The Image Biomarker Standardization Initiative validated consensus-based reference values for 169 radiomics features, thus enabling calibration and verification of radiomics software. Background Radiomic features may quantify characteristics present in medical imaging. However, the lack of standardized definitions and validated reference values have hampered clinical use. Purpos...
Filters are commonly used to enhance specific structures and patterns in images, such as vessels or peritumoral regions, to enable clinical insights beyond the visible image using radiomics. However, their lack of standardization restricts reproducibility and clinical translation of radiomics decision support tools. In this special report, teams of researchers who developed radiomics software participated in a three-phase study (September 2020 to December 2022) to establish a standardized set of filters. The first two phases focused on finding reference filtered images and reference feature values for commonly used convolutional filters: mean, Laplacian of Gaussian, Laws and Gabor kernels, separable and nonseparable wavelets (including decomposed forms), and Riesz transformations. In the first phase, 15 teams used digital phantoms to establish 33 reference filtered images of 36 filter configurations. In phase 2, 11 teams used a chest CT image to derive reference values for 323 of 396 features computed from filtered images using 22 filter and image processing configurations. Reference filtered images and feature values for Riesz transformations were not established. Reproducibility of standardized convolutional filters was validated on a public data set of multimodal imaging (CT, fluorodeoxyglucose PET, and T1-weighted MRI) in 51 patients with soft-tissue sarcoma. At validation, reproducibility of 486 features computed from filtered images using nine configurations × three imaging modalities was assessed using the lower bounds of 95% CIs of intraclass correlation coefficients. Out of 486 features, 458 were found to be reproducible across nine teams with lower bounds of 95% CIs of intraclass correlation coefficients greater than 0.75. In conclusion, eight filter types were standardized with reference filtered images and reference feature values for verifying and calibrating radiomics software packages. A web-based tool is available for compliance checking.
Radiation dose to the cardio-pulmonary system is critical for radiotherapy-induced mortality in non-small cell lung cancer. Our goal was to automatically segment substructures of the cardio-pulmonary system for use in outcomes analyses for thoracic cancers. We built and validated a multi-label Deep Learning Segmentation (DLS) model for accurate auto-segmentation of twelve cardio-pulmonary substructures. The DLS model utilized a convolutional neural network for segmenting substructures from 217 thoracic radiotherapy Computed Tomography (CT) scans. The model was built in the presence of variable image characteristics such as the absence/presence of contrast. We quantitatively evaluated the final model against expert contours for a hold-out dataset of 24 CT scans using Dice Similarity Coefficient (DSC), 95th Percentile of Hausdorff Distance and Dose-volume Histograms (DVH). DLS contours of an additional 25 scans were qualitatively evaluated by a radiation oncologist to determine their clinical acceptability. The DLS model reduced segmentation time per patient from about one hour to 10 s. Quantitatively, the highest accuracy was observed for the Heart (median DSC = (0.96 (0.95–0.97)). The median DSC for the remaining structures was between 0.81 and 0.93. No statistically significant difference was found between DVH metrics of the auto-generated and manual contours (p-value ⩾ 0.69). The expert judged that, on average, 85% of contours were qualitatively equivalent to state-of-the-art manual contouring. The cardio-pulmonary DLS model performed well both quantitatively and qualitatively for all structures. This model has been incorporated into an open-source tool for the community to use for treatment planning and clinical outcomes analysis.
Many dose-limiting normal tissues in radiotherapy (RT) display considerable internal motion between fractions over a course of treatment, potentially reducing the appropriateness of using planned dose distributions to predict morbidity. Accounting explicitly for rectal motion could improve the predictive power of modelling rectal morbidity. To test this, we simulated the effect of motion in two cohorts. The included patients (232 and 159 cases) received RT for prostate cancer to 70 and 74 Gy. Motion-inclusive dose distributions were introduced as simulations of random or systematic motion to the planned dose distributions. Six rectal morbidity endpoints were analysed. A probit model using the QUANTEC recommended parameters was also applied to the cohorts. The differences in associations using the planned over the motion-inclusive dose distributions were modest. Statistically significant associations were obtained with four of the endpoints, mainly at high doses (55-70 Gy), using both the planned and the motion-inclusive dose distributions, primarily when simulating random motion. The strongest associations were observed for GI toxicity and rectal bleeding (Rs=0.12-0.21; Rs=0.11-0.20). Applying the probit model, significant associations were found for tenesmus and rectal bleeding (Rs=0.13, p=0.02). Equally strong associations with rectal morbidity were observed at high doses (>55 Gy), for the planned and the simulated dose distributions including in particular random rectal motion. Future studies should explore patient-specific descriptions of rectal motion to achieve improved predictive power.