Radiology Teaching Files: an Assessment of Their Role and Desired Features Based on a National Survey.

A radiology teaching file (TF) is a system containing a collection of cases with teaching value. Given the wide variety of TF solutions available, we conducted a national survey to better understand the need for TFs, TF features desired by users and their current implementation. A 28-question survey was created which explored TF implementation, utilization, and preferences among respondents. The survey was emailed to residents and faculty throughout the USA, with a request for program coordinators to forward the survey to their departments. The survey was completed by 396 respondents from 115 different institutions. These respondents included 60% residents, 21% attendings (non-program directors), 12% program directors, 5% fellows, and 1% medical students. TFs were assigned to one of three categories: personal TFs, shared in-house TFs, and public TFs. Seventy-six percent of respondents kept a personal TF using a variety of media, and 67% used a shared in-house TF. Of the public TFs used, the most popular were those requiring paid subscriptions. The features respondents valued most provided efficient querying of cases, simulated basic PACS functionality, enabled self-directed learning, and facilitated case submissions. There is a trend toward utilizing electronic media for TFs. The media utilized should be understood and reviewed to ensure PHI is properly secured. Contemporary users demand a high degree of functionality from TF solutions, and use both in-house and commercial products to meet their needs.

A curated mammography data set for use in computer-aided detection and diagnosis research.

Published research results are difficult to replicate due to the lack of a standard evaluation data set in the area of decision support systems in mammography; most computer-aided diagnosis (CADx) and detection (CADe) algorithms for breast cancer in mammography are evaluated on private data sets or on unspecified subsets of public databases. This causes an inability to directly compare the performance of methods or to replicate prior results. We seek to resolve this substantial challenge by releasing an updated and standardized version of the Digital Database for Screening Mammography (DDSM) for evaluation of future CADx and CADe systems (sometimes referred to generally as CAD) research in mammography. Our data set, the CBIS-DDSM (Curated Breast Imaging Subset of DDSM), includes decompressed images, data selection and curation by trained mammographers, updated mass segmentation and bounding boxes, and pathologic diagnosis for training data, formatted similarly to modern computer vision data sets. The data set contains 753 calcification cases and 891 mass cases, providing a data-set size capable of analyzing decision support systems in mammography.