Abstract
Methods 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 (κ) and accuracy (proportion of cases correctly classified) were calculated for binary (BI-RADS a-b versus c-d) and 4-class classification.
Results While the agreement of individual radiologists with the PMR ranged from κ=0.483 to κ=0.885, the ABDE correctly classified 563/613 mammograms (92 %). A substantial agreement for binary classification was found for individual
reader pairs (κ=0.620, standard deviation [SD]=0.140), individual versus PMR (κ=0.736, SD=0.117), and individual versus ABDE (κ=0.674, SD=0.095). Agreement between ABDE and PMR was almost perfect (κ=0.831).
Conclusions 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.
Original language | English |
---|---|
Journal | European Radiology |
Publication status | Published - 2016 |
Fingerprint
Cite this
Mammographic density: Comparison of visual assessment with fully automatic calculation on a multivendor dataset. / Sacchetto, Daniela; Morra, Lia; Agliozzo, S.; Bernardi, D.; Björklund, Tomas; Brancato, Beniamino; Bravetti, Patrizia; Carbonaro, Luca A.; Correale, L.; Fantò, Carmen; Favettini, Elisabetta; Martincich, Laura; Milanesio, Luisella; Mombelloni, Sara; Monetti, Francesco; Morrone, D.; Pellegrini, Marco; Pesce, Barbara; Petrillo, Antonella; Saguatti, G.; Stevanin, Carmen; Trimboli, Rubina M.; Tuttobene, Paola; Valentini, Marvi; Marra, Vincenzo; Frigerio, A.; Bert, Alberto; Sardanelli, Francesco.
In: European Radiology, 2016.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Mammographic density: Comparison of visual assessment with fully automatic calculation on a multivendor dataset
AU - Sacchetto, Daniela
AU - Morra, Lia
AU - Agliozzo, S.
AU - Bernardi, D.
AU - Björklund, Tomas
AU - Brancato, Beniamino
AU - Bravetti, Patrizia
AU - Carbonaro, Luca A.
AU - Correale, L.
AU - Fantò, Carmen
AU - Favettini, Elisabetta
AU - Martincich, Laura
AU - Milanesio, Luisella
AU - Mombelloni, Sara
AU - Monetti, Francesco
AU - Morrone, D.
AU - Pellegrini, Marco
AU - Pesce, Barbara
AU - Petrillo, Antonella
AU - Saguatti, G.
AU - Stevanin, Carmen
AU - Trimboli, Rubina M.
AU - Tuttobene, Paola
AU - Valentini, Marvi
AU - Marra, Vincenzo
AU - Frigerio, A.
AU - Bert, Alberto
AU - Sardanelli, Francesco
PY - 2016
Y1 - 2016
N2 - Objectives 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.Methods 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 evaluatedby 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 (κ) and accuracy (proportion of cases correctly classified) were calculated for binary (BI-RADS a-b versus c-d) and 4-class classification.Results While the agreement of individual radiologists with the PMR ranged from κ=0.483 to κ=0.885, the ABDE correctly classified 563/613 mammograms (92 %). A substantial agreement for binary classification was found for individualreader pairs (κ=0.620, standard deviation [SD]=0.140), individual versus PMR (κ=0.736, SD=0.117), and individual versus ABDE (κ=0.674, SD=0.095). Agreement between ABDE and PMR was almost perfect (κ=0.831).Conclusions 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.
AB - Objectives 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.Methods 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 evaluatedby 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 (κ) and accuracy (proportion of cases correctly classified) were calculated for binary (BI-RADS a-b versus c-d) and 4-class classification.Results While the agreement of individual radiologists with the PMR ranged from κ=0.483 to κ=0.885, the ABDE correctly classified 563/613 mammograms (92 %). A substantial agreement for binary classification was found for individualreader pairs (κ=0.620, standard deviation [SD]=0.140), individual versus PMR (κ=0.736, SD=0.117), and individual versus ABDE (κ=0.674, SD=0.095). Agreement between ABDE and PMR was almost perfect (κ=0.831).Conclusions 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.
M3 - Article
C2 - 25929945
JO - European Radiology
JF - European Radiology
SN - 0938-7994
ER -