Hirohiko Kimura MD, PhD, Presenter: Nothing to Disclose

Toyohiko Sakai MD, Abstract Co-Author: Nothing to Disclose

Kenji Kondo, Abstract Co-Author: Employee, Panasonic Corporation

Kazutoyo Takata, Abstract Co-Author: Employee, Panasonic Corporation

Kazuki Kozuka, Abstract Co-Author: Employee, Panasonic Corporation

Masakai Kiyono, Abstract Co-Author: Employee, Panasonic Corporation

Masayuki Inubushi, Abstract Co-Author: Research collaboration, Panasonic Corporation

Mariko Toyooka MD, Abstract Co-Author: Research collaboration, Panasonic Corporation

Daily clinical operations generate a vast amount of medical images, which increase radiologists’ workloads, and reduce their available time for educating medical students, residents, or new radiologists. While medical books and teaching files are critical for self-education, finding specific sources within many pages or files is difficult. Earlier, we proposed an image-retrieval technology based on radiologists’ knowledge, for the accurate location of related images. In this study, we propose a diagnostic imaging education system for lung computed tomography (CT) images, based on similar technology.

The proposed system handles cases from medical books and picture archiving and communication systems (PACS), and combines the benefits of medial books and real digital imaging and communications in medicine (DICOM) cases. In medical books, diagnostic methods for most diseases are described. In contrast, real DICOM cases are more varied in appearance for a given disease, and contain three-dimensional lesion structures constructed of multiple slice images. To operate the system, a user first scans relevant medical book pages by selecting thumbnails of retrieval results, and then finds distinctive traits of some likely diseases. Second, the user specifies a disease from a list of similar cases, and learns the common features of the disease by browsing actual DICOM images.

Currently, the system is linked to our hospital’s radiology department system, and employs a trial database containing 981 images from two medical books, and 1,147 cases from our hospital PACS. Further, the system allows easy access to relevant information from medical books and teaching files for cases met in daily clinical practices.

The current study introduces a diagnostic imaging education system based on image-retrieval technology for medical books and DICOM images. This system could help medical students and radiologists master diagnostic imaging, and encourage more widespread use of these systems.

http://abstract.rsna.org/uploads/2014/14008839/14008839_qnzz.jpg

Kimura, H, Sakai, T, Kondo, K, Takata, K, Kozuka, K, Kiyono, M, Inubushi, M, Toyooka, M, A Diagnostic Imaging Education System for Lung CT Images based on Image-Retrieval Technology for Medical Books and DICOM Images.  Radiological Society of North America 2014 Scientific Assembly and Annual Meeting, - ,Chicago IL. http://archive.rsna.org/2014/14008839.html