Search

Tumor volume and volumetric reduction have been used as a metric to predict treatment response for patients under chemo-radiation treatments of advanced head and neck cancers. However, cut off values for volumetric changes vary widely among published studies. Imaging biomarkers that stratify patients at risk for treatment failure would be useful to identify patients who are not candidates for dose-deescalation radiotherapy. Radiomics aims to quantitatively capture complex tumor phenotypes from medical images to associate them with clinical outcomes. In this study, we evaluated retrospectively a single shape-type feature, namely, the lymph node gross tumor volume (GTVn) sphericity. The patient data comes from contrast-enhanced CT scans of an ongoing phase II institutional clinical research protocol. The CT scans are acquired at two time intervals (pre-treatment and at week 4 during chemo-radiation treatment) to evaluate radiation dose deescalation based on nodal reduction (ΔGTVn > 40%). Twenty-four patients have been currently enrolled in the study, thirteen of which presented multi-nodal involvement. The sphericity is calculated for two sets of GTVn contoured on CT scans: 1) largest node (based on volume size), and 2) all nodes involved. In the multi-nodal case the sphericity is obtained by averaging the sphericity of individual nodes. The mean pre-treatment sphericity across all patients was 0.746 0.074 for the largest node and 0.656 0.061 for all the nodes (p = 0.002 < 0.05). For both sphericity analyses, the deescalated patients showed higher sphericity range of variations, between the two time intervals compared to the non-deescalated patients (p < 0.05). These results suggest the prognostic value of lymph node tumor sphericity in clinical models, giving special attention to the lymph node GTVn definition as this significantly influences the sphericity values. [ABSTRACT FROM AUTHOR]

Radiomics aims for ways to personalize patient's treatments based on the extraction of texture features from routine clinical images. However, the implementation of Radiomics-based models in routine patient care poses a significant number of challenges, since there are multi-step processes in the implementation of the model. These include image selection (e.g CT, MRI, PET, or a combination of these), region of interest (ROI) segmentation, texture-feature extraction, model development, and model-validation. Each of these processes needs careful evaluation to ensure reproducibility and accuracy of the final Radiomics-based model before it can be introduced into the clinical practice. Image selection, ROI segmentation, and texture feature extraction are the most critical component in Radiomics modeling, because they define the reliability of the model. In this short review, after presenting a brief description of a Radiomics-based model representative workflow, we will concentrate in particular on the status of various technical aspects of imaging modality, segmentation selection, and texture feature extraction, including their shortcomings and possible solutions with emphasis in radiation therapy. [ABSTRACT FROM AUTHOR]