ESTRO 2024 - Abstract Book

S5084

Physics - Radiomics, functional and biological imaging and outcome prediction

ESTRO 2024

[1] McWilliam A, Abravan A, Banfill K, Faivre-Finn C, van Herk M. Demystifying the Results of RTOG 0617: Identification of Dose Sensitive Cardiac Subregions Associated With Overall Survival. J Thorac Oncol. 2023 May;18(5):599-607. doi: 10.1016/j.jtho.2023.01.085. Epub 2023 Feb 3. PMID: 36738929. [2] Johnson-Hart CN, Price GJ, Faivre-Finn C, Aznar MC, van Herk M. Residual Setup Errors Towards the Heart After Image Guidance Linked With Poorer Survival in Lung Cancer Patients: Do We Need Stricter IGRT Protocols? Int J Radiat Oncol Biol Phys. 2018 Oct 1;102(2):434-442. doi: 10.1016/j.ijrobp.2018.05.052. Epub 2018 Jun 1. PMID: 29908945. [3] Johnson-Hart C, Price G, McWilliam A, Green A, Faivre-Finn C, van Herk M. Impact of small residual setup errors after image guidance on heart dose and survival in non-small cell lung cancer treated with curative-intent radiotherapy. Radiother Oncol. 2020 Nov;152:177-182. doi: 10.1016/j.radonc.2020.04.008. Epub 2020 Apr 14. PMID: 32360033; PMCID: PMC7707351.

1762

Digital Poster

From inception to the present: A review analysing the application of the radiomics quality score.

Nathaniel Barry 1,2 , Jake Kendrick 1,2 , Pejman Rowshanfarzad 1,2 , Ghulam M Hassan 1 , Martin A Ebert 1,2,3

1 University of Western Australia, School of Physics, Mathematics and Computing, Crawley, Australia. 2 Centre for Advanced Technologies in Cancer Research, (CATCR), Perth, Australia. 3 Sir Charles Gairdner Hospital, Department of Radiation Oncology, Nedlands, Australia

Purpose/Objective:

The field of radiomics specializes in the high-throughput extraction of quantitative features from medical images. Those features that adequately characterize tumour heterogeneity, can be incorporated into diagnostic and prognostic models, with performance exceeding qualitative assessment alone. As radiomics studies became more frequent, there was rising concern regarding the reproducibility and lack of clinical translation of the resulting models, which led to the introduction of the radiomics quality score (RQS) by Lambin et al. in 2017 [1]. This quality score ranges from -8 to 36 and consists of 16 criteria assessing multiple aspects of the radiomics workflow, with associated scores and penalties. Since its inception, the RQS has become the de facto tool for assessment of radiomics studies in systematic reviews. Here we report an analysis of the RQS when applied in these reviews.

Material/Methods:

The literature was systematically searched (keyword search: ((“radiomics” OR “radiomic”) AND “quality” AND “score”)) to identify systematic reviews that had employed the RQS from 1 Jan 2022. Reviews conducted prior to 1 Jan 2022 were taken from a previous systematic review [2]. The following data, if available, were extracted from each review: the mean RQS, attributed points for all 16 criteria and the final scores for each paper in the respective review, and data from multiple readers. All results reported here were generated from the raw scores where possible, with additional cross-referencing against the information provided in each review. The average percentage of adherence