Mammographic density: Comparison of visual assessment with fully automatic calculation on a multivendor dataset

Daniela Sacchetto, Lia Morra, S. Agliozzo, D. Bernardi, Tomas Björklund, Beniamino Brancato, Patrizia Bravetti, Luca A. Carbonaro, L. Correale, Carmen Fantò, Elisabetta Favettini, Laura Martincich, Luisella Milanesio, Sara Mombelloni, Francesco Monetti, D. Morrone, Marco Pellegrini, Barbara Pesce, Antonella Petrillo, G. SaguattiCarmen Stevanin, Rubina M. Trimboli, Paola Tuttobene, Marvi Valentini, Vincenzo Marra, A. Frigerio, Alberto Bert, Francesco Sardanelli

Research output: Contribution to journalArticle

Abstract

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 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 languageEnglish
JournalEuropean Radiology
Publication statusPublished - 2016

Fingerprint

Breast
Radiologists
Datasets
Breast Density

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 journalArticle

Sacchetto, D, Morra, L, Agliozzo, S, Bernardi, D, Björklund, T, Brancato, B, Bravetti, P, Carbonaro, LA, Correale, L, Fantò, C, Favettini, E, Martincich, L, Milanesio, L, Mombelloni, S, Monetti, F, Morrone, D, Pellegrini, M, Pesce, B, Petrillo, A, Saguatti, G, Stevanin, C, Trimboli, RM, Tuttobene, P, Valentini, M, Marra, V, Frigerio, A, Bert, A & Sardanelli, F 2016, 'Mammographic density: Comparison of visual assessment with fully automatic calculation on a multivendor dataset', European Radiology.
Sacchetto D, Morra L, Agliozzo S, Bernardi D, Björklund T, Brancato B et al. Mammographic density: Comparison of visual assessment with fully automatic calculation on a multivendor dataset. European Radiology. 2016.
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. / Mammographic density: Comparison of visual assessment with fully automatic calculation on a multivendor dataset. In: European Radiology. 2016.
@article{61185234a6ee4ac3912165ad38de1bac,
title = "Mammographic density: Comparison of visual assessment with fully automatic calculation on a multivendor dataset",
abstract = "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.",
author = "Daniela Sacchetto and Lia Morra and S. Agliozzo and D. Bernardi and Tomas Bj{\"o}rklund and Beniamino Brancato and Patrizia Bravetti and Carbonaro, {Luca A.} and L. Correale and Carmen Fant{\`o} and Elisabetta Favettini and Laura Martincich and Luisella Milanesio and Sara Mombelloni and Francesco Monetti and D. Morrone and Marco Pellegrini and Barbara Pesce and Antonella Petrillo and G. Saguatti and Carmen Stevanin and Trimboli, {Rubina M.} and Paola Tuttobene and Marvi Valentini and Vincenzo Marra and A. Frigerio and Alberto Bert and Francesco Sardanelli",
year = "2016",
language = "English",
journal = "European Radiology",
issn = "0938-7994",
publisher = "Springer Verlag",

}

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 -