Chin-Hsiang Feng BS, Presenter: Nothing to Disclose

Samir Abboud MD, Abstract Co-Author: Nothing to Disclose

Jessica Ann Galandak MD, Abstract Co-Author: Nothing to Disclose

Lyn Wan Ho MD, Abstract Co-Author: Nothing to Disclose

Scott Rotenberg MD, Abstract Co-Author: Nothing to Disclose

Eliot L. Siegel MD, Abstract Co-Author: Research Grant, General Electric Company Speakers Bureau, Siemens AG Board of Directors, Carestream Health, Inc Research Grant, XYBIX Systems, Inc Research Grant, Steelcase, Inc Research Grant, Anthro Corp Research Grant, RedRick Technologies Inc Research Grant, Evolved Technologies Corporation Research Grant, Barco nv Research Grant, Intel Corporation Research Grant, Dell Inc Research Grant, Herman Miller, Inc Research Grant, Virtual Radiology Research Grant, Anatomical Travelogue, Inc Medical Advisory Board, Fovia, Inc Medical Advisory Board, Toshiba Corporation Medical Advisory Board, McKesson Corporation Medical Advisory Board, Carestream Health, Inc Medical Advisory Board, Bayer AG Research, TeraRecon, Inc Medical Advisory Board, Bracco Group Researcher, Bracco Group Medical Advisory Board, Merge Healthcare Incorporated Medical Advisory Board, Microsoft Corporation Researcher, Microsoft Corporation

Cristina Irene Caterina Campassi MD, Abstract Co-Author: Nothing to Disclose

The iPad has similar performance to a conventional workstation for classifying breast composition across trained breast imagers. Initial data suggests the iPad may have similar performance for identifying positive screenings. Further studies are needed to analyze the iPad’s lesion detection for features such as masses, calcifications, and asymmetries in order to clarify the iPad’s utility in mammography.

Recent studies have evaluated mobile displays for conventional radiography tasks such as tuberculosis screening. This study investigated the use of the iPad3 display for ultra high resolution tasks such as mammography. 

We compared the iPad3 3.1 megapixel display using the MobileMIM app with an AGFA IMPAX workstation with 5MP monitors for the evaluation of two parameters: breast composition and positive screening mammograms. Positive screening mammograms were defined as abnormal cases (BIRADS 0). Negative screening mammograms were defined as negative (BIRADS 1) or benign (BIRADS 2) cases. We selected 60 digital screening mammograms with a biopsy diagnosis or a minimum of 2 years of follow-up to represent all 4 groups of breast composition. The dataset was enhanced, increasing the positive cases to 25 %. Of these cases, 32 were interpreted with and 28 without a prior screening mammogram. The dataset was anonymized and read in randomized order first on the iPad and then on the workstation with a 2 week interval between sessions. Four radiologists, 3 attendings with varying expertise in breast imaging and 1 fellow in training, interpreted the cases blinded to outcome. Breast composition, lesion type and location, and assessment category were recorded for each case according to BIRADS standards. For each reader, the interpretation on the workstation served as the gold standard, and the performance of the two displays was evaluated by kappa statistics.

For breast composition, the iPad and 5MP comparison yielded a substantial kappa value ranging from 0.63 to 0.78 in all readers. For the positive screening assessment, the iPad and 5MP comparison yielded a fair kappa value of 0.39 for the fellow and a moderate to substantial kappa value of 0.56 to 0.72 for the attendings.

Feng, C, Abboud, S, Galandak, J, Ho, L, Rotenberg, S, Siegel, E, Campassi, C, Comparison between iPad3 and Conventional Workstation for Assessment of Breast Composition and Abnormal Cases (BIRADS 0) in Screening Mammography .  Radiological Society of North America 2014 Scientific Assembly and Annual Meeting, - ,Chicago IL. http://archive.rsna.org/2014/14006834.html