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.
MRI-Based AI Radiomics Model Offers 'Robust' Prediction of Perineural Invasion in Prostate Cancer
July 26th 2024A model that combines MRI-based deep learning radiomics and clinical factors demonstrated an 84.8 percent ROC AUC and a 92.6 percent precision-recall AUC for predicting perineural invasion in prostate cancer cases.
Breast MRI Study Examines Common Factors with False Negatives and False Positives
July 24th 2024The absence of ipsilateral breast hypervascularity is three times more likely to be associated with false-negative findings on breast MRI and non-mass enhancement lesions have a 4.5-fold likelihood of being linked to false-positive results, according to new research.
Can Polyenergetic Reconstruction Help Resolve Streak Artifacts in Photon Counting CT?
July 22nd 2024New research looking at photon-counting computed tomography (PCCT) demonstrated significantly reduced variation and tracheal air density attenuation with polyenergetic reconstruction in contrast to monoenergetic reconstruction on chest CT.