Radiomics is defined as the use of automated or semi-automated post-processing and analysis of multiple features derived from imaging exams. Extracted features might generate models able to predict the molecular profile of solid tumors. The aim of this study was to develop a predictive algorithm to define the mutational status of EGFR in treatment-naïve patients with advanced non–small cell lung cancer (NSCLC). CT scans from 109 treatment-naïve patients with NSCLC (21 EGFR-mutant and 88 EGFR-wild type) underwent radiomics analysis to develop a machine learning model able to recognize EGFR-mutant from EGFR-WT patients via CT scans. A “test–retest” approach was used to identify stable radiomics features. The accuracy of the model was tested on an external validation set from another institution and on a dataset from the Cancer Imaging Archive (TCIA). The machine learning model that considered both radiomic and clinical features (gender and smoking status) reached a diagnostic accuracy of 88.1% in our dataset with an AUC at the ROC curve of 0.85, whereas the accuracy values in the datasets from TCIA and the external institution were 76.6% and 83.3%, respectively. Furthermore, 17 distinct radiomics features detected at baseline CT scan were associated with subsequent development of T790M during treatment with an EGFR inhibitor. In conclusion, our machine learning model was able to identify EGFR-mutant patients in multiple validation sets with globally good accuracy, especially after data optimization. More comprehensive training sets might result in further improvement of radiomics-based algorithms. Significance: These findings demonstrate that data normalization and “test–retest” methods might improve the performance of machine learning models on radiomics images and increase their reliability when used on external validation datasets.
Delta-radiomics is a branch of radiomics in which features are confronted after time or after introducing an external factor (such as treatment with chemotherapy or radiotherapy) to extrapolate prognostic data or to monitor a certain condition. Immune checkpoint inhibitors (ICIs) are currently revolutionizing the treatment of non-small cell lung cancer (NSCLC); however, there are still many issues in defining the response to therapy. Contrast-enhanced CT scans of 33 NSCLC patients treated with ICIs were analyzed; altogether, 43 lung lesions were considered. The radiomic features of the lung lesions were extracted from CT scans at baseline and at first reassessment, and their variation (delta, Δ) was calculated by means of the absolute difference and relative reduction. This variation was related to the final response of each lesion to evaluate the predictive ability of the variation itself. Twenty-seven delta features have been identified that are able to discriminate radiologic response to ICIs with statistically significant accuracy. Furthermore, the variation of nine features significantly correlates with pseudo-progression.
Introduction: In the last 2 decades, several studies in the literature evaluated the possible role of covered stents in the treatment of TransAtlantic Inter-Society Consensus (TASC) C and D femoropopliteal lesions but, despite the encouraging results, the employment of these devices was never included in clinical guidelines. The aim of this study is to evaluate the role of the technical aspects in patients with TASC C or D lesions that were treated with the GORE VIABAHN endoprosthesis and to elaborate a computerized method to objectively estimate the post-stent run-off and predict stent-graft failure. Materials and Methods: In this monocentric retrospective study, we collected the patients who were treated in our department from December 2014 to May 2021. Inclusion criteria comprised: (1) patients who underwent endovascular treatment of a TASC C or D femoropopliteal lesions using one or more heparin-bonded covered stent(s) and (2) clinical follow-up >2 years. Exclusion criteria were clinical follow-up <2 years or missing. An in-house computerized analysis to estimate the post-stent run-off, CEVERO (Computerized Estimation of VEssel Run-Off), was elaborated. Results: Sixty-six patients were enrolled in the study. Eleven patients had a TASC type C lesion, and 55 patients presented a type D lesion. The median follow-up time was 2.6 years. Twenty-nine patients (43.9%) experienced a major adverse limb event. Primary patency after 6, 12 and 24 months was 74.2%, 60.6%, and 57.6%; primary-assisted patency was 78.8%, 65.2%, and 59.1%. The presence of <2 run-off vessels (p<0.001) was correlated with stent-graft failure. The CEVERO analysis demonstrated an accuracy of 90.0% in predicting stent-graft failure. Conclusions: The treatment of TASC C and D femoropopliteal lesions remains technically challenging. Our study supported the hypothesis that run-off is the most critical factor in determining the outcome of the procedure and that concomitant angioplasty of the tibial vessels might improve the patency of the covered stent. The CEVERO analysis could permit a real-time, objective estimation of the distal run-off using conventional angiographic images, and it might be employed as a tool in the intraprocedural decision-making process, but its clinical applicability should be evaluated on external validation cohorts. Clinical Impact: The endovascular treatment of TASC C and D femoropopliteal lesions is technically challenging and run-off seems to be the most critical factor in determining the outcome. Concurrent angioplasty of the tibial vessels can create adequate run-off to avoid stent failure. The CEVERO analysis is a computerized estimation of run-off that might be a useful tool in the decision-making process.
10 February 2023 in Journal of Vascular and Interventional Radiology