Learning objectives
Artificial intelligence in recent years has demonstrated extraordinary progress in image-recognition tasks. Machine learning is a subfield of artificial intelligence that utilises mathematical algorithms and programs that allows computers to learn automatically with minimal or no human intervention. There is both considerable excitement and anxiety concerning the impact of machine learning on radiological practice. Traditionally, physicians are trained to visually and qualitatively assess medical images for detection and characterisation of disease. However, machine learning can recognise complex patterns in imaging data and provide a quantitative...
Background
A literature review was conducted to investigate the role of machine learning in radiology. Key search terms were used in PubMed, MEDLINE and CINAHL Plus to identify relevant studies and reviews. Images were compiled to illustrate findings.
Imaging findings OR Procedure details
The key findings of this review indicate that advances in machine learning techniques have the potential to improve all aspects of the radiology workflow. This includes improvements in the accuracy, safety, efficiency and productivity of clinical decision making, as well as providing better patient care through improved detection and interpretation of radiological findings and reporting.
For instance, machine learning is capable of extracting regions of interest on the basis of expert knowledge in cancer characterisation such as tumour volume, shape, texture, intensity and location. The...
Conclusion
The radiological community has a strong history of embracing new technology, and machine learning should be no exception. This exhibit provides health professionals and students with an educational and pictorial depiction of the evolving role of machine learning in radiology. In particular, this exhibit highlights the ability of machine learning to recognise complex patterns in medical imaging data and provide a quantitative (as opposed to traditional qualitative) interpretation and clinical diagnosis of radiographic characteristics.
References
Beregi JP, Zins M, Masson JP, Cart P, Bartoli JM, Silberman B, et al. Radiology and artificial intelligence: An opportunity for our specialty. Diagn Interv Imaging. 2018;99(11):677-8.
Choy G, Khalilzadeh O, Michalski M, Do S, Samir AE, Pianykh OS, et al. Current Applications and Future Impact of Machine Learning in Radiology. Radiology. 2018;288(2):318-28.
Hosny A, Parmar C, Quackenbush J, Schwartz LH, Aerts HJWL. Artificial intelligence in radiology. Nat Rev Cancer. 2018;18(8):500-10.
Kahn CE. From Images to Actions: Opportunities for Artificial Intelligence in Radiology. Radiology. 2017;285(3):719-20....