A Multicentre Evaluation of Dosiomics Features Reproducibility, Stability and Sensitivity.

Lorenzo Placidi,Jacopo Lenkowicz,Enrico Menghi,Annarita Fanizzi,Davide Maestri,Eliana Gioscio,Cristina Garibaldi,Raffaella Massafra,Michele Avanzo,Giacomo Reggiori,Tiziana Rancati,Roberto Sghedoni,Pasquale Tamborra,Luca Boldrini,Alfredo Mirandola,Stefania Comi

doi:10.3390/cancers13153835

Abstract

Simple SummaryDosiomics is born directly as an extension of radiomics: it entails extracting features from the patients’ three-dimensional (3D) radiotherapy dose distribution rather than from conventional medical images to obtain specific spatial and statistical information. Dosiomic studies, in a multicentre setting, require assessing the features’ stability to dose calculation settings and the features’ capability in distinguishing different dose distributions. This study provides the first multicentre evaluation of the dosiomic features in terms of reproducibility, stability and sensitivity across various dose distributions obtained from multiple technologies and techniques and considering different dose calculation algorithms of TPS and two different resolutions of the dose grid. Harmonisation strategies to account for a possible variation in the dose distribution due to these confounding factors should be adopted when investigating a correlation between dosiomic features and clinical outcomes in multicentre studies.Dosiomics is a texture analysis method to produce dose features that encode the spatial 3D distribution of radiotherapy dose. Dosiomic studies, in a multicentre setting, require assessing the features’ stability to dose calculation settings and the features’ capability in distinguishing different dose distributions. Dose distributions were generated by eight Italian centres on a shared image dataset acquired on a dedicated phantom. Treatment planning protocols, in terms of planning target volume coverage and dose–volume constraints to the organs at risk, were shared among the centres to produce comparable dose distributions for measuring reproducibility/stability and sensitivity of dosiomic features. In addition, coefficient of variation (CV) was employed to evaluate the dosiomic features’ variation. We extracted 38,160 features from 30 different dose distributions from six regions of interest, grouped by four features’ families. A selected group of features (CV < 3 for the reproducibility/stability studies, CV > 1 for the sensitivity studies) were identified to support future multicentre studies, assuring both stable features when dose distributions variation is minimal and sensitive features when dose distribution variations need to be clearly identified. Dosiomic is a promising tool that could support multicentre studies, especially for predictive models, and encode the spatial and statistical characteristics of the 3D dose distribution.

Highlights

In the era of personalised medicine and targeted therapy, one of the most promising methods introduced in clinical practice is radiomics [1]
We extracted a total amount of 38,160 dosiomic features from 30 different dose distributions from six regions of interest (ROIs), grouped by four features’ families
We evaluated 5088 and 10,176 dosiomic features to assess the reproducibility and stability of the extracted dosiomic features, respectively

Summary

Introduction

In the era of personalised medicine and targeted therapy, one of the most promising methods introduced in clinical practice is radiomics [1]. Dosiomics is born directly as an extension of radiomics; it entails extracting features from the patients’ three-dimensional (3D) radiotherapy dose distribution rather than from conventional medical images [15,16] to obtain specific spatial and statistical information. Developing robust models requires ample training and validation datasets with radiotherapy data from many patients for any specific cancer site These needs settle dosiomics in the framework of “big data” and push towards multicentre studies. The variability due to these sources may hide any potential variability associated with the dose–response, making at least some of the dosiomic models unreliable and preventing the generalization of results In this frame, Placidi et al evaluated the robustness of dosiomic signatures across grid resolution and algorithm for dose calculation [25] in a monocentric setting. We here propose to investigate the stability of dosiomic features in a multicentre setting with two main aims: (a) to provide

Objectives

Results

Discussion

Conclusion