A Multicentre Evaluation of Dosiomics Features Reproducibility, Stability and Sensitivity

Abstract

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.

Impact of Interfractional Error on Dosiomic Features

“…Many studies have been performed on the stability of radiomic features, whereas only a few studies have reported on the stability of dosiomic features (6,7,22). This is the first report to introduce a concern about the stability of dosiomic features under interfractional error in radiation therapy.…”

“…, respectively. CV has been used in previous studies for radiomic feature stability analysis (19)(20)(21)(22). The CV was calculated for all features and all total numbers of fraction groups.…”

Deep Learning With Radiomics for Disease Diagnosis and Treatment: Challenges and Potential

“…(b) Dosiomics is similarly subject to reproducibility issues because dose calculation algorithms, grid sizes, planners, and treatment regimens can lead to variations in DVI values and dosiomic characteristics. Recently, Placidi et al (168) evaluated the correlation between dosiomic properties and clinical outcomes by employing various dose calculation algorithms, 30 distinct dose distributions, and 2 grid resolutions at 8 centers to determine the sensitivity characteristics when there is a change in the dose distribution. This study favorably supports a multicenter investigation of this method, although only dosiomic signatures were considered, without including all possible RT techniques and excluding different feature extraction algorithms.…”

Precision Medicine in Head and Neck Cancers: Genomic and Preclinical Approaches

“…In the field of radiomics, the technology involved in the extraction of spatial information, which is used afterwards to construct prediction model, is named dosiomics. Through machine learning techniques, dosiomics extracts characteristics from 3D radiotherapy dose distribution by intensity, textural, and shape-based characteristics that allow a high complexity description of the dose distribution [ 97 , 98 ]. Dosiomics is increasingly used to improve the prediction of clinical outcomes and side effects, such as the locoregional recurrence in HNSCCs after intensity-modulated radiation therapy (IMRT) or local control after radiotherapy [ 99 ].…”