Author(s) :
Camil Ciprian Mireștean 1,2, Roxana Irina Iancu 3,4, and Dragoș Petru Teodor Iancu 5,6
1University of Medicine and Pharmacy Craiova, Department of Oncology and Radiotherapy, Craiova 200349, Romania;
2 Railways Clinical Hospital Iasi, Department of Surgery, Iași 700506, Romania
3“Gr. T. Popa” University of Medicine and Pharmacy, Faculty of Dental Medicine, Oral Pathology Department, Iași 700115, Romania;
4“St. Spiridon” Emergency Universitary Hospital, Department of Clinical Laboratory, Iași 700111, Romania
5“Gr. T. Popa” University of Medicine and Pharmacy, Faculty of Medicine, Oncology and Radiotherapy Department, Iași 700115, Romania;
6Regional Institute of Oncology, Department of Radiation Oncology, Iași 700483, Romania
Corresponding author: Roxana Irina Iancu, Email: roxana.iancu@umfiasi.ro
Publication History: Received - , Revised - , Accepted - , Published Online - 1 April 2023.
Copyright: © The author(s). Published by Casa Cărții de Știință.
User License: Creative Commons Attribution – NonCommercial (CC BY-NC)
PDF
Share
Abstract
Radiomics, the method by which digital images could be transformed into mineable data, opens new horizons for biomedical research and in particular in oncology, for diagnostic, predictive and prognostic purposes. The use of artificial intelligence (AI) algorithms in the radiomics algorithm makes radiomics and AI two inseparable, intricate domains. AI defined as machine capability of imitating human intelligence, has already been implemented on a large scale in oncology and radiotherapy. One of the two main branches (the virtual one) of machine learning depending on the application, artificial intelligence is involved both in the diagnostics processes as well as treatment planning, – dose delivery and radiotherapy quality assurance (QA). Head and neck cancer (HNC), although it is the 6th malignancy in incidence worldwide, is redoubtable due to the high rate of therapeutic failures, especially of loco-regional recurrence. Although intensity-modulated treatment techniques have brought benefits especially in limiting the toxicities associated with irradiation, AI and especially radiomics, due the possibility to extract data from high-resolution medical imaging in order to build predictive diagnostic and prognostic models, could upgrade the technological revolution in HNC radiotherapy at a higher level. Beyond the already intensively studied diagnostic applications, radiomics could be useful for predicting the response to radio-chemotherapy, anticipating treatment related toxicities and for pre-therapeutic evaluation of the need for adaptive radiotherapy (ART). Clinical-radiomic models have superior predictive power and the delta variation of radiomic features could be a biomarker still less evaluated. Due to characteristics of modern radiotherapy which includes as standard the image guided radiotherapy (IGRT) concept using the computer tomography (CT) simulator and Cone Beam CT (CBCT) to ensure the accuracy of the patient’s positioning during the treatment, radiomics in radiotherapy could be the spearhead of the translation radiomics in daily clinical routine and of the HNC RGRT concept development.
| Author/year of publication | Topic addressed | Article type | Image type used for radiomic analysis | Number of patients | Results/Conclusions |
| Rabasco Meneghetti et al., 2022 (15) | prediction of loco-regional control (LRC) | original | CT | 206 | multi-omics analyzes could generate models for personalizing treatment |
| Sellam et al., 2022 (18) | prediction of progression after radiotherapy | original | CBCT | 93 | a combined model including Coarsness extracted from CBCT in the 4th week of treatment and clinical features (hemoglobin level) offers the best predictive capacity |
| Berger et al., 2023 (23) |
prediction of radiation-induced sticky saliva and xerostomia |
original | CT | 109 | None of previously identified features were associated with endpoint prediction. The study demonstrates the pitfalls of generalizing radiomic studies. |
| Carbonara et al., 2021 (24) | investigation of radiation-induced toxicity | systematic review | different imaging methods being evaluated Radiomic Quality Score (RQS) | 8 studies | parotid glands, cochlea, masticatory muscles, and white brain matter were evaluated. A variability in the interpretation of RQS was identified. |
| Y et al., 2019 (26) | prediction of ART eligibility | original | MRI | 70 | 6 selected features for joint T1-T2 model could be superior to a single sequence model |
| Lam et al., 2022 (31) | prediction of ART eligibility | original | CT | 182 | CT-based neck nodal radiomics could predict the need for ART in nasopharyngeal cancer |
Mireştean et al.2021 |
The use of delta variation of radiomic features in order to predict necessity of personalizing the treatment by intensifying or de-escalating | concept | CT | Not applicable | standardization by using the same platform and the same acquisition parameters make CT simulation a good starting point for delta radiomic analysis |