Measuring mammographic density: comparing a fully automated volumetric assessment versus European radiologists' qualitative classification

被引:43
|
作者
Sartor, Hanna [1 ,2 ]
LAyenng, Kristina [1 ,2 ]
Rosso, Aldana [3 ]
Borgquist, Signe [4 ,5 ]
Zackrisson, Sophia [1 ,2 ]
Timberg, Pontus [6 ]
机构
[1] Lund Univ, Dept Translat Med, Med Radiol, Lund, Sweden
[2] Skane Univ Hosp, Dept Med Imaging & Physiol, Inga Marie Nilssons Gata 49, SE-20502 Malmo, Sweden
[3] Skane Univ Hosp, Epidemiol & Register Ctr South ERC Syd, Klinkgatan 22, SE-22185 Lund, Sweden
[4] Lund Univ, Div Oncol & Pathol, Dept Clin Sci Lund, Lund, Sweden
[5] Skane Univ Hosp, Dept Oncol, Getingevagen 4, SE-22185 Lund, Sweden
[6] Lund Univ, Dept Med Radiat Phys, Dept Translat Med, Lund, Sweden
关键词
Mammography; Screening; Diagnostic imaging; Breast cancer; Women' health; BREAST-CANCER RISK; VISUAL ASSESSMENT; DATA SYSTEM; METAANALYSIS; VARIABILITY; RELIABILITY; CATEGORIES; ACCURACY; KAPPA;
D O I
10.1007/s00330-016-4309-3
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
Breast Imaging-Reporting and Data System (BI-RADS) mammographic density categories are associated with considerable interobserver variability. Automated methods of measuring volumetric breast density may reduce variability and be valuable in risk and mammographic screening stratification. Our objective was to assess agreement of mammographic density by a volumetric method with the radiologists' classification. Eight thousand seven hundred and eighty-two examinations from the Malmo Breast Tomosynthesis Screening Trial were classified according to BI-RADS, 4th Edition. Volumetric breast density was assessed using automated software for 8433 examinations. Agreement between volumetric breast density and BI-RADS was descriptively analyzed. Agreement between radiologists and between categorical volumetric density and BI-RADS was calculated, rendering kappa values. The observed agreement between BI-RADS scores of different radiologists was 80.9 % [kappa 0.77 (0.76-0.79)]. A spread of volumetric breast density for each BI-RADS category was seen. The observed agreement between categorical volumetric density and BI-RADS scores was 57.1 % [kappa 0.55 (0.53-0.56)]. There was moderate agreement between volumetric density and BI-RADS scores from European radiologists indicating that radiologists evaluate mammographic density differently than software. The automated method may be a robust and valuable tool; however, differences in interpretation between radiologists and software require further investigation. aEuro cent Agreement between qualitative and software density measurements has not been frequently studied. aEuro cent There was substantial agreement between different radiologistsA ' qualitative density assessments. aEuro cent There was moderate agreement between software and radiologists' density assessments. aEuro cent Differences in interpretation between software and radiologists require further investigation.
引用
收藏
页码:4354 / 4360
页数:7
相关论文
共 16 条
  • [1] Measuring mammographic density: comparing a fully automated volumetric assessment versus European radiologists’ qualitative classification
    Hanna Sartor
    Kristina Lång
    Aldana Rosso
    Signe Borgquist
    Sophia Zackrisson
    Pontus Timberg
    European Radiology, 2016, 26 : 4354 - 4360
  • [2] Breast Density Estimation with Fully Automated Volumetric Method: Comparison to Radiologists' Assessment by BI-RADS Categories
    Singh, Tulika
    Sharma, Madhurima
    Singla, Veenu
    Khandelwal, Niranjan
    ACADEMIC RADIOLOGY, 2016, 23 (01) : 78 - 83
  • [3] Radiologist Assessment of Breast Density by BI-RADS Categories Versus Fully Automated Volumetric Assessment
    Gweon, Hye Mi
    Youk, Ji Hyun
    Kim, Jeong-Ah
    Son, Eun Ju
    AMERICAN JOURNAL OF ROENTGENOLOGY, 2013, 201 (03) : 692 - 697
  • [4] Evaluation of Automated Mammographic Density Classification in Tomosynthesis: Comparison with Radiologists
    Kiziloglu, Hueseyin Alper
    Beyhan, Murat
    Gokce, Erkan
    Birisik, Yasar
    Battal, Muhammet Furkan
    Ceker, Muhammed Erkam
    Demir, Osman
    EUROPEAN JOURNAL OF THERAPEUTICS, 2024, 30 (03): : 258 - 266
  • [5] Mammographic Breast Density Evaluation in Korean Women Using Fully Automated Volumetric Assessment
    Youn, Inyoung
    Choi, SeonHyeong
    Kook, Shin Ho
    Choi, Yoon Jung
    JOURNAL OF KOREAN MEDICAL SCIENCE, 2016, 31 (03) : 457 - 462
  • [6] Mammographic Breast Density Assessment Using Automated Volumetric Software and Breast Imaging Reporting and Data System (BIRADS) Categorization by Expert Radiologists
    Damases, Christine N.
    Brennan, Patrick C.
    Mello-Thoms, Claudia
    McEntee, Mark F.
    ACADEMIC RADIOLOGY, 2016, 23 (01) : 70 - 77
  • [7] Mammographic density assessment: comparison of radiologists, automated volumetric measurement, and artificial intelligence-based computer-assisted diagnosis
    Eom, Hye Joung
    Cha, Joo Hee
    Choi, Woo Jung
    Cho, Su Min
    Jin, Kiok
    Kim, Hak Hee
    ACTA RADIOLOGICA, 2024, 65 (07) : 708 - 715
  • [8] Comparison of subjective and fully automated methods for measuring mammographic density
    Moshina, Nataliia
    Roman, Marta
    Sebuodegard, Sofie
    Waade, Gunvor G.
    Ursin, Giske
    Hofvind, Solveig
    ACTA RADIOLOGICA, 2018, 59 (02) : 154 - 160
  • [9] Assessment of a fully automated, high-throughput mammographic density measurement tool for use with processed digital mammograms
    Couwenberg, A. M.
    Verkooijen, H. M.
    Li, J.
    Pijnappel, R. M.
    Charaghvandi, K. R.
    Hartman, M.
    van Gils, C. H.
    CANCER CAUSES & CONTROL, 2014, 25 (08) : 1037 - 1043
  • [10] Assessment of a fully automated, high-throughput mammographic density measurement tool for use with processed digital mammograms
    A. M. Couwenberg
    H. M. Verkooijen
    J. Li
    R. M. Pijnappel
    K. R. Charaghvandi
    M. Hartman
    C. H. van Gils
    Cancer Causes & Control, 2014, 25 : 1037 - 1043