An online database-driven image library and teaching file program allows healthcare professionals to share an organized, cataloged, and searchable database of captioned and annotated medical images.The system, called
An online database-driven image library and teaching file program allows healthcare professionals to share an organized, cataloged, and searchable database of captioned and annotated medical images.
The system, called MedPix, was developed by the departments of radiology and medical informatics of the U.S. Uniformed Services University.
"The vision of MedPix was to take the teaching file out of the closet and create a collaborative tool for organizing and displaying teaching file cases between geographically separated institutions using the existing Internet infrastructure," said Dr. James G. Smirniotopoulos, chair of radiology and nuclear medicine at Uniformed Services University of the Health Sciences (USUHS) in Bethesda, MD.
MedPix works as a Web-enabled, cross-platform database, integrating images and textual information. It is aimed at a target audience of radiologists, radiology residents, practicing clinicians, medical students, graduate nursing students, and other postgraduate trainees. No special software other than a standard Web browser is required.
Material in the MedPix database -- organized by disease category, disease location (organ system), and patient profile -- can be searched through multiple internal text search engines. Users can browse the image database through a slide-sorter that displays selections as a collection of thumbnails.
Smirniotopoulos cited four goals of the program:
The original database design of MedPix, developed jointly by Smirniotopoulos and Henry Irvine, a USUHS medical student, evolved from a hierarchical note-taking program written in Visual Basic in 1995.
MedPix development has progressed through several stages over the past two years. The initial database-driven Web site was written as a text-only program under Linux. The image uploading and downloading facilities were added next. The Teaching File component was launched in November 2000.
The site already features a Radiology Case of the Week, and Smirniotopoulos has plans to add a Pathology Case of the Week soon.
Can Ultrasound-Based Radiomics Enhance Differentiation of HER2 Breast Cancer?
March 11th 2025Multicenter research revealed that a combined model of clinical factors and ultrasound-based radiomics exhibited greater than a 23 percent higher per patient-level accuracy rate for identifying HER2 breast cancer than a clinical model.