3068 Background: Radiomics is an image based approach that allows for characterization and quantification of tumor lesions in cancer patients. Radiomics has been proven capable of potentially adding value in the diagnostic and prognostic patient managment. In this study we evaluated the potential of Radiomics to bring additional insight also in early drug development. Methods: All the visible malignant lung and liver metastasis lesions of 7 uveal melanoma patients (86% of women, 60±11y) treated with IOA-244 (EudraCT 2019-000686-20) were manually segmented and analyzed in their size and shape via a radiomics approach. The CT scans at baseline and first follow-up (8 weeks) were included in the study and compared. Descriptive statistics and linear mixed effect (LME) models were used to quantify volumetric lesion-specific response to treatment. Response has been defined both as continuous variable and in three discrete categories (lesion shrinkage, stable and progressive disease for a volume change of [-100%;-0%];[0%-+25%] and > 25%, respectively). The influence of lesion shape at baseline (e.g. compactness, elongation or surface roughness among others) on the treatment response has been explore through LME models as well. Results: We identified and segmented 126 metastatic lesions (70 lung and 56 liver) from baseline scans and 122 lesions (71 lung and 51 liver) from post treatment scans. Of those, 64% could be consistently mapped between visits, resulting in a total of 147 matching lesions on which the radiomics analysis was performed. We found 19% of complete response and 16% of new lesions appearing. 8 weeks after treatment start, we observed non progressive disease in 61% of all lesions, of which 42% was shrinking. LME did not show a significant change in lesion volume between visits, but the mean difference between visits was negative. LME did show that lesion shape is significantly different between progressors and non-progressors at baseline for lung lesions (compact and irregular lesions are more likely to respond), and that there are moderate correlations (0.4-0.7) between tumor shape and volume change for liver lesions (compact lesions have a larger volume drop). Conclusions: This work demonstrates both the clinical potential of IOA-244 for treatment of Uveal Melanoma patients with lesions in the lung and in the liver and the potential of radiomics individual lesion analysis for clinical research in the very early stages of drug development. Lesion evolution volumetric assessment has allowed a more accurate and sensitive understanding of IOA-244 efficacy and impact across different lesions, in both lung and liver. Radiomics showed a promising response of selected population to IOA-244 over the first time point (W0-W8). A further radiomics analysis on next follow-up scans would allow a radiological proof of treatment-induced changes and long-term patient outcome prediction.
e20580 Background: The vascularization of lung nodules has been proven as severe risk factor for malignancy, and in lung cancer, indication of worse prognosis (1,2). For this reason, we developed a novel imagining endpoint based on the vasculature surrounding a lung mass and we tested this endpoint for the prediction of malignancy for lung nodules. Methods: The vasculature of the nodules (both arteries and veins) has been computed using the surface intersection between the nodule and the vascular structure 3D meshes. Both 3D structures were obtained by converting the segmentations of the nodule and of the vessels to meshes with a marching cubes algorithm. Nodule and vessels segmentation has been obtained with an in-house deep learning segmentation model. The features considered are the numbers of intersections, the total area of intersection and the mean area of intersection. These features have been used to predict nodule malignancy on thoracic CT scans from the Lung Image Database Consortium image collection (3). Quality controls on clinical data completeness and imaging parameters resulted in a cohort of 894 scans (715 for training and 179 for testing), from the original 1018 cases. The malignancy status is defined as high risk and low risk, based on the consensus classification of a panel of four radiologists. Firstly, an univariate analysis is performed to assess the variability of the features grouped by the malignancy score by using Mann-Whitney and ANOVA tests. After, seven combinations of features have been used to train generalized linear models (GLM) to predict nodule malignancy. To compare the models, the Area Under the Curve (AUC) is used as the main performance metric. Results: Univariate analysis of each feature grouped by the malignancy outcome showed that all the three features have good univariate discriminative power between high risk and low risk categories ( p value ≤ 0.05), with nb_connections as the most predictive singular feature ( p value of 1.343277 × 10-36). All the GLM models developed showed a good performance (AUC equal or higher than 0.7), with the best model in testing based on the combination of mean_area and sum_area (AUC of 0.84). Conclusions: The radiomics vascularity endpoint has been proven capable of predicting nodule malignancy with very good performance. The singular feature that is most related to malignancy is the number of vessels intersecting the nodule while the total area of intersection followed by the number of intersections are the most useful to model risk of malignancy. Wang et al., Lung Cancer 114: 38–43, 2017. Hamanaka et al., Diagn Pathol 10,17, 2015. G. Armato et al., Med. Phys., 38: 915-931, 2011.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.