Page 29 - ARNM-2-2

Advances in Radiotherapy &

Nuclear Medicine

PERSPECTIVE ARTICLE
Optimizing conventional radiotherapy: A

synergistic approach with generative artificial
intelligence and computational sustainability

1
João Melo e Castro * and José Neves 1,2
1 Artificial Intelligence and Health Research Unit, Polytechnic Health Higher Institute of the North/
Advanced Polytechnic and University Cooperative, Famalicão, Portugal
2 Department of information and Technology, University of Minho, Braga, Minho, Portugal & Artificial
Intelligence and Health Research Unit, Polytechnic Health Higher Institute of the North/ Advanced
Polytechnic and University Cooperative, Famalicão, Portugal

Abstract

Conventional radiotherapy (CR) stands at a critical juncture, poised for transformation
through the integration of cutting-edge technologies. This article explores the
transformative potential of integrating generative artificial intelligence (GAI)
and computational sustainability (CS) principles into CR. The convergence of GAI
techniques, such as generative adversarial networks, with CS offers novel approaches
for optimizing treatment planning, enhancing precision, and ensuring long-term
sustainability in radiotherapy practices. We delve deeper into the personalized
medicine strategy facilitated by generative models, taking into account patient-
specific anatomical variations and dose optimization. The article highlights the
role of GAI in adaptive radiotherapy, enabling real-time adjustments to treatment
plans based on dynamic changes in patient anatomy. CS principles contribute to
*Corresponding author: resource optimization and energy efficiency, addressing the environmental impact
João Melo e Castro
(Jag.melo@ensp.unl.pt) of CR practices. The synergy between GAI and CS fosters innovations in treatment
techniques, data-driven decision-making, and ethical considerations, promoting
Citation: Melo e Castro J, equitable access and minimizing disparities. This article provides a comprehensive
Neves J. Optimizing conventional
radiotherapy: A synergistic overview of the potential benefits and challenges associated with the integration
approach with generative artificial of GAI and CS in CR, shaping the future of precision, efficiency, and sustainable
intelligence and computational radiotherapy practices.
sustainability. Adv Radiother Nucl
Med. 2024;2(2):3523.
doi: 10.36922/arnm.3523
Keywords: Generative artificial intelligence; Computational sustainability; Conventional
Received: April 29, 2024 radiotherapy; Treatment planning optimization; Adaptive radiotherapy
Accepted: June 13, 2024
Published Online: June 25, 2024
Copyright: © 2024 Author(s). 1. Introduction
This is an Open-Access article
distributed under the terms of the Conventional radiotherapy (CR) stands at a critical juncture, poised for transformation
Creative Commons Attribution through the integration of cutting-edge technologies. This article explores the convergence
License, permitting distribution,
and reproduction in any medium, of generative artificial intelligence (GAI) and computational sustainability (CS) principles,
provided the original work is unveiling a novel approach to revolutionize CR practices. The synergy between GAI,
properly cited. with a focus on models, such as generative adversarial networks (GANs), and CS offers
Publisher’s Note: AccScience a unique framework to enhance precision, efficiency, and sustainability in radiotherapy.
Publishing remains neutral with By leveraging generative approaches, we explore the potential for personalized treatment
regard to jurisdictional claims in
published maps and institutional planning, real-time adaptive radiotherapy, and resource optimization. Simultaneously,
affiliations the infusion of CS principles addresses ecological considerations, contributing to the

Volume 2 Issue 2 (2024) 1 doi: 10.36922/arnm.3523