A comparasion between artificial intelligence and radiologists in the field of interpretation of image exams
DOI:
https://doi.org/10.33448/rsd-v13i11.47411Keywords:
Radiology; Artificial Intelligence; Diagnosis.Abstract
In the field of imaging interpretation, radiologists combine clinical and technical expertise to achieve an accurate diagnosis. On the other hand, artificial intelligence (AI) can process and combine large volumes of data. In addition, it is questioned what would be the role of AI in the field of radiology when compared to radiologists. The present study seeks to make a comparison between artificial intelligence and radiologists in the field of interpretation of imaging exams by means of a literature review, which used the PubMed, SciELO and Fiocruz databases as research means. There are studies that prove that currently some artificial intelligence databases based on "deep learning" are still not sufficient to achieve diagnostic imaging results higher than 80% sensitivity, taking as a comparison the sensitivity of standard exams without artificial intelligence interpretation. The conclusion was that there are indications that AI can achieve levels of accuracy similar to or higher than those of radiologists under certain conditions. However, the joint participation between humans and artificial intelligence increases the sensitivity of imaging exams, as well as accuracy.
References
Araújo-Filho, J., et al. (2019). Inteligência artificial e diagnóstico por imagem: o futuro chegou? Revista da Sociedade de Cardiologia do Estado de São Paulo, 346-349.
Auffermann, W. F., Gozansky, E. K., & Tridandapani, S. (2019). Artificial Intelligence in Cardiothoracic Radiology. AJR American Journal of Roentgenology, 212(5), 997-1001. https://doi.org/10.2214/AJR.18.20771
Azevedo-Marques, P. M. (2001). Diagnóstico auxiliado por computador na radiologia. Radiologia Brasileira, 34, 285-293.
Baghdadi, L. R., et al. (2024). Patients’ attitudes toward the use of artificial intelligence as a diagnostic tool in radiology in Saudi Arabia: Cross-sectional study. JMIR Human Factors, 11(1), e53108.
Brejnebøl, M. W., et al. (2024). Interobserver agreement and performance of concurrent AI assistance for radiographic evaluation of knee osteoarthritis. Radiology, 312(1), e233341.
Bretas, E. A. S., et al. (2020). Estimating the productivity of radiologists in Brazil: The search for a benchmark. Radiologia Brasileira, 53(2), 73-80. https://doi.org/10.1590/0100-3984.2019.0081
Char, D. S., Shah, N. H., & Magnus, D. (2018). Implementing machine learning in health care: Addressing ethical challenges. New England Journal of Medicine, 378(11), 981-983.
Dembrower, K., et al. (2023). Artificial intelligence for breast cancer detection in screening mammography in Sweden: A prospective, population-based, paired-reader, non-inferiority study. The Lancet Digital Health, 5(10), e703-e711.
Dias, A., et al. (2024). The new era of artificial intelligence in neuroradiology: Current research and promising tools. Arquivos de Neuro-Psiquiatria, 82(6), 1-12.
Esteva, A., et al. (2017). Dermatologist-level classification of skin cancer with deep neural networks. Nature, 542(7639), 115-118.
Ghaffar Nia, N., Kaplanoglu, E., & Nasab, A. (2023). Evaluation of artificial intelligence techniques in disease diagnosis and prediction. Discover Artificial Intelligence, 3(1), 5.
Geras, K. J., et al. (2019). Artificial intelligence for mammography and digital breast tomosynthesis: Current concepts and future perspectives. Radiology, 293(2), 246-259.
Hinton, G., Vinyals, O., & Dean, J. (2015). Distilling the knowledge in a neural network. Stat, 1050, 9.
Johansson, J. V., & Engström, E. (2024). ‘Humans think outside the pixels’–Radiologists’ perceptions of using artificial intelligence for breast cancer detection in mammography screening in a clinical setting. Health Informatics Journal, 30(3), 14604582241275020.
Kelly, B. S., et al. (2022). Radiology artificial intelligence: A systematic review and evaluation of methods (RAISE). European Radiology, 32(11), 7998-8007.
Krittanawong, C., Kaplin, S., & Sharma, S. K. (2024). Artificial intelligence on interventional cardiology. In Artificial Intelligence in Clinical Practice (pp. 51-63). Academic Press.
Liew, C. (2018). The future of radiology augmented with artificial intelligence: A strategy for success. European Journal of Radiology, 102, 152-156.
Leitão, C. A., Salvador, G. L. O., Rabelo, L. M., & Escuissato, D. L. (2024). Performance of ChatGPT on questions from the Brazilian College of Radiology annual resident evaluation test. Radiologia Brasileira, 57, e20230083. https://doi.org/10.1590/0100-3984.2023.0083-en
Li, M. D., & Little, B. P. (2023). Appropriate reliance on artificial intelligence in radiology education. Journal of the American College of Radiology, 20(11), 1126-1130.
Litjens, G., et al. (2017). A survey on deep learning in medical image analysis. Medical Image Analysis, 42, 60-88.
Lobo, L. C. (2017). Inteligência artificial e medicina. Revista Brasileira de Educação Médica, 41, 185-193.
McKinney, S. M., et al. (2020). International evaluation of an AI system for breast cancer screening. Nature, 577(7788), 89-94.
Nana, M., et al. (2024). Accuracy of an artificial intelligence system for interval breast cancer detection at screening mammography. Radiology, 312(2), e232303.
Offiah, A. C. (2022). Current and emerging artificial intelligence applications for pediatric musculoskeletal radiology. Pediatric Radiology, 52(11), 2149-2158.
Park, S. H., et al. (2023). Methods for clinical evaluation of artificial intelligence algorithms for medical diagnosis. Radiology, 306(1), 20-31.
Rajpurkar, P., et al. (2017). Chexnet: Radiologist-level pneumonia detection on chest x-rays with deep learning. arXiv preprint arXiv:1711.05225.
Reyes, M., et al. (2020). On the interpretability of artificial intelligence in radiology: Challenges and opportunities. Radiology: Artificial Intelligence, 2(3), e190043.
Santos, M. K., et al. (2019). Artificial intelligence, machine learning, computer-aided diagnosis, and radiomics: Advances in imaging towards precision medicine. Radiologia Brasileira, 52(6), 387-396.
Pereira, A. S., et al. (2018). Metodologia da pesquisa científica. Santa Maria, RS: Ed. UAB/NTE/UFSM.
Pereira, R. F. B., et al. (2024). Accuracy of an artificial intelligence algorithm for detecting moderate-to-severe vertebral compression fractures on abdominal and thoracic computed tomography scans. Radiologia Brasileira, 57, e20230102.
Sogani, J., et al. (2020). Artificial intelligence in radiology: The ecosystem essential to improving patient care. Clinical Imaging, 59(1), A3-A6.
Topol, E. J. (2019). High-performance medicine: The convergence of human and artificial intelligence. Nature Medicine, 25(1), 44-56.
Veronezi, C. C. D., et al. (2011). Análise computacional para auxílio ao diagnóstico de osteoartrite de coluna lombar baseado em redes neurais artificiais. Revista Brasileira de Ortopedia, 46, 195-199.
Wang, D., et al. (2016). Deep learning for identifying metastatic breast cancer. arXiv preprint arXiv:1606.05718.
Yacoub, B., et al. (2022). Performance of an artificial intelligence-based platform against clinical radiology reports for the evaluation of noncontrast chest CT. Academic Radiology, 29, S108-S117.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Giovanna Bastos Prado de Melo; Igor de Bernardi Borges Araujo; Guilherme Pinheiro Guedes; Rodrigo Nascimento Alves; Márcio José Rosa Requeijo
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
1) Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
2) Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
3) Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
