Choosing the right artificial intelligence solutions for your radiology department: key factors to consider

Abstract

The rapid evolution of artificial intelligence (AI), particularly in deep learning, has significantly impacted radiology, introducing an array of AI solutions for interpretative tasks. This paper provides radiology departments with a practical guide for selecting and integrating AI solutions, focusing on interpretative tasks that require the active involvement of radiologists. Our approach is not to list available applications or review scientific evidence, as this information is readily available in previous studies; instead, we concentrate on the essential factors radiology departments must consider when choosing AI solutions. These factors include clinical relevance, performance and validation, implementation and integration, clinical usability, costs and return on investment, and regulations, security, and privacy. We illustrate each factor with hypothetical scenarios to provide a clearer understanding and practical relevance. Through our experience and literature review, we provide insights and a practical roadmap for radiologists to navigate the complex landscape of AI in radiology. We aim to assist in making informed decisions that enhance diagnostic precision, improve patient outcomes, and streamline workflows, thus contributing to the advancement of radiological practices and patient care.

Keywords: Radiology; artificial intelligence; clinical decision-making; computer-assisted healthcare economics and organizations; data security in healthcare; regulatory compliance in medicine.

Figure 1.

The number of (a) CE-marked and (b) FDA-approved commercially available radiology AI software per subspecialty. The most common AI software is for neuro followed by chest imaging for both CE-marked and FDA-approved products. CE, Conformité Européenne; FDA, Food and Drug Administration; AI, artificial intelligence.

Figure 2.

The number of FDA-approved commercially available radiology AI software each year. There has been an increasing trend in the number of commercially available applications, with a steep increase observed after 2015. However, there appears to be a stabilization after 2022 and even a slight decrease in 2023 compared with 2022. FDA, Food and Drug Administration; AI, artificial intelligence.

Figure 3

The roadmap for choosing the right AI solutions for radiology departments, addressing key factors. First, radiologists must critically evaluate the clinical relevance of AI products for their department’s specific needs, covering the scope of the product, its features and outputs, intended end-users, and potential clinical benefits. Then, they should thoroughly evaluate performance and validation, implementation and integration, clinical usability, cost and return on investment, and regulations, security, and privacy. AI, artificial intelligence.