POTENSI KECERDASAN BUATAN DALAM PENINGKATAN AKURASI PEMBACAAN HASIL MAMOGRAFI: TINJAUAN SISTEMATIS DAN META-ANALISIS

Authors

  • AL MUNAWIR Laboratorium Patologi Anatomi FK Universitas Jember
  • Sekar Arum Srigati Fakultas Kedokteran, Universitas Jember
  • Pipiet Wulandari Departemen Fisiologi, Fakultas Kedokteran, Universitas Jember

DOI:

https://doi.org/10.23887/gm.v3i1.55575

Keywords:

AI, deep learning, kanker payudara, mamografi

Abstract

ABSTRAK

Kanker payudara merupakan suatu penyakit keganasan oleh karena proliferasi tak terkontrol dari sel-sel di payudara. Jumlah morbiditas dan mortalitas yang cukup tinggi menjadikan upaya skrining dan deteksi dini kanker payudara penting untuk dilakukan. Mamografi merupakan modalitas utama skrining kanker payudara yang diinterpretasikan oleh ahli radiologi berdasarkan persepsi visual. Namun, peningkatan permintaan skrining selaras dengan peningkatan beban kerja yang dapat mempengaruhi efektivitas dan menyebabkan kesalahan interpretasi hasil mamografi. Perkembangan teknologi, salah satunya kecerdasan buatan (AI) dengan algoritma deep learning diklaim memiliki kinerja yang lebih baik daripada kinerja rata-rata ahli radiologi. Tujuan penelitian ini adalah untuk mengkaji potensi AI dalam meningkatkan akurasi pembacaan hasil mamografi. Penelitian ini merupakan tinjauan sistematis dan meta-analisis menggunakan artikel dengan desain penelitian retrospektif dari lima basis data sesuai panduan Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). Risiko bias dikaji menggunakan Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2). Total terdapat 12 artikel terinklusi yang dianalisis berdasarkan penggunaan tunggal AI, ahli radiologi, dan kombinasi ahli radiologi-AI. Hasil meta-analisis penggunaan tunggal AI menunjukkan hasil yang lebih tinggi dibandingkan lainnya pada sensitivitas (88% (95% CI 82%-92%)), spesifisitas (89% (95% CI 81%-93%)), dan AUC (0,94 (95% CI 0,92-0,96)). Penelitian ini menunjukkan adanya potensi yang menjanjikan dari kecerdasan buatan (AI) untuk meningkatkan akurasi pembacaan hasil mamografi.

Kata Kunci: AI, deep learning, kanker payudara, mamografi

ABSTRACT

Breast cancer is a malignancy caused by the uncontrollable proliferation of breast cells. The high morbidity and mortality make an essential excuse for screening and early detection of breast cancer. Mammography is the main modality in the examination of breast cancer screening which is interpreted by radiologists based on visual perception. The increase in screening demand leads to workload which affects the effectiveness and misinterpretation of mammography results. These years, technological development such as artificial intelligence (AI) in its deep learning algorithm claimed to have better performance than the average performance of radiologists. Hence, this study aimed to investigate the potency of AI to enhance the accuracy of a mammography reading. This systematic review and meta-analysis conducted retrospective articles from five electronic databases based on Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). The risk of biases was assessed from each study using Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2). Twelve articles were included and analyzed for the AI stand-alone, radiologists stand-alone, and combination of radiologists with AI. The current study showed the higher results of AI stand-alone compared to others in its sensitivity (88% (95% CI 82%-92%)), specificity (89% (95% CI 81%-93%)), and area under the curves (0,94 (95% CI 0,92-0,96)). In conclusion, this systematic review and meta-analysis provide valuable evidence about AI's promising potency to enhance mammography reading accuracy.

Keywords: AI, breast cancer, deep learning, mammography

References

DAFTAR PUSTAKA

Centers for Disease Control and Prevention (CDC). What is breast cancer? Centers for Disease Control and Prevention. 2021.

Sun YS, Zhao Z, Yang ZN, Xu F, Lu HJ, Zhu ZY, et al. Risk factors and preventions of breast cancer. Int J Biol Sci. 2017;13(11):1387–97.

World Health Organization (WHO). Breast cancer [Internet]. World Health Organizations. 2021. Available from: https://www.who.int/news-room/fact-sheets/detail/breast%02cancer

Globocan. Indonesia fact sheets: Globocan 2020 [Internet]. International Agency for Research on Cancer. 2021. Available from: https://gco.iarc.fr/today/data/factsheets/populations/360-%0Aindonesia-fact-sheets.pdf

Shiryazdi SM, Kholasehzadeh G, Neamatzadeh H, Kargar S. Health beliefs and breast cancer screening behaviors among Iranian female health workers. Asian Pacific J Cancer Prev. 2014;15(22):9817–22.

Dewi GAT, Hendrati LY. Analisis risiko kanker payudara berdasar riwayat pemakaian kontrasepsi hormonal dan usia. J Berk Epidemiol. 2015;3(1):12–23.

McKinney SM, Sieniek M, Godbole V, Godwin J, Antropova N, Ashrafian H, et al. International evaluation of an AI system for breast cancer screening. Nature [Internet]. 2020;577(7788):89–94. Available from: http://dx.doi.org/10.1038/s41586-019-1799-6

Schaffter T, Buist DSM, Lee CI, Nikulin Y, Ribli D, Guan Y. Evaluation of Combined Artificial Intelligence and Radiologist Assessment to Interpret Screening Mammograms. JAMA Netw Open. 2020;3(3):1–15.

Zhou L, Wu X, Huang S, Wu G, Ye H, Radiology QW-. Detection of Breast Cancer with Mammography: Effect of an Artificial Intelligence Support System. Radiology [Internet]. 2020;294(1):19–28. Available from: https://doi.org/10.1148/radiol.2019190372

Rodríguez-Ruiz A, Krupinski E, Mordang JJ, Schilling K, Heywang-Köbrunner SH, Sechopoulos I, et al. Detection of breast cancer with mammography: Effect of an artificial intelligence support system. Radiology. 2019;290(3):305–14.

Lotter W, Diab AR, Haslam B, Kim JG, Grisot G, Wu E, et al. Robust breast cancer detection in mammography and digital breast tomosynthesis using an annotation-efficient deep learning approach. Nat Med [Internet]. 2021;27(February):244–9. Available from: http://dx.doi.org/10.1038/s41591-020-01174-9

Freeman K, Geppert J, Stinton C, Todkill D, Johnson S, Clarke A. Use of artificial intelligence for image analysis in breast cancer screening programs : a systematic review of test accuracy. BMJ Open. 2021;374(1872):1–15.

Bao C, Shen J, Zhang Y, Zhang Y, Wei W, Wang Z, et al. Evaluation of an artificial intelligence support system for breast cancer screening in Chinese people based on a mammogram. Cancer Med. 2022;

Kim HE, Kim HH, Han BK, Kim KH, Han K, Nam H, et al. Changes in cancer detection and false-positive recall in mammography using artificial intelligence: a retrospective, multi-reader study. Lancet Digit Heal [Internet]. 2020;2(3):e138–48. Available from: http://dx.doi.org/10.1016/S2589-7500(20)30003-0

Lee JH, Kim KH, Lee EH, Ahn JS, Ryu JK, Park YM, et al. Improving the Performance of Radiologists Using Artificial Intelligence-Based Detection Support Software for Mammography: A Multi-Reader Study. Korean J Radiol. 2022;23(5):505–16.

Leibig C, Brehmer M, Bunk S, Byng D, Pinker K, Umutlu L. Combining the strengths of radiologists and AI for breast cancer screening: a retrospective analysis. Lancet Digit Heal [Internet]. 2022;4(7):e507–19. Available from: http://dx.doi.org/10.1016/S2589-7500(22)00070-X

Park GE, Kang BJ, Kim SH, Lee J. Retrospective Review of Missed Cancer Detection and Its Mammography Findings with Artificial-Intelligence-Based, Computer-Aided Diagnosis. Diagnostics. 2022;12(2).

Salim M, Wåhlin E, Dembrower K, Azavedo E, Foukakis T, Liu Y, et al. External Evaluation of 3 Commercial Artificial Intelligence Algorithms for Independent Assessment of Screening Mammograms. JAMA Oncol. 2020;6(10):1581–8.

Sasaki M, Tozaki M, Rodríguez-Ruiz A, Yotsumoto D, Ichiki Y, Terawaki A, et al. Artificial intelligence for breast cancer detection in mammography: experience of use of the ScreenPoint Medical Transpara system in 310 Japanese women. Breast Cancer [Internet]. 2020;27(4):642–51. Available from: https://doi.org/10.1007/s12282-020-01061-8

Sharma N, Ng AY, James JJ, Khara G, Ambrozay E, Austin CC, et al. Retrospective large-scale evaluation of an AI system as an independent reader for double reading in breast cancer screening. medRxiv [Internet]. 2022;2021.02.26.21252537. Available from: https://www.medrxiv.org/content/10.1101/2021.02.26.21252537v2%0Ahttps://www.medrxiv.org/content/10.1101/2021.02.26.21252537v2.abstract

Yala A, Schuster T, Miles R, Barzilay R, Lehman C. A deep learning model to triage screening mammograms: A simulation study. Radiology. 2019;293(1):38–46.

Liu J, Lei J, Ou Y, Zhao y, Tuo X, Zhang B, et al. Mammography diagnosis of breast cancer screening through machine learning: a systematic review and meta-analysis. Clin Exp Med. 2022;

Pacilè S, Lopez J, Chone P, Bertinotti T, Grouin JM, Fillard P. Improving breast cancer detection accuracy of mammography with the concurrent use of an artificial intelligence tool. Radiol Artif Intell. 2020;2(6):1–9.

Downloads

Published

2023-05-12

Issue

Section

Articles