Mammographic density: Comparison of visual assessment with fully automatic calculation on a multivendor dataset
2016 (English)In: European Radiology, ISSN 0938-7994, E-ISSN 1432-1084, Vol. 26, no 1, 175-183 p.Article in journal (Refereed) PublishedText
To compare breast density (BD) assessment provided by an automated BD evaluator (ABDE) with that provided by a panel of experienced breast radiologists, on a multivendor dataset. Twenty-one radiologists assessed 613 screening/diagnostic digital mammograms from nine centers and six different vendors, using the BI-RADS a, b, c, and d density classification. The same mammograms were also evaluated by an ABDE providing the ratio between fibroglandular and total breast area on a continuous scale and, automatically, the BI-RADS score. A panel majority report (PMR) was used as reference standard. Agreement (kappa) and accuracy (proportion of cases correctly classified) were calculated for binary (BI-RADS a-b versus c-d) and 4-class classification. While the agreement of individual radiologists with the PMR ranged from kappa = 0.483 to kappa = 0.885, the ABDE correctly classified 563/613 mammograms (92 %). A substantial agreement for binary classification was found for individual reader pairs (kappa = 0.620, standard deviation [SD] = 0.140), individual versus PMR (kappa = 0.736, SD = 0.117), and individual versus ABDE (kappa = 0.674, SD = 0.095). Agreement between ABDE and PMR was almost perfect (kappa = 0.831). The ABDE showed an almost perfect agreement with a 21-radiologist panel in binary BD classification on a multivendor dataset, earning a chance as a reproducible alternative to visual evaluation. aEuro cent Individual BD assessment differs from PMR with kappa as low as 0.483. aEuro cent An ABDE correctly classified 92 % of mammograms with almost perfect agreement (kappa = 0.831). aEuro cent An ABDE can be a valid alternative to subjective BD assessment.
Place, publisher, year, edition, pages
Springer, 2016. Vol. 26, no 1, 175-183 p.
Breast density, Digital mammography, Automated system, BI-RADS density classification, Multireader/multivendor
Radiology, Nuclear Medicine and Medical Imaging
IdentifiersURN: urn:nbn:se:kth:diva-180206DOI: 10.1007/s00330-015-3784-2ISI: 000365725200021PubMedID: 25929945ScopusID: 2-s2.0-84948992707OAI: oai:DiVA.org:kth-180206DiVA: diva2:895931
QC 201601202016-01-202016-01-082016-01-20Bibliographically approved