Skip to content
2000
  1. Home
  2. A-Z Publications
  3. Current Medical Imaging
  4. Volume 20, Issue 1
  5. Article
Volume 20, Issue 1
  • ISSN: 1573-4056
  • E-ISSN: 1875-6603
file format pdf download PDF
side by side viewer icon HTML

Abstract

Background

The usage of artificial intelligence in medical image analysis has significantly surpassed that of earlier related technologies. This paper aimed to investigate the diagnostic accuracy of Artificial Intelligence (AI) based-deep learning models for breast cancer detection.

Methods

We used the PICO (Patient/Population/Problem, Intervention, Comparison, Outcome) scheme to formulate the research question and construct our search terms. Studies were systematically examined from the available literature using the constructed search terms from PubMed, and ScienceDirect according to the PRISMA guidelines. The quality of the included studies was assessed using the QUADAS-2 checklist. The characteristics of each included study such as the study design, population, index test, and reference standard, were extracted. The sensitivity, specificity, and AUC for each study were also reported.

Results

In this systematic review, 14 studies were analyzed. Eight studies showed that AI was more accurate than radiologists in evaluating mammographic images, while one comprehensive study found AI to be less precise. Studies that reported sensitivity and specificity without radiologist intervention showed performance scores ranging from 16.0% to 89.71%. With radiologist intervention, sensitivity was between 62% to 86%. Only three studies reported a specificity of 73.5% to 79%. The AUC of the studies was between 0.79 and 0.95. Thirteen studies were retrospective, and one was prospective.

Conclusion

There's inadequate evidence on the effectiveness of AI-based deep learning for breast cancer screening in clinical settings. More research is needed, including studies evaluating accuracy, RCTs, and large-scale cohort studies. This systematic review found that AI-based deep learning improves radiologists' accuracy, especially for novice radiologists. Younger, tech-savvy clinicians may be more accepting of AI. Although it can't replace radiologists, the encouraging results suggest it will play a significant role in identifying breast cancer in the future.

Registration Number

PROSPERO - CRD42021278655

© 2024 The Author(s). Published by Bentham Science Publisher.
This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International Public License (CC-BY 4.0), a copy of which is available at: https://creativecommons.org/licenses/by/4.0/legalcode. This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Loading

Article metrics loading...

/content/journals/cmir/10.2174/1573405620666230417085624
2024-01-01
2025-04-24

  • From This Site

    /content/journals/cmir/10.2174/1573405620666230417085624
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
The full text of this item is not currently available.

References

  1. WHObreast cancer.World health organization2018
     [Google Scholar]
  2. YouldenD.R. CrambS.M. DunnN.A.M. MullerJ.M. PykeC.M. BaadeP.D. The descriptive epidemiology of female breast cancer: An international comparison of screening, incidence, survival and mortality.Cancer Epidemiol.201236323724810.1016/j.canep.2012.02.00722459198
     [Google Scholar]
  3. KalagerM. HaldorsenT. BretthauerM. HoffG. ThoresenS.O. AdamiH.O. Improved breast cancer survival following introduction of an organized mammography screening program among both screened and unscreened women: A population-based cohort study.Breast Cancer Res.2009114R4410.1186/bcr233119575807
     [Google Scholar]
  4. van LuijtP.A. HeijnsdijkE.A.M. FracheboudJ. OverbeekL.I.H. BroedersM.J.M. WesselingJ. den HeetenG.J. de KoningH.J. The distribution of ductal carcinoma in situ (DCIS) grade in 4232 women and its impact on overdiagnosis in breast cancer screening.Breast Cancer Res.20161814710.1186/s13058‑016‑0705‑527160733
     [Google Scholar]
  5. YenM.F. TabárL. VitakB. SmithR.A. ChenH.H. DuffyS.W. Quantifying the potential problem of overdiagnosis of ductal carcinoma in situ in breast cancer screening.Eur. J. Cancer200339121746175410.1016/S0959‑8049(03)00260‑012888370
     [Google Scholar]
  6. NehmatH. NehmatH. Overdiagnosis of breast cancer in population screening: Does it make breast screening worthless?Cancer Biol. Med.20171411810.20892/j.issn.2095‑3941.2016.005028443199
     [Google Scholar]
  7. KolbT.M. LichyJ. NewhouseJ.H. Occult cancer in women with dense breasts: Detection with screening US--diagnostic yield and tumor characteristics.Radiology1998207119119910.1148/radiology.207.1.95303169530316
     [Google Scholar]
  8. KerlikowskeK. GradyD. BarclayJ. SicklesE.A. ErnsterV. Effect of age, breast density, and family history on the sensitivity of first screening mammography.JAMA19962761333810.1001/jama.1996.035400100350278667536
     [Google Scholar]
  9. KolbT.M. LichyJ. NewhouseJ.H. Comparison of the performance of screening mammography, physical examination, and breast US and evaluation of factors that influence them: An analysis of 27,825 patient evaluations.Radiology2002225116517510.1148/radiol.225101166712355001
     [Google Scholar]
  10. ElmoreJ.G. MigliorettiD.L. ReischL.M. BartonM.B. KreuterW. ChristiansenC.L. FletcherS.W. Screening mammograms by community radiologists: Variability in false-positive rates.J. Natl. Cancer Inst.200294181373138010.1093/jnci/94.18.137312237283
     [Google Scholar]
  11. ZhangD. MishraS. BrynjolfssonE. EtchemendyJ. GanguliD. GroszB. LyonsT. ManyikaJ. NieblesJ.C. SellittoM. ShohamY. The AI index 2021 annual report.arXiv preprint arXiv:2103.063122021
     [Google Scholar]
  12. KimH.E. KimH.H. HanB.K. KimK.H. HanK. NamH. LeeE.H. KimE.K. Changes in cancer detection and false-positive recall in mammography using artificial intelligence: A retrospective, multireader study.Lancet Digit. Health202023e138e14810.1016/S2589‑7500(20)30003‑033334578
     [Google Scholar]
  13. DustlerM. Evaluating AI in breast cancer screening: A complex task.Lancet Digit. Health202023e106e10710.1016/S2589‑7500(20)30019‑433334574
     [Google Scholar]
  14. ObermeyerZ. EmanuelE.J. Predicting the future—big data, machine learning, and clinical medicine.N. Engl. J. Med.2016375131216121910.1056/NEJMp160618127682033
     [Google Scholar]
  15. ChockleyK. EmanuelE. The end of radiology? Three threats to the future practice of radiology.J. Am. Coll. Radiol.201613121415142010.1016/j.jacr.2016.07.01027652572
     [Google Scholar]
  16. StowerH. AI for breast-cancer screening.Nat. Med.202026216332047318
     [Google Scholar]
  17. HosnyA. ParmarC. QuackenbushJ. SchwartzL.H. AertsH.J.W.L. Artificial intelligence in radiology.Nat. Rev. Cancer201818850051010.1038/s41568‑018‑0016‑529777175
     [Google Scholar]
  18. McDonaldR.J. SchwartzK.M. EckelL.J. DiehnF.E. HuntC.H. BartholmaiB.J. EricksonB.J. KallmesD.F. The effects of changes in utilization and technological advancements of cross-sectional imaging on radiologist workload.Acad. Radiol.20152291191119810.1016/j.acra.2015.05.00726210525
     [Google Scholar]
  19. LeCunY BengioY HintonG. Deep learning.nature20155217553436444
     [Google Scholar]
  20. JanieschC. ZschechP. HeinrichK. Machine learning and deep learning.Electron. Mark.202131368569510.1007/s12525‑021‑00475‑2
     [Google Scholar]
  21. WaddenJ.J. Defining the undefinable: The black box problem in healthcare artificial intelligence.J. Med. Ethics2022481076476810.1136/medethics‑2021‑10752934290113
     [Google Scholar]
  22. von EschenbachW.J. Transparency and the black box problem: Why we do not trust AI.Philos. Technol.20213441607162210.1007/s13347‑021‑00477‑0
     [Google Scholar]
  23. DuránJ.M. JongsmaK.R. Who is afraid of black box algorithms? On the epistemological and ethical basis of trust in medical AI.J. Med. Ethics2021475medethics-2020-10682010.1136/medethics‑2020‑10682033737318
     [Google Scholar]
  24. MoherD. LiberatiA. TetzlaffJ. AltmanD.G. Preferred reporting items for systematic reviews and meta-analyses: The PRISMA statement.Int. J. Surg.20108533634110.1016/j.ijsu.2010.02.00720171303
     [Google Scholar]
  25. SantosC.M.C. PimentaC.A.M. NobreM.R.C. The PICO strategy for the research question construction and evidence search.Rev. Lat. Am. Enfermagem200715350851110.1590/S0104‑1169200700030002317653438
     [Google Scholar]
  26. WhitingP.F. RutjesA.W. WestwoodM.E. MallettS. DeeksJ.J. ReitsmaJ.B. LeeflangM.M. SterneJ.A. BossuytP.M. QUADAS-2: A revised tool for the quality assessment of diagnostic accuracy studies.Ann. Intern. Med.2011155852953610.7326/0003‑4819‑155‑8‑201110180‑0000922007046
     [Google Scholar]
  27. BeckerA.S. MarconM. GhafoorS. WurnigM.C. FrauenfelderT. BossA. Deep learning in mammography: Diagnostic accuracy of a multipurpose image analysis software in the detection of breast cancer.Invest. Radiol.201752743444010.1097/RLI.000000000000035828212138
     [Google Scholar]
  28. WatanabeA.T. LimV. VuH.X. ChimR. WeiseE. LiuJ. BradleyW.G. ComstockC.E. Improved cancer detection using artificial intelligence: A retrospective evaluation of missed cancers on mammography.J. Digit. Imaging201932462563710.1007/s10278‑019‑00192‑531011956
     [Google Scholar]
  29. DembrowerK. WåhlinE. LiuY. SalimM. SmithK. LindholmP. EklundM. StrandF. Effect of artificial intelligence-based triaging of breast cancer screening mammograms on cancer detection and radiologist workload: A retrospective simulation study.Lancet Digit. Health202029e468e47410.1016/S2589‑7500(20)30185‑033328114
     [Google Scholar]
  30. RibliD. HorváthA. UngerZ. PollnerP. CsabaiI. Detecting and classifying lesions in mammograms with Deep Learning.Sci. Rep.201881416510.1038/s41598‑018‑22437‑z29545529
     [Google Scholar]
  31. Rodríguez-RuizA. KrupinskiE. MordangJ.J. SchillingK. Heywang-KöbrunnerS.H. SechopoulosI. MannR.M. Detection of breast cancer with mammography: Effect of an artificial intelligence support system.Radiology2019290230531410.1148/radiol.201818137130457482
     [Google Scholar]
  32. Rodriguez-RuizA. LångK. Gubern-MeridaA. BroedersM. GennaroG. ClauserP. HelbichT.H. ChevalierM. TanT. MertelmeierT. WallisM.G. AnderssonI. ZackrissonS. MannR.M. SechopoulosI. Stand-alone artificial intelligence for breast cancer detection in mammography: Comparison with 101 radiologists.J. Natl. Cancer Inst.2019111991692210.1093/jnci/djy22230834436
     [Google Scholar]
  33. LångK. DustlerM. DahlblomV. ÅkessonA. AnderssonI. ZackrissonS. Identifying normal mammograms in a large screening population using artificial intelligence.Eur. Radiol.20213131687169210.1007/s00330‑020‑07165‑132876835
     [Google Scholar]
  34. McKinneyS.M. SieniekM. GodboleV. GodwinJ. AntropovaN. AshrafianH. BackT. ChesusM. CorradoG.S. DarziA. EtemadiM. Garcia-VicenteF. GilbertF.J. Halling-BrownM. HassabisD. JansenS. KarthikesalingamA. KellyC.J. KingD. LedsamJ.R. MelnickD. MostofiH. PengL. ReicherJ.J. Romera-ParedesB. SidebottomR. SuleymanM. TseD. YoungK.C. De FauwJ. ShettyS. International evaluation of an AI system for breast cancer screening.Nature20205777788899410.1038/s41586‑019‑1799‑631894144
     [Google Scholar]
  35. PacilèS. LopezJ. ChoneP. BertinottiT. GrouinJ.M. FillardP. Improving breast cancer detection accuracy of mammography with the concurrent use of an artificial intelligence tool.Radiol. Artif. Intell.202026e19020810.1148/ryai.202019020833937844
     [Google Scholar]
  36. Raya-PovedanoJ.L. Romero-MartínS. Elías-CabotE. Gubern-MéridaA. Rodríguez-RuizA. Álvarez-BenitoM. AI-based strategies to reduce workload in breast cancer screening with mammography and tomosynthesis: A retrospective evaluation.Radiology20213001576510.1148/radiol.202120355533944627
     [Google Scholar]
  37. Akselrod-BallinA. ChorevM. ShoshanY. SpiroA. HazanA. MelamedR. BarkanE. HerzelE. NaorS. KaravaniE. KorenG. GoldschmidtY. ShalevV. Rosen-ZviM. GuindyM. Predicting breast cancer by applying deep learning to linked health records and mammograms.Radiology2019292233134210.1148/radiol.201918262231210611
     [Google Scholar]
  38. SalimM. WåhlinE. DembrowerK. AzavedoE. FoukakisT. LiuY. SmithK. EklundM. StrandF. External evaluation of 3 commercial artificial intelligence algorithms for independent assessment of screening mammograms.JAMA Oncol.20206101581158810.1001/jamaoncol.2020.332132852536
     [Google Scholar]
  39. SchaffterT. BuistD.S.M. LeeC.I. NikulinY. RibliD. GuanY. LotterW. JieZ. DuH. WangS. FengJ. FengM. KimH.E. AlbiolF. AlbiolA. MorrellS. WojnaZ. AhsenM.E. AsifU. Jimeno YepesA. YohanandanS. Rabinovici-CohenS. YiD. HoffB. YuT. Chaibub NetoE. RubinD.L. LindholmP. MargoliesL.R. McBrideR.B. RothsteinJ.H. SiehW. Ben-AriR. HarrerS. TristerA. FriendS. NormanT. SahinerB. StrandF. GuinneyJ. StolovitzkyG. MackeyL. CahoonJ. ShenL. SohnJ.H. TrivediH. ShenY. ButurovicL. PereiraJ.C. CardosoJ.S. CastroE. KallebergK.T. PelkaO. NedjarI. GerasK.J. NensaF. GoanE. KoitkaS. CaballeroL. CoxD.D. KrishnaswamyP. PandeyG. FriedrichC.M. PerrinD. FookesC. ShiB. Cardoso NegrieG. KawczynskiM. ChoK. KhooC.S. LoJ.Y. SorensenA.G. JungH. Evaluation of combined artificial intelligence and radiologist assessment to interpret screening mammograms.JAMA Netw. Open202033e20026510.1001/jamanetworkopen.2020.026532119094
     [Google Scholar]
  40. ValenciaE.M. PruthiS. Practice-changing opportunity to reduce disparities in screening mammography—implementation of risk assessment in primary care.JAMA Netw. Open202149e212453510.1001/jamanetworkopen.2021.2453534505890
     [Google Scholar]
  41. HuynhP.T. JarolimekA.M. DayeS. The false-negative mammogram.Radiographics19981851137115410.1148/radiographics.18.5.97476129747612
     [Google Scholar]
  42. ParkS.H. HanK. Methodologic guide for evaluating clinical performance and effect of artificial intelligence technology for medical diagnosis and prediction.Radiology2018286380080910.1148/radiol.201717192029309734
     [Google Scholar]
  43. PeroneC.S. Cohen-AdadJ. Promises and limitations of deep learning for medical image segmentation.J. Med. Artif. Intell.2019211210.21037/jmai.2019.01.01
     [Google Scholar]
  44. Nussbaumer-StreitB. KleringsI. DobrescuA.I. PersadE. StevensA. GarrittyC. KamelC. AffengruberL. KingV.J. GartlehnerG. Excluding non-English publications from evidence-syntheses did not change conclusions: A meta-epidemiological study.J. Clin. Epidemiol.2020118425410.1016/j.jclinepi.2019.10.01131698064
     [Google Scholar]
  45. MorrisonA. PolisenaJ. HusereauD. MoultonK. ClarkM. FianderM. Mierzwinski-UrbanM. CliffordT. HuttonB. RabbD. The effect of English-language restriction on systematic review-based meta-analyses: A systematic review of empirical studies.Int. J. Technol. Assess. Health Care201228213814410.1017/S026646231200008622559755
     [Google Scholar]
  46. TufailA. RudisillC. EganC. KapetanakisV.V. Salas-VegaS. OwenC.G. LeeA. LouwV. AndersonJ. LiewG. BolterL. SrinivasS. NittalaM. SaddaS. TaylorP. RudnickaA.R. Automated diabetic retinopathy image assessment software: Diagnostic accuracy and cost-effectiveness compared with human graders.Ophthalmology2017124334335110.1016/j.ophtha.2016.11.01428024825
     [Google Scholar]
  47. HeydonP. EganC. BolterL. ChambersR. AndersonJ. AldingtonS. StrattonI.M. ScanlonP.H. WebsterL. MannS. du CheminA. OwenC.G. TufailA. RudnickaA.R. Prospective evaluation of an artificial intelligence-enabled algorithm for automated diabetic retinopathy screening of 30 000 patients.Br. J. Ophthalmol.2021105572372810.1136/bjophthalmol‑2020‑31659432606081
     [Google Scholar]
  48. SteyerbergE.W. MoonsK.G.M. van der WindtD.A. HaydenJ.A. PerelP. SchroterS. RileyR.D. HemingwayH. AltmanD.G. Prognosis Research Strategy (PROGRESS) 3: Prognostic model research.PLoS Med.2013102e100138110.1371/journal.pmed.100138123393430
     [Google Scholar]
  49. LiuX. FaesL. KaleA.U. WagnerS.K. FuD.J. BruynseelsA. MahendiranT. MoraesG. ShamdasM. KernC. LedsamJ.R. SchmidM.K. BalaskasK. TopolE.J. BachmannL.M. KeaneP.A. DennistonA.K. A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: A systematic review and meta-analysis.Lancet Digit. Health201916e271e29710.1016/S2589‑7500(19)30123‑233323251
     [Google Scholar]
  50. KimD.W. JangH.Y. KimK.W. ShinY. ParkS.H. Design characteristics of studies reporting the performance of artificial intelligence algorithms for diagnostic analysis of medical images: Results from recently published papers.Korean J. Radiol.201920340541010.3348/kjr.2019.002530799571
     [Google Scholar]
/content/journals/cmir/10.2174/1573405620666230417085624
Loading
Diagnostic Performance of Deep Learning in Screened Mammogram: Systematic Review
Curr. Med. Imaging 20, e170423215871 (2024); https://doi.org/10.2174/1573405620666230417085624
/content/journals/cmir/10.2174/1573405620666230417085624
/content/journals/cmir/10.2174/1573405620666230417085624
Loading

Data & Media loading...

Supplements

PRISMA checklist is available as supplementary material on the publisher’s website along with the published article.

file format download Download

  • Article Type:     Review Article
Keyword(s): Artificial intelligence (AI); Breast cancer; Computer-aided diagnosis system (CAD); Convolutional neural network (CNN); Deep learning; Mammogram

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test