Abstract
Medical imaging is essential nowadays throughout medical education, research, and care. Accordingly, international efforts have been made to set large-scale image repositories for these purposes. Yet, to date, browsing of large-scale medical image repositories has been troublesome, time-consuming, and generally limited by text search engines. A paradigm shift, by means of a query-by-example search engine, would alleviate these constraints and beneficially impact several practical demands throughout the medical field. The current project aims to address this gap in medical imaging consumption by developing a content-based image retrieval (CBIR) system, which combines two image processing architectures based on deep learning. Furthermore, a first-of-its-kind intelligent visual browser was designed that interactively displays a set of imaging examinations with similar visual content on a similarity map, making it possible to search for and efficiently navigate through a large-scale medical imaging repository, even if it has been set with incomplete and curated metadata. Users may, likewise, provide text keywords, in which case the system performs a content- and metadata-based search. The system was fashioned with an anonymizer service and designed to be fully interoperable according to international standards, to stimulate its integration within electronic healthcare systems and its adoption for medical education, research and care. Professionals of the healthcare sector, by means of a self-administered questionnaire, underscored that this CBIR system and intelligent interactive visual browser would be highly useful for these purposes. Further studies are warranted to complete a comprehensive assessment of the performance of the system through case description and protocolized evaluations by medical imaging specialists.
Highlights
Nowadays, imaging plays a central role in medicine
We found that most respondents from the healthcare sector foresee that a content-based image retrieval (CBIR) system would be useful for medical education (57/67 = 85%), research (51/67 = 76%), and clinical care (57/67 = 85%), while it would be less useful for innovation and technological development (25/67 = 37%), personal study (2/67 = 0.3%), and management statistics (1/67 = 0.1%)
It is noteworthy that single medical imaging examinations may comprise thousands of images, meaning that massive amounts of images have to be stored in medical image repositories, which challenges the efficiency of CBIR systems for medical purposes and clinical settings [22]
Summary
Large amounts of imaging data are constantly generated in daily clinical practice, leading to continuously expanding archives, and ever progressive efforts are being made across the world to build large-scale medical imaging repositories [1,2]. This trend is in line with the increasing medical image consumption needs, which have been studied and categorized into four groups: patient care-related, research-related, education-related, and other [3]. There is an enormous need for efficiently archiving, organizing, managing, and mining massive medical image datasets on the basis of their visual content (e.g., shape, morphology, structure), and it may be expected that this demand will only become more substantial in the foreseeable future
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
