Artificial- intelligence- enhanced synthetic thick slabs versus standard slices in digital breast tomosynthesis

被引:1
|
作者
Sauer, Stephanie Tina [1 ]
Christner, Sara Aniki [1 ]
Kuhl, Philipp Josef [1 ]
Kunz, Andreas Steven [1 ]
Huflage, Henner [1 ]
Luetkens, Karsten Sebastian [1 ]
Schlaiss, Tanja [2 ]
Bley, Thorsten Alexander [1 ]
Grunz, Jan-peter [1 ]
机构
[1] Univ Hosp Wurzburg, Dept Diagnost & Intervent Radiol, Oberdurrbacher Str, Wurzburg, Germany
[2] Univ Hosp Wurzburg, Dept Obstet & Gynaecol, Josef Schneider Str, Wurzburg, Germany
来源
BRITISH JOURNAL OF RADIOLOGY | 2023年 / 96卷 / 1145期
关键词
2D MAMMOGRAPHY; READING TIME; CANCER; PERFORMANCE; ACCURACY; SOCIETY; READER; IMPACT;
D O I
10.1259/bjr.20220967
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
Objectives: Digital breast tomosynthesis (DBT) can provide additional information over mammography, albeit at the cost of prolonged reading time. This study retrospectively investigated the impact of reading enhanced synthetic 6 mm slabs instead of standard 1 mm slices on interpretation time and readers performance in a diagnostic assessment centre.Methods: Three radiologists (R1- 3; 6/4/2 years of breast imaging experience) reviewed 111 diagnostic DBT exam- inations. Two datasets were interpreted independently for each patient, with one set containing artificial- intelligence- enhanced synthetic 6 mm slabs with 3 mm overlap, while the other set comprised standard 1 mm slices. Blinded to histology and follow - up, readers noted individual BIRADS categories and diagnostic confidence while reading time was recorded. Among the 111 exami- nations, 70 findings were histopathologically correlated including 56 malignancies.Results: No significant difference was found between BIRADS categories assigned based on 6 mm vs 1 mm datasets (p >= 0.317). Diagnostic accuracy was compa- rable for 6 mm and 1 mm readings (R1: 87.0% vs 87.0%; R2: 86.1% vs 87.0%; R3: 80.0% vs 84.4%; p >= 0.125) with high interrater agreement (intraclass correlation coeffi- cient 0.848 vs 0.865). One reader reported higher confi- dence with 1 mm slices (R1: p=0.033). Reading time was substantially shorter when interpreting 6 mm slabs compared to 1 mm slices (R1: 33.5 vs 46.2; R2: 49.1 vs 64.8; R3: 39.5 vs 67.2 sec; all p < 0.001).Conclusions: Artificial-intelligence-enhanced synthetic 6 mm slabs allow for substantial interpretation time reduction in diagnostic DBT without a decrease in reader accuracy.Advances in knowledge: A simplified slab - only protocol instead of 1 mm slices may offset the higher reading time without a loss of diagnosis- relevant image information in first and second readings. Further evaluations are required regarding workflow implications, particularly in screening settings.
引用
收藏
页数:7
相关论文
共 48 条
  • [1] New Horizons: Artificial Intelligence for Digital Breast Tomosynthesis
    Goldberg, Julia E.
    Reig, Beatriu
    Lewin, Alana A.
    Gao, Yiming
    Heacock, Laura
    Heller, Samantha L.
    Moy, Linda
    [J]. RADIOGRAPHICS, 2023, 43 (01) : 19 - 19
  • [2] The Power and Promise of Artificial Intelligence for Digital Breast Tomosynthesis
    Iutaka, Tatiana
    de Freitas, Marina Bellintani
    Omar, Samir Sari
    Scortegagna, Felipe Alba
    Nael, Kambiz
    Nunes, Renato Hoffmann
    Pacheco, Felipe Torres
    Maia Junior, Antonio Carlos Martins
    do Amaral, Lazaro Luis Faria
    da Rocha, Antonio Jose
    [J]. RADIOGRAPHICS, 2023, 43 (01) : 1 - 19
  • [3] Artificial Intelligence for Reducing Workload in Breast Cancer Screening with Digital Breast Tomosynthesis
    Shoshan, Yoel
    Bakalo, Ran
    Gilboa-Solomon, Flora
    Ratner, Vadim
    Barkan, Ella
    Ozery-Flato, Michal
    Amit, Mika
    Khapun, Daniel
    Ambinder, Emily B.
    Oluyemi, Eniola T.
    Panigrahi, Babita
    DiCarlo, Philip A.
    Rosen-Zvi, Michal
    Mullen, Lisa A.
    [J]. RADIOLOGY, 2022, 303 (01) : 69 - 77
  • [4] Artificial Intelligence in Breast Imaging: A Special Focus on Advances in Digital Mammography & Digital Breast Tomosynthesis
    Avendano, Daly
    Sofia, Carmelo
    Zapata, Pedro
    Portaluri, Antonio
    Orlando, Alessia Angela Maria
    Avalos, Pablo
    Blandino, Alfredo
    Ascenti, Giorgio
    Cardona-Huerta, Servando
    Marino, Maria Adele
    [J]. CURRENT MEDICAL IMAGING, 2023, 19 (08) : 799 - 806
  • [5] Artificial intelligence for breast cancer detection in mammography and digital breast tomosynthesis: State of the art
    Sechopoulos, Ioannis
    Teuwen, Jonas
    Mann, Ritse
    [J]. SEMINARS IN CANCER BIOLOGY, 2021, 72 : 214 - 225
  • [6] Artificial Intelligence for Mammography and Digital Breast Tomosynthesis: Current Concepts and Future Perspectives
    Geras, Krzysztof J.
    Mann, Ritse M.
    Moy, Linda
    [J]. RADIOLOGY, 2019, 293 (02) : 246 - 259
  • [7] Improving Accuracy and Efficiency with Concurrent Use of Artificial Intelligence for Digital Breast Tomosynthesis
    Conant, Emily F.
    Toledano, Alicia Y.
    Periaswamy, Senthil
    Fotin, Sergei, V
    Go, Jonathan
    Boatsman, Justin E.
    Hoffmeister, Jeffrey W.
    [J]. RADIOLOGY-ARTIFICIAL INTELLIGENCE, 2019, 1 (04)
  • [8] Artificial Intelligence Detection of Missed Cancers at Digital Mammography That Were Detected at Digital Breast Tomosynthesis
    Dahlblom, Victor
    Andersson, Ingvar
    Lang, Kristina
    Tingberg, Anders
    Zackrisson, Sophia
    Dustler, Magnus
    [J]. RADIOLOGY-ARTIFICIAL INTELLIGENCE, 2021, 3 (06)
  • [9] Multicenter Evaluation of Breast Cancer Screening with Digital Breast Tomosynthesis in Combination with Synthetic versus Digital Mammography
    Zuckerman, Samantha P.
    Sprague, Brian L.
    Weaver, Donald L.
    Herschorn, Sally D.
    Conant, Emily F.
    [J]. RADIOLOGY, 2020, 297 (03) : 545 - 553
  • [10] Personalized breast cancer screening with selective addition of digital breast tomosynthesis through artificial intelligence
    Dahlblom, Victor
    Tingberg, Anders
    Zackrisson, Sophia
    Dustler, Magnus
    [J]. JOURNAL OF MEDICAL IMAGING, 2023, 10