Artificial Intelligence in the Era of Clinical Imaging: How Training Models Could Be a Challenge for New Upcoming Physicians in Radiology – Learner Needs of Radiology Residents Regarding AI

Artificial Intelligence in the Era of Clinical Imaging: How Training Models Could Be a Challenge for New Upcoming Physicians in Radiology – Learner Needs of Radiology Residents Regarding AI

Georgios Kolostoumpis, Olga Vasila-Vakhnina, Nikolaos Vasilas
DOI: 10.4018/978-1-7998-8871-0.ch015
OnDemand:
(Individual Chapters)
Available
$33.75
List Price: $37.50
10% Discount:-$3.75
TOTAL SAVINGS: $3.75

Abstract

Artificial intelligence technology is a marked change in the imaging field. Clinical imaging and operations applications are metamorphosed as new methods and tools, and algorithms are being brought into radiology's daily practice. Looking forward, further attempts could prove quite beneficial to the literature. Modern technologies like AI technology, particularly deep learning, clearly show evidence of development. AI technology can be exceptionally good at identifying. The authors outline how to interact with and methods to effectively, safely, and efficiency use these tools and technologies.
Chapter Preview
Top

Strengthening The Learning Environment In Radiology

Highlighting and reviewing present teaching - centred methods and achievements as presented by authors (Sivarajah, R. T., Curci, N. E., Johnson, E. M., Lam, D. L., Lee, J. T., & Richardson, M. L., 2019), stating and justifying the acceptability of traditional didactic and effective methods of teaching, based on the recommendations of radiologists take part in many types of activities such as instructors and learners. We are focused on resident radiology performance, not instructor performance, and on behaviour, not subject matter; there should be only one learning outcome per objectives.

Despite the fact, that residents radiologists learn more and retain their knowledge longer if they acquire it in an active rather than a passive manner. However, flexibility is a great value for the optimal asset of knowledge, so in a way that deliberately avoids harm designed learning experiences. The greatest challenges in the radiology learning environment involve the engagement and contribution of the instructors, or faculty members, who must practice and innovative while teaching and mentoring the next generation.

The most well-known findings underlined by author (Collins, J., 2007), based on a learning expectations and experiences placed on that activity. At this point means that we are increasing the utilization of imaging examinations in clinical practice leads to increasing complexity and volumes of cases, requiring ever more knowledge, focus and time for interpretation. Merging healthcare system also tax existing workflow, as these systems may complicate already stretched systems.

In spite of the fact that adding to these stressors are radiologist-specific metrics such as turnaround times, peer review reporting and discordance rates. We are of the opinion that radiologists in a daily duty during the actual practice are affected not only by the vast amounts of imaging data they must review on a daily basis, as mentioned by authors (Collado-Mesa, F., Alvarez, E., & Arheart, K., 2018), have been clearly identified the time it takes them to search and find contextual clinical information regarding the imaging studies they read. Many interrelated challenges affect the radiology work environment, that means further evidence for every radiologist in worldwide view an every 3 second of every working day for the entire year.

Key Terms in this Chapter

ML: Machine learning.

EHR: Electronic health record.

Complete Chapter List

Search this Book:
Reset