Integration of artificial intelligence, machine learning, and deep learning into clinically routine molecular imaging

Geoffrey Currie, Eric Rohren

Research output: Book chapter/Published conference paperChapter (peer-reviewed)peer-review

Abstract

Assimilation of artificial intelligence (AI) and machine learning (ML) into clinical practice is a potential driver for reengineering precision nuclear medicine and molecular imaging capabilities. Across members of the nuclear medicine community there is a spectrum of opinions and positions in relation to the role and capability of AI now, and in the future. While the applications of AI, ML, and deep learning (DL) in nuclear medicine and molecular imaging are growing quickly; there remain a number of barriers. The opportunities and applications emerging in this space may transform the molecular imaging landscape. Despite concerns with respect to the impact of AI on the workforce, deep assimilation of an AI program in nuclear medicine and molecular imaging is likely to expand the workforce while improving clinical outcomes. This chapter expressly considers the assimilation of AI, ML, and DL into routine clinical practice in molecular imaging but excludes the wealth of applications that enrich research practice.
Original languageEnglish
Title of host publicationArtificial intelligence/Machine learning in nuclear medicine and hybrid imaging
EditorsPatrick Veit-Haibach, Ken Herrmann
Place of PublicationCham, Switzerland
PublisherSpringer
Chapter7
Pages87-108
Number of pages22
Edition1st
ISBN (Electronic)9783031001192
ISBN (Print)9783031001185
DOIs
Publication statusPublished - 2022

Fingerprint

Dive into the research topics of 'Integration of artificial intelligence, machine learning, and deep learning into clinically routine molecular imaging'. Together they form a unique fingerprint.

Cite this