| Autor: |
Morciano F; Private Practice, 44123 Ferrara, Italy., Marcazzan C; AULSS 9 Scaligera, Breast Unit, Department of Radiology, 37122 Verona, Italy., Rella R; ASL ROMA 3, Department of Radiology, 00125 Rome, Italy., Tommasini O; ASL ROMA 3, Department of Radiology, 00125 Rome, Italy., Conti M; UOC di Radiologia Toracica e Cardiovascolare, Dipartimento di Diagnostica per Immagini, Radioterapia Oncologica ed Ematologia, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, 00168 Rome, Italy., Belli P; UOC di Radiologia Toracica e Cardiovascolare, Dipartimento di Diagnostica per Immagini, Radioterapia Oncologica ed Ematologia, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, 00168 Rome, Italy.; Facoltà di Medicina e Chirurgia, Università Cattolica Sacro Cuore, Largo F. Vito 1, 00168 Rome, Italy., Spagnolo A; AULSS 9 Scaligera, Breast Unit, Department of Radiology, 37122 Verona, Italy., Quaglia A; AULSS 9 Scaligera, Breast Unit, Department of Radiology, 37122 Verona, Italy., Tambalo S; CIMEC-Center for Mind/Brain, University of Trento, 38068 Rovereto, Italy., Trisca AG; Private Practice, 37122 Verona, Italy., Rossati C; AULSS 9 Scaligera, Breast Unit, Department of Radiology, 37122 Verona, Italy., Fornasa F; AULSS 9 Scaligera, Breast Unit, Department of Radiology, 37122 Verona, Italy., Romanucci G; AULSS 9 Scaligera, Breast Unit, Department of Radiology, 37122 Verona, Italy. |
| Abstrakt: |
Mammographic density (MD) assessment is subject to inter- and intra-observer variability. An automated method, such as Quantra software, could be a useful tool for an objective and reproducible MD assessment. Our purpose was to evaluate the performance of Quantra software in assessing MD, according to BI-RADS ® Atlas Fifth Edition recommendations, verifying the degree of agreement with the gold standard, given by the consensus of two breast radiologists. A total of 5009 screening examinations were evaluated by two radiologists and analysed by Quantra software to assess MD. The agreement between the three assigned values was expressed as intraclass correlation coefficients (ICCs). The agreement between the software and the two readers (R1 and R2) was moderate with ICC values of 0.725 and 0.713, respectively. A better agreement was demonstrated between the software's assessment and the average score of the values assigned by the two radiologists, with an index of 0.793, which reflects a good correlation. Quantra software appears a promising tool in supporting radiologists in the MD assessment and could be part of a personalised screening protocol soon. However, some fine-tuning is needed to improve its accuracy, reduce its tendency to overestimate, and ensure it excludes high-density structures from its assessment. |
