Computer-Aided Approach for BI-RADS Breast Density
Classification: Multicentric Retrospective Study

C 2024

Computer-Aided Approach for BI-RADS Breast Density Classification: Multicentric Retrospective Study

KVAK, Daniel; Marek BIROŠ; Robert HRUBÝ a Eva JANŮ

Základní údaje

Originální název

Computer-Aided Approach for BI-RADS Breast Density Classification: Multicentric Retrospective Study

Autoři

KVAK, Daniel; Marek BIROŠ; Robert HRUBÝ a Eva JANŮ

Vydání

Cham, Germany, Breast Cancer Pathophysiology: An Interdisciplinary Approach, od s. 311-322, 2024

Nakladatel

Springer, Cham

Další údaje

Jazyk

angličtina

Typ výsledku

Kapitola resp. kapitoly v odborné knize

Obor

30204 Oncology

Stát vydavatele

Německo

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

tištěná verze "print"

Označené pro přenos do RIV

Organizační jednotka

Lékařská fakulta

ISBN

978-3-031-65834-1

DOI

https://doi.org/10.1007/16833_2024_284

Klíčová slova anglicky

BI-RADS, Breast density, Computer-aided diagnosis, Deep learning, Full-field digital mammography, Medical image processing

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 7. 9. 2024 08:42, Mgr. Daniel Kvak

Anotace

V originále

Assessing mammographic breast density, a crucial risk determinant for breast cancer, is typically conducted by radiologists through a visual examination of mammography images using the Breast Imaging and Reporting Data System (BI-RADS) breast density classification. However, significant interobserver variability among radiologists leads to inconsistency and potential inaccuracy in breast density assessments and consequent risk predictions. To address this, we analyzed 3835 Full-Field Digital Mammography (FFDM) studies from three mammographic centers. A team of 10 radiologists with experience in breast imaging ranging from 2 to 27 years evaluated these studies, establishing a ground truth for 2127 cases. We utilized 1122 (BI-RADS A: 356, BI-RADS B: 356, BI-RADS C: 356, BI-RADS D: 54) of the studies for training and 122 (BI-RADS A: 39, BI-RADS B: 39, BI-RADS C: 39, BI-RADS D: 5) for testing our Deep-Learning-based Automatic Detection (DLAD) algorithm. The proposed DLAD demonstrated an overall high accuracy (0.853), with balanced accuracy (BA) scores of 0.899 for BI-RADS Category A, 0.838 for Category B, 0.900 for Category C, and 0.900 for Category D. Our findings suggest that the proposed DLAD model can serve as a substantial support in the evaluation process, introducing an additional layer of analysis.

Návaznosti

MUNI/A/1551/2023, interní kód MU

Název: Rozvoj vědeckých aspektů simulačního vzdělávání na LF MU I.

Investor: Masarykova univerzita, Rozvoj vědeckých aspektů simulačního vzdělávání na LF MU I.

Citovat

KVAK, Daniel; Marek BIROŠ; Robert HRUBÝ a Eva JANŮ. Computer-Aided Approach for BI-RADS Breast Density Classification: Multicentric Retrospective Study. In Rezaei, N. Breast Cancer Pathophysiology: An Interdisciplinary Approach. Cham, Germany: Springer, Cham, 2024, s. 311-322. ISBN 978-3-031-65834-1. Dostupné z: https://doi.org/10.1007/16833_2024_284.

@inbook{2429938,
   author = {Kvak, Daniel and Biroš, Marek and Hrubý, Robert and Janů, Eva},
   address = {Cham, Germany},
   booktitle = {Breast Cancer Pathophysiology: An Interdisciplinary Approach},
   doi = {https://doi.org/10.1007/16833_2024_284},
   editor = {Rezaei, N.},
   keywords = {BI-RADS, Breast density, Computer-aided diagnosis, Deep learning, Full-field digital mammography, Medical image processing},
   howpublished = {tištěná verze "print"},
   language = {eng},
   location = {Cham, Germany},
   isbn = {978-3-031-65834-1},
   pages = {311-322},
   publisher = {Springer, Cham},
   title = {Computer-Aided Approach for BI-RADS Breast Density Classification: Multicentric Retrospective Study},
   year = {2024}
}

TY  - CHAP
ID  - 2429938
AU  - Kvak, Daniel - Biroš, Marek - Hrubý, Robert - Janů, Eva
PY  - 2024
TI  - Computer-Aided Approach for BI-RADS Breast Density Classification: Multicentric Retrospective Study
PB  - Springer, Cham
CY  - Cham, Germany
SN  - 9783031658341
KW  - BI-RADS, Breast density, Computer-aided diagnosis, Deep learning, Full-field digital mammography, Medical image processing
N2  - Assessing mammographic breast density, a crucial risk determinant for breast cancer, is typically conducted by radiologists through a visual examination of mammography images using the Breast Imaging and Reporting Data System (BI-RADS) breast density classification. However, significant interobserver variability among radiologists leads to inconsistency and potential inaccuracy in breast density assessments and consequent risk predictions. To address this, we analyzed 3835 Full-Field Digital Mammography (FFDM) studies from three mammographic centers. A team of 10 radiologists with experience in breast imaging ranging from 2 to 27 years evaluated these studies, establishing a ground truth for 2127 cases. We utilized 1122 (BI-RADS A: 356, BI-RADS B: 356, BI-RADS C: 356, BI-RADS D: 54) of the studies for training and 122 (BI-RADS A: 39, BI-RADS B: 39, BI-RADS C: 39, BI-RADS D: 5) for testing our Deep-Learning-based Automatic Detection (DLAD) algorithm. The proposed DLAD demonstrated an overall high accuracy (0.853), with balanced accuracy (BA) scores of 0.899 for BI-RADS Category A, 0.838 for Category B, 0.900 for Category C, and 0.900 for Category D. Our findings suggest that the proposed DLAD model can serve as a substantial support in the evaluation process, introducing an additional layer of analysis.
ER  -

KVAK, Daniel; Marek BIROŠ; Robert HRUBÝ a Eva JANŮ. Computer-Aided Approach for BI-RADS Breast Density Classification: Multicentric Retrospective Study. In Rezaei, N. \textit{Breast Cancer Pathophysiology: An Interdisciplinary Approach}. Cham, Germany: Springer, Cham, 2024, s.~311-322. ISBN~978-3-031-65834-1. Dostupné z: https://doi.org/10.1007/16833\_{}2024\_{}284.

Přehled o publikaci