Elsevier

Physica Medica

Volume 83, March 2021, Pages 9-24
Physica Medica

Review paper
AI applications to medical images: From machine learning to deep learning

https://doi.org/10.1016/j.ejmp.2021.02.006Get rights and content

Highlights

  • Strategies how to develop AI applications as clinical decision support systems are provided.

  • We focus on differences between radiomic machine learning and deep learning application domains.

  • Pros and cons, recommendations and references to software tools are provided.

Abstract

Purpose

Artificial intelligence (AI) models are playing an increasing role in biomedical research and healthcare services. This review focuses on challenges points to be clarified about how to develop AI applications as clinical decision support systems in the real-world context.

Methods

A narrative review has been performed including a critical assessment of articles published between 1989 and 2021 that guided challenging sections.

Results

We first illustrate the architectural characteristics of machine learning (ML)/radiomics and deep learning (DL) approaches. For ML/radiomics, the phases of feature selection and of training, validation, and testing are described. DL models are presented as multi-layered artificial/convolutional neural networks, allowing us to directly process images. The data curation section includes technical steps such as image labelling, image annotation (with segmentation as a crucial step in radiomics), data harmonization (enabling compensation for differences in imaging protocols that typically generate noise in non-AI imaging studies) and federated learning. Thereafter, we dedicate specific sections to: sample size calculation, considering multiple testing in AI approaches; procedures for data augmentation to work with limited and unbalanced datasets; and the interpretability of AI models (the so-called black box issue). Pros and cons for choosing ML versus DL to implement AI applications to medical imaging are finally presented in a synoptic way.

Conclusions

Biomedicine and healthcare systems are one of the most important fields for AI applications and medical imaging is probably the most suitable and promising domain. Clarification of specific challenging points facilitates the development of such systems and their translation to clinical practice.

Keywords

Artificial intelligence
Deep learning
Machine learning
Medical imaging
Radiomics

Cited by (0)

1

Isabella Castiglioni, Leonardo Rundo, and Marina Codari equally contributed to this paper.

View Abstract