Page 108 - ARNM-3-2

Advances in Radiotherapy
& Nuclear Medicine Artificial intelligence in radiotherapy

Despite the ethical and legal dilemmas surrounding 4. Huynh E, Hosny A, Guthier C, et al. Artificial intelligence in
AI usage, present advancements suggest that AI will radiation oncology. Nat Rev Clin Oncol. 2020;17(12):771-781.
coexist with existing systems or even replace some of doi: 10.1038/s41571-020-0417-8
them. Furthermore, in the face of such extensive big data,
not utilizing AI may be both scientifically and ethically 5. Yakar M, Etiz D, Metintas M, Ak G, Celik O. Prediction
of radiation pneumonitis with machine learning in stage
questionable.
III lung cancer: A pilot study. Technol Cancer Res Treat.
The success of AI systems depends on large, accurate, 2021;20:15330338211016373.
and diverse datasets. Such datasets can help prevent doi: 10.1177/15330338211016373
algorithmic biases and enhance generalizability. To achieve
this, internationally standardized and secured datasets 6. Akcay M, Etiz D, Celik O, Ozen A. Evaluation of acute
hematological toxicity by machine learning in gynecologic
should be established, accompanied with measures to cancers using postoperative radiotherapy. Indian J Cancer.
ensure data privacy.
2022;59(2):178-186.
For AI algorithms to transition into clinical practice, doi: 10.4103/ijc.IJC_666_19
multicenter validation studies must be conducted. It is
essential to demonstrate that model performance yields 7. Akcay M, Etiz D, Celik O, Ozen A. Evaluation of prognosis
consistent results across diverse patient populations. In in nasopharyngeal cancer using machine learning. Technol
Cancer Res Treat. 2020;19:1533033820909829.
addition, to enable the effective and accurate use of AI,
training programs should be organized for clinicians and doi: 10.1177/1533033820909829
professionals working in healthcare technologies. 8. Akcay M, Etiz D, Celik O. Prediction of survival and
Ethical and legal guidelines must be established recurrence patterns by machine learning in gastric cancer
internationally to define AI’s role in clinical decision- cases undergoing radiation therapy and chemotherapy. Adv
making. These guidelines should delineate AI’s boundaries Radiat Oncol. 2020;5(6):1179-1187.
as a tool and ensure that these technologies operate under doi: 10.1016/j.adro.2020.07.007
human oversight while prioritizing ethical principles, such 9. Janssen S, El Shafie RA, Ruder AM, et al. Mobile applications
as informed patient consent. in radiation oncology-current choices and future potentials.
Although the use of AI in radiation oncology is still in Strahlenther Onkol. 2023;199(4):337-349.
its early stages, implementing the above recommendations doi: 10.1007/s00066-023-02048-y
will bring these technologies one step closer to a reliable, 10. Bibault JE, Giraud P, Burgun A. Big Data and machine
effective, and widespread clinical application. This progress learning in radiation oncology: State of the art and future
has the potential to transform healthcare by improving prospects. Cancer Lett. 2016;382(1):110-117.
patient outcomes and increasing the efficiency of medical
services. doi: 10.1016/j.canlet.2016.05.033
11. Bibault JE, Giraud P. Deep learning for automated
Conflict of interest segmentation in radiotherapy: A narrative review. Br J
Radiol. 2024;97(1153):13-20.
The author declares that she has no conflict of interest and
has no competing interests. doi: 10.1093/bjr/tqad018
12. Samarasinghe G, Jameson M, Vinod S, et al. Deep learning
References for segmentation in radiation therapy planning: A review.
1. Lambin P, Rios-Velazquez E, Leijenaar R, et al. Radiomics: J Med Imaging Radiat Oncol. 2021;65(5):578-595.
Extracting more information from medical images using doi: 10.1111/1754-9485.13286
advanced feature analysis. Eur J Cancer. 2012;48(4):441-446.
13. Liu X, Chen X, Chen D, et al. A patient-specific auto-
doi: 10.1016/j.ejca.2011.11.036 planning method for MRI-guided adaptive radiotherapy in
2. Jiang F, Jiang Y, Zhi H, et al. Artificial intelligence in prostate cancer. Radiother Oncol. 2024;200:110525.
healthcare: Past, present and future. Stroke Vasc Neurol. doi: 10.1016/j.radonc.2024.110525
2017;2(4):230-243.
14. Zeverino M, Piccolo C, Wuethrich D, et al. Clinical
doi: 10.1136/svn-2017-000101
implementation of deep learning-based automated left
3. Yakar M, Etiz D. Artificial intelligence in radiation oncology. breast simultaneous integrated boost radiotherapy treatment
Artif Intell Med Imaging. 2021;2(2):13-31. planning. Phys Imaging Radiat Oncol. 2023;28:100492.
doi: 10.35711/aimi.v2.i2.13 doi: 10.1016/j.phro.2023.100492

Volume 3 Issue 2 (2025) 100 doi: 10.36922/arnm.8429