Page 7 - AIH-1-4

Artificial Intelligence in Health

REVIEW ARTICLE
Prognostic evaluation using radiomics after

stereotactic body radiotherapy in early-stage
lung cancer

Melek Yakar*

Melek Yakar* {https://orcid.org/0000-0002-9042-9489} Department of Radiation Oncology, Faculty of Medicine, Osmangazi University, Eskişehir, Turkey

Abstract

Non-small cell lung cancer (NSCLC), the leading cause of cancer-related deaths, is
the most common subtype of lung cancer with an incidence of 85%. Stereotactic
body radiotherapy (SBRT) is a curative treatment option for patients with early-
stage NSCLC who cannot undergo surgery due to medical reasons or who refuse
surgery. Radiomics non-invasively extracts advanced imaging features invisible to
the human eye from medical images. Radiomics has prognostic value in predicting
oncological outcomes after lung SBRT. Although studies on this subject are available
in the literature, they are quite heterogeneous. There is a need for large-scale
multicenter studies in which standard imaging techniques are used to obtain radiomic
features, artificial intelligence-based segmentations are used to eliminate differences
between contours, and SBRT dose schemes with appropriate therapeutic indexes
are applied. This review aimed to interpret the existing studies and emphasize the
clinical importance of radiomics, which can contribute to personalized treatment.
A comprehensive literature search was conducted through the PubMed database
*Corresponding author: using a wide range of keywords, which yielded 11 peer-reviewed articles published
Melek Yakar between 2017 and 2024. Seven articles evaluated computed tomography radiomics,
(myakar@ogu.edu.tr) and four evaluated fluorodeoxyglucose positron emission tomography-computed
Citation: Yakar M. Prognostic tomography radiomics. Oncological outcomes are not always identical in patients
evaluation using radiomics after with a similar history receiving similar treatments at the same stage and age. Clinical,
stereotactic body radiotherapy in demographic, or treatment-related data are insufficient to predict prognosis and
early-stage lung cancer. Artif Intell
Health. 2024;1(4):1-11. determine personalized treatment. Incorporating radiomics to these data can help
doi: 10.36922/aih.3541 establish models with higher accuracy and achieve personalized treatment.
Received: April 30, 2024
Accepted: August 1, 2024 Keywords: Artificial intelligence; Lung cancer; Stereotactic body radiotherapy; Prognosis;
Radiomics
Published Online: October 16, 2024
Copyright: © 2024 Author(s).
This is an Open-Access article
distributed under the terms of the
Creative Commons Attribution 1. Introduction
License, permitting distribution,
and reproduction in any medium, Non-small cell lung cancer (NSCLC) is the most common subtype of lung cancer
provided the original work is with an incidence of 85% and has the highest cancer-related mortality. Stereotactic
properly cited. body radiotherapy (SBRT) is a curative treatment option for patients with early-stage
Publisher’s Note: AccScience NSCLC who cannot undergo surgery due to medical reasons or who refuse surgery.
Publishing remains neutral with Although 92 – 98% of local tumor control can be achieved using SBRT in these patients,
regard to jurisdictional claims in 1
published maps and institutional varying recurrence patterns have been reported in 18 – 20% of the patients. Stereotactic
affiliations. irradiation focuses multiple X-rays at different angles on a small localized lesion, provided

Volume 1 Issue 4 (2024) 1 doi: 10.36922/aih.3541