Intelligent imaging: Developing a machine learning project

Research output: Contribution to journalArticlepeer-review

Abstract

Artificial intelligence (AI) has rapidly progressed with exciting opportunities that drive enthusiasm for significant projects. A sensible and sustainable approach would be to start building an AI footprint with smaller, machine learning (ML) based initiatives using artificial neural networks (ANN) before progressing to more complex deep learning (DL) approaches using convolutional neural networks (CNN). A number of strategies and examples of entry level projects are outlined, including mock potential projects using CNN to progress toward. The examples provide a narrow snapshot of potential applications designed to inspire readers to think outside the box at problem solving using AI and ML. The simple and resource light ML approaches are ideal for problem solving, accessible starting points for a developing institutional AI program, and provide solutions that can have a significant and immediate impact on practice. A logical approach would be to use ML to examine the problem and identify amongst the broader ML projects which problems are most likely to benefit from a DL approach.
Original languageEnglish
Pages (from-to)44-48
Number of pages15
JournalJournal of Nuclear Medicine Technology
Volume49
Issue number1
Early online date24 Dec 2020
DOIs
Publication statusPublished - Mar 2021

Fingerprint Dive into the research topics of 'Intelligent imaging: Developing a machine learning project'. Together they form a unique fingerprint.

Cite this