AI & Data Significance 7/10

AI in Radiology: Deep Learning Methods for Quantitative Medical Image Analysis

This opinion article in Nature Reviews Cancer establishes a framework for understanding AI methods in radiological image analysis, from convolutional neural networks to variational autoencoders. The authors discuss how these tools transition radiology from qualitative visual assessment to quantitative, reproducible characterisation of disease, with a focus on oncology applications. The piece addresses both the promise and the implementation challenges of clinical AI deployment in diagnostic imaging.

The original study

Artificial intelligence in radiology.

Authors
Hosny A, Parmar C, Quackenbush J, Schwartz LH, Aerts HJWL
Journal
Nature reviews. Cancer
Type
Journal Article, Research Support, N.I.H., Extramural, Review
PMID
29777175
Read the original study →

Original abstract

Artificial intelligence (AI) algorithms, particularly deep learning, have demonstrated remarkable progress in image-recognition tasks. Methods ranging from convolutional neural networks to variational autoencoders have found myriad applications in the medical image analysis field, propelling it forward at a rapid pace. Historically, in radiology practice, trained physicians visually assessed medical images for the detection, characterization and monitoring of diseases. AI methods excel at automatically recognizing complex patterns in imaging data and providing quantitative, rather than qualitative, assessments of radiographic characteristics. In this Opinion article, we establish a general understanding of AI methods, particularly those pertaining to image-based tasks. We explore how these methods could impact multiple facets of radiology, with a general focus on applications in oncology, and demonstrate ways in which these methods are advancing the field. Finally, we discuss the challenges facing clinical implementation and provide our perspective on how the domain could be advanced.