Page 24 - Diagnostic Radiology - Interpreting the Risks Part Two_Neat

SVMIC Diagnostic Radiology: Interpreting the Risks

consumed by large automachinations? Will AI take the place of

physicians in diagnosing and treating patients?

Artificial intelligence in medicine may be characterized as the
scientific discipline pertaining to research studies, projects, and

applications that aim at supporting decision-based medical
tasks through knowledge and/or data-intensive, computer-

based solutions that ultimately support and improve the
performance of a human care provider.
8

This technology is swiftly advancing, and many systems that
can read and interpret multiple images rapidly are already in

the pipeline. Hundreds of images can be taken for an injury
or disease, but imaging and radiology are costly. Any system

that provides better diagnostics, reduction of humans reading,
or processing test results will not only lower costs, but also

benefit patients and physicians. Artificial intelligence algorithms,
particularly deep learning, have demonstrated remarkable

progress in image-recognition tasks. Methods ranging from
convolutional neural networks to variational autoencoders have

found myriad applications in the medical image analysis field,
propelling AI forward at a rapid pace. Historically, in radiology

practice, trained physicians have visually assessed medical
images for the detection, characterization, and monitoring

of diseases. AI methods excel at automatically recognizing
complex patterns in imaging data and providing quantitative,

rather than qualitative, assessments of radiographic
characteristics.
9

There is no doubt that the practice of radiology will change

because of AI, but radiologists will continue to exist because

8 www.journals.elsevier.com/artificial-intelligence-in-medicine
9 https://www.nature.com/articles/s41568-018-0016-5

Page 24