Levels of Autonomous Radiology

TL;DR

This paper proposes a level-wise classification of AI automation in radiology, outlining challenges and solutions to facilitate structured adoption of AI technologies in medical imaging workflows.

Contribution

It introduces a novel framework categorizing AI automation levels in radiology, providing insights into challenges and strategies for implementation.

Findings

A structured classification of AI automation levels in radiology.

Identification of key challenges at each automation level.

Proposed solutions to facilitate AI adoption in radiology workflows.

Abstract

Radiology, being one of the younger disciplines of medicine with a history of just over a century, has witnessed tremendous technological advancements and has revolutionized the way we practice medicine today. In the last few decades, medical imaging modalities have generated seismic amounts of medical data. The development and adoption of Artificial Intelligence (AI) applications using this data will lead to the next phase of evolution in radiology. It will include automating laborious manual tasks such as annotations, report-generation, etc., along with the initial radiological assessment of cases to aid radiologists in their evaluation workflow. We propose a level-wise classification for the progression of automation in radiology, explaining AI assistance at each level with corresponding challenges and solutions. We hope that such discussions can help us address the challenges in a structured way and take the necessary steps to ensure the smooth adoption of new technologies in radiology.