Applications and limitations of machine learning in radiation oncology

Abstract

Machine learning approaches to problem-solving are growing rapidly within healthcare, and radiation oncology is no exception. With the burgeoning interest in machine learning comes the significant risk of misaligned expectations as to what it can and cannot accomplish. This paper evaluates the role of machine learning and the problems it solves within the context of current clinical challenges in radiation oncology. The role of learning algorithms within the workflow for external beam radiation therapy are surveyed, considering simulation imaging, multimodal fusion, image segmentation, treatment planning, quality assurance, and treatment delivery and adaptation. For each aspect, the clinical challenges faced, the learning algorithms proposed, and the successes and limitations of various approaches are analyzed. It is observed that machine learning has largely thrived on reproducibly mimicking conventional human-driven solutions with more efficiency and consistency. On the other hand, since algorithms are generally trained using expert opinion as ground truth, machine learning is of limited utility where problems or ground truths are not well-defined, or if suitable measures of correctness are not available. As a result, machines may excel at replicating, automating and standardizing human behaviour on manual chores, meanwhile the conceptual clinical challenges relating to definition, evaluation, and judgement remain in the realm of human intelligence and insight.

Figure 1.

Number of search results by year for publications relating to “Radiation Oncology” and “Artificial Intelligence” or “Machine Learning”. Results from Google Scholar may represent a wider cross-section of publications than from PubMed. AI, Artificial Intelligence;ML, machine learning.

Figure 2.

Schematic overview of the external beam radiation therapy workflow. Conceptually, we split this into (1) diagnosis and decision support, (2) treatment planning, and (3) treatment delivery. OAR, organ at risk.

Figure 3.

Example of unedited segmentation of OARs. The use of automatic OAR segmentation based on deep learning methods has demonstrated time savings in the clinical workflow. OAR,organ at risk.