AI in Radiation Treatment Planning.
Purpose To explore the efficacy and limitations of artificial intelligence (AI) in radiation treatment planning. Methods Multiple electronic databases were searched to find articles published in 2016 or later that were related to the use of AI in radiation treatment planning. Results The literature...
| Publicado en: | Radiation Therapist Vol. 31; no. 1; pp. 9 - 15 |
|---|---|
| Autor principal: | |
| Formato: | glossary pictorial research systematic review tables/charts Journal Article |
| Publicado: |
American Society of Radiologic Technologists
Spring2022
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=155735931&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 155735931 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 10841911 GTK jtl: Radiation Therapist issn: 10841911 maglogo: N pubinfo: dt: Spring2022 vid: 31 iid: 1 pid: 7052 pub: American Society of Radiologic Technologists place: Alburquerque, New Mexico artinfo: ui: 155735931 155735931 155735931 155735931 ppf: 9 ppct: 6 formats: fmt: @attributes: type: P tig: atl: AI in Radiation Treatment Planning. aug: au: Alam-Siddiqui, Fawad affil: First-year medical student, University of Pikeville - Kentucky College of Osteopathic Medicine sug: subj: Artificial Intelligence Utilization Radiotherapy Health and Welfare Planning Human Systematic Review Quality Assurance Radiation Dosage Machine Learning Deep Learning Workflow Radiation Oncology Artificial Intelligence Ethical Issues Artificial Intelligence Economics Image Processing, Computer Assisted PubMed CINAHL Database ab: Purpose To explore the efficacy and limitations of artificial intelligence (AI) in radiation treatment planning. Methods Multiple electronic databases were searched to find articles published in 2016 or later that were related to the use of AI in radiation treatment planning. Results The literature shows that the use of AI has demonstrated multiple benefits in radiation treatment planning, particularly in efficiency and quality assurance, image segmentation, and dose optimization. Limitations to AI use also were identified such as initial cost, limited clinical testing, and ethical concerns. Discussion AI and its subsets machine learning and deep learning (DL) are used to improve imaging efficiency and streamline workflow in radiation oncology; however, costs, limited clinical testing and ethical dilemmas are limiting factors that prevent widespread clinical adoption. Costs are expected to decrease as technology progresses, and limited clinical testing can be solved with time, but distrust in neural networks that allow DL predictive power could prove to be a barrier to acceptance. Conclusion The benefits of AI to workflow efficiency, image segmentation, and dose optimization are evident; however, limiting factors such as cost, limited clinical testing, and ethical dilemmas must be addressed before widespread clinical adoption is feasible. pubtype: Academic Journal doctype: glossary pictorial research systematic review tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|