Computer-aided detection (CAD) systems are widely implemented to improve radiologists’ sensitivity. As breast imaging advances, evaluating how CAD aids interact with digital breast tomosynthesis (DBT) and global classifications, such as the Breast Imaging Reporting and Database System (BI-RADS), to impact performance is essential. This study compared five CAD implementations: analog CAD (aCAD), original BI-RADS (oBI-RADS), oBI-RADS with aCAD, novel BI-RADS (nBI-RADS), and nBI-RADS with aCAD. The nBI-RADS CAD system incorporated intuitive colors, less clutter, and holistic guidance. Participants judged whether pseudo-DBT sets contained “cancer” with and without the assistance of their assigned CAD aid. Measures of trust in automation, usability, and workload were also assessed. Results suggest CAD aids may improve sensitivity, speed, and workload. Differences between implementations, including BI-RADS-integrated versions, were not statistically significant on any measure. These findings support CAD use with DBT while indicating more research is needed to determine more effective automated BI-RADS systems.
AdamoS. H.EricsonJ.M.NahJ. C.BremR.MitroffS. R. (2018). Mammography to tomosynthesis: Examining the differences between two-dimensional and segmented-three-dimensional visual search. Cognitive Research: Principles and Implications, 3, Article 17. https://doi.org/10.1186/s41235-018-0103-x
2.
BalleyguierC.Arfi-RoucheJ.LevyL.ToubianaP. R.Cohen-ScaliF.ToledanoA. Y.BoyerB. (2017). Improving digital breast tomosynthesis reading time: A pilot multi-reader, multi-case study using concurrent computer-aided detection (CAD). European Journal of Radiology, 97, 83–89. https://doi.org/10.1016/j.ejrad.2017.10.014
3.
BoumarafS.LiuX.FerkousC.MaX. (2020). A new computer-aided diagnosis system with modified genetic feature selection for BI-RADS classification of breast masses in mammograms. BioMed Research International, 2020, article 7695207. https://doi.org/10.1155/2020/7695207
4.
BrookeJ. (1996). SUS: A quick and dirty usability scale. In JordanP. W.ThomasB.McClellendI. L.WeerdmeesterB. (Eds.), Usability evaluation in industry (1st ed., pp. 189–194). CRC Press.
5.
CainM. S.MitroffS. R. (2012). Memory for found targets interferes with subsequent performance in multiple-target visual search. Journal of Experimental Psychology: Human Perception and Performance, 39(5), 1398–1408. https://doi.org/10.1037/a0030726
6.
ChaeE. Y.KimH. H.JeongJw.ChaeS.LeeS.ChoiY. (2019). Decrease in interpretation time for both novice and experienced readers using a concurrent computer-aided detection system for digital breast tomosynthesis. European Radiology, 29, 2518–2525. https://doi.org/10.1007/s00330-018-5886-0
7.
ChenY.WuZ.WangP.XieL.YanM.JiangM.YangZ.ZhengJ.ZhangJ.ZhuJ. (2023). Radiology residents' perceptions of artificial intelligence: Nationwide cross-sectional survey study. Journal of Medical Internet Research, 25, e48249. https://doi.org/10.2196/48249
8.
ConantE. F.ToledanoA. Y.PeriaswamyS.FotinS. V.GoJ.BoatsmanJ. E.HoffmeisterJ. W. (2019). Improving accuracy and efficiency with concurrent use of artificial intelligence for digital breast tomosynthesis. Radiology: Artificial Intelligence, 1(4), 13. https://doi.org/10.1186/s41235-022-00361-1
9.
CunninghamC.A.DrewT.WolfeJ.M. (2017). Analog computer-aided detection (CAD) information can be more effective than binary marks. Attention, Perception, & Psychophysics, 79, 679–690. https://doi.org/10.3758/s13414-016-1250-0
10.
DembrowerK.WåhlinE.LiuY.SalimM.SmithK.LindholmP.EklundM.StrandF. (2020). Effect of artificial intelligence-based triaging of breast cancer screening mammograms on cancer detection and radiologist workload: A retrospective simulation study. The Lancet, Digital Health, 2(9), e468–e474. https://doi.org/10.1016/S2589-7500(20)30185-0
11.
DrewT.GuthrieJ.RebackI. (2020). Worse in real life: An eye-tracking examination of the cost of CAD at low prevalence. Journal of Experimental Psychology, Applied, 26(4), 659–670. https://doi.org/10.1037/xap0000277
12.
European Society of Radiology. (2022). Current practical experience with artificial intelligence in clinical radiology: A survey of the European Society of Radiology. Insights into Imaging, 13(1), 107. https://doi.org/10.1186/s13244-022-01247-y
13.
GiaquintoA. N.SungH.NewmanL. A.FreedmanR. A.SmithR. A.StarJ.JemalA.SiegelR. L. (2024). Breast cancer statistics 2024. CA: A Cancer Journal for Clinicians, 74(6), 477–495. https://doi.org/10.3322/caac.21863
14.
GreenD. M.SwetsJ. A. (1988). Signal detection theory and psychophysics. Peninsula Publishing. (Original work published 1966)
15.
HartS. G.StavelandL. E. (1988). Development of NASA-TLX (Task Load Index): Results of empirical and theoretical research. Advances in Psychology, 52, 139–183. https://doi.org/10.1016/S0166-4115(08)62386-9
16.
HongI.MaheshwariC.WolfeJ. M. (2024, May17–22). Advantage and disadvantage of sequential vs. simultaneous search in simulated breast cancer screening. VSS 2024, St. Pete Beach, FL, United States.
17.
HupseR.SamulskiM.LobbesM. B.MannR. M.MusR.den HeetenG. J.BeijerinckD.PijnappelR. M.BoetesC.KarssemeijerN. (2013). Computer-aided detection of masses at mammography: Interactive decision support versus prompts. Radiology, 266(1), 123–129. https://doi.org/10.1148/radiol.12120218
JianJ.-Y.BisantzA. M.DruryC. G. (2000). Foundations for an empirically determined scale of trust in automated systems. International Journal of Cognitive Ergonomics, 4(1), 53–71. https://doi.org/10.1207/S15327566IJCE0401_04
20.
KeenJ. D.KeenJ. M.KeenJ. E. (2018). Utilization of computer-aided detection for digital screening mammography in the United States, 2008 to 2016. Journal of the American College of Radiology, 15(1 Pt A), 44–48. https://doi.org/10.1016/j.jacr.2017.08.033
KunarM. A. (2022). The optimal use of computer aided detection to find low prevalence cancers. Cognitive Research: Principles and Implications, 7, 13. https://doi.org/10.1186/s41235-022-00361-1
23.
KyonoT.GilbertF. J.van der SchaarM. (2018). MAMMO: A deep learning solution for facilitating radiologist-machine collaboration in breast cancer diagnosis. ArXiv. https://doi.org/10.48550/arXiv.1811.02661
24.
LeeC. S.MoyL. (2023). New screening performance metrics for digital breast tomosynthesis in U.S. community practice from the Breast Cancer Surveillance Consortium. Radiology, 307(4), e230505. https://doi.org/10.1148/radiol.230505
25.
LehmanC. D.WellmanR. D.BuistD. S. M.KerlikowskeK.TostesonA. N. A.MigliorettiD. L. (2015). Diagnostic accuracy of digital screening mammography with and without computer-aided detection. JAMA Internal Medicine, 175(11), 1828–1837. https://doi.org/10.1001/jamainternmed.2015.5231
26.
LowryK. P.Trentham-DietzA.SchechterC. B.AlagozO.BarlowW. E.BurnsideE. S.ConantE. F.HamptonJ. M.HuangH.KerlikowskeK.LeeS. J.MigliorettiD. L.SpragueB. L.TostesonA. N. A.YaffeM. J.StoutN. K. (2020). Long-term outcomes and cost-effectiveness of breast cancer screening with digital breast tomosynthesis in the United States. Journal of the National Cancer Institute, 112(6), 582–589. https://doi.org/10.1093/jnci/djz184
27.
MerrittS. M.HeimbaughH.LaChapellJ.LeeD. (2013). I trust it, but I don’t know why: Effects of implicit attitudes toward automation on trust in an automated system. Human Factors, 55(3), 520–534. https://doi.org/10.1177/0018720812465081
28.
MyersE. R.MoormanP.GierischJ. M.HavrileskyL. J.GrimmL. J.GhateS.DavidsonB.MongtomeryR. C.CrowleyM. J.McCroryD. C.KendrickA.SandersG. D. (2015). Benefits and harms of breast cancer screening: A systematic review. JAMA, 314(15), 1615–1634. https://doi.org/10.1001/jama.2015.13183
29.
NishikawaR. M.BaeK. T. (2018). Importance of better human-computer interaction in the era of deep learning: Mammography computer-aided diagnosis as a use case. Journal of the American College of Radiology, 15(1 Pt A), 49–52. https://doi.org/10.1016/j.jacr.2017.08.027
30.
O’DonnellP. H.WadhwaN.DanaheyK.BordenB. A.LeeS. M.HallJ. P.KlammerC.HussainS.SieglerM.SorrentinoM. J.DavisA. M.SacroY. A.NandaR.PolonskyT. S.KoynerJ. L.BurnetD. L.LipstreuerK.RubinD. T.MulcahyC., . . . RatainM. J. (2017). Pharmacogenomics-based point-of-care clinical decision support significantly alters drug prescribing. Clinical Pharmacology and Therapeutics, 102(5), 859–869. https://doi.org/10.1002/cpt.709
QianW.SunW.ZhengB. (2015). Improving the efficacy of mammography screening: The potential and challenge of developing new computer-aided detection approaches. Expert Review of Medical Devices, 12(5), 497–499. https://doi.org/10.1586/17434440.2015.1068115
33.
RozenshteinA.FindeissL. K.WoodM. J.ShihG.ParikhJ. R. (2024). The U.S. radiologist workforce: AJR expert panel narrative review. American Journal of Roentgenology. Advance online publication. https://doi.org/10.2214/AJR.24.32085
34.
SaboK. E. (2024). Detection and assessment of targets in mock digital breast tomosynthesis images using computer-aided detection systems (Publication No. 4219) [Master’s thesis, Clemson University]. TigerPrints.
35.
SechopoulosI.GhettiC. (2009). Optimization of the acquisition geometry in digital tomosynthesis of the breast. Medical Physics, 36(4), 1199–1207. https://doi.org/10.1118/1.3090889
36.
SicklesE. A.D’OrsiC. J.BassettL. W.AppletonC. M.BergW. A.BurnsideE. S.FeigS. A.GavenonisS. C.NewellM. S.TrinhM. M. (2013). ACR BI-RADS® Mammography. In D’OrsiC. J. (Ed.), ACR BI-RADS® Atlas, breast imaging reporting and data system. American College of Radiology.
37.
TrieuP. D. Y.XiaoQ.GuY.LewisS. J.BarronM. L.TapiaK.BrennanP. C.LiT. (2023). Variations of image interpretations of radiologists from different populations in mammography and tomosynthesis with different levels of breast density. Journal of Medical Imaging, 10(2), 025502. https://doi.org/10.1117/1.JMI.10.2.025502
