Herrera, Markonis, et al, ) was done for the work described here. Finally, a training set with 17,042 images containing manually attached labels is used.…”

“…Both the improved retrieval system combining several techniques and the multimodal query interface constitute the main contributions of this article. The system was refined based on two user tests with a previous system that was performed in the Khresmoi project (Markonis, Baroz, Ruiz de Castaneda, Boyer, & Müller, ; Markonis et al, ). Several adaptations to the interface and the retrieval techniques were done for the prototypes described in this article.…”

A Multimodal Search Engine for Medical Imaging Studies

“…Once issued, the results are shown as a grid of images, all of which can be dragged and dropped for a manual form of relevance feedback. Not only a grid layout of results is more fitting for drag-and-drop operations but it is also known that radiologists often prefer this layout to a list of items [26]. Any further changes in the multimodal query will automatically trigger a new search.…”

Video Retrieval System for Meniscal Surgery to Improve Health Care Services

“…It could be possible via the fabrication of a connexion between information technology and medical sciences. Information technology is capable of providing medical diagnosis, clinical analysis, and treatment planning through a practice known as medical imaging [11,2,12].…”

“…Journal of Sensors and less-experienced surgeons to get appropriate information about surgical methods, procedures, and tools to perform a successful surgery [11,2,12]. These meniscal recordings can additionally be used for the explanation of the patients and their follow-up sessions [9].…”