Machine learning and modeling: Data, validation, communication challenges
Машинное обучение и моделирование: проблемы данных, валидации и коммуникации
2018-08-24
SCID: 54.1/mu9c8rzq
Discuss with AI
machine learningorgan segmentationradiation oncologytransparent reportingtreatment response modeling
Figures from the paper
Abstract (AI)
With the era of big data, the utilization of machine learning algorithms in radiation oncology is rapidly growing with applications including: treatment response modeling, treatment planning, contouring, organ segmentation, image-guidance, motion tracking, quality assurance, and more. Despite this interest, practical clinical implementation of machine learning as part of the day-to-day clinical operations is still lagging. The aim of this white paper is to further promote progress in this new field of machine learning in radiation oncology by highlighting its untapped advantages and potentials for clinical advancement, while also presenting current challenges and open questions for future research. The targeted audience of this paper includes newcomers as well as practitioners in the field of medical physics/radiation oncology. The paper also provides general recommendations to avoid common pitfalls when applying these powerful data analytic tools to medical physics and radiation oncology problems and suggests some guidelines for transparent and informative reporting of machine learning results.
Key Findings
1
Despite growing research interest, practical clinical implementation of machine learning in routine radiation oncology operations remains limited.
2
It provides recommendations for avoiding common methodological pitfalls when applying machine learning to medical physics and radiation oncology.
3
Machine learning applications in radiation oncology are expanding across response modeling, treatment planning, contouring, segmentation, image guidance, motion tracking, and quality assurance.
4
The paper suggests guidelines for transparent and informative reporting of machine learning results and targets both newcomers and experienced practitioners.
5
The white paper identifies untapped opportunities and open research questions for advancing machine learning in radiation oncology.
Research Object
Machine learning applications in radiation oncology and medical physics clinical operations
Research Subject
Clinical implementation challenges, validation, data practices, communication, reporting, and potential benefits of machine learning for treatment response modeling, planning, contouring, segmentation, image guidance, motion tracking, and quality assurance
Publication Details
Publication Date
2018-08-24
Journal
Publisher
ISSN
Cited by
104
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest