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]

Lung cancer is the leading cause of death from cancer worldwide. Medical images are essential in the diagnosis and prognosis of lung cancer. Medical image processing techniques such as Radiomics allow extracting information from these images that it is not accessible without computational means, and may be useful in the detection and treatment of cancer. This article presents the state of the art of image processing techniques applied in the study of lung cancer, emphasizing in two main tasks: segmentation of nodules or tumors, and extraction of useful features for classification and prognosis of tumor evolution using Radiomics. [ABSTRACT FROM AUTHOR]