CT derived radiomic score for predicting the added benefit of adjuvant chemotherapy following surgery in stage I, II resectable non-small cell lung cancer: a retrospective multicohort study for outcome prediction

Abstract

Background Use of adjuvant chemotherapy in patients with early-stage lung cancer is controversial because no definite biomarker exists to identify patients who would receive added benefit from it. We aimed to develop and validate a quantitative radiomic risk score (QuRiS) and associated nomogram (QuRNom) for early-stage non-small cell lung cancer (NSCLC) that is prognostic of disease-free survival and predictive of the added benefit of adjuvant chemotherapy following surgery. MethodsWe did a retrospective multicohort study of individuals with early-stage NSCLC (stage I and II) who either received surgery alone or surgery plus adjuvant chemotherapy. We selected patients for whom we had available pretreatment diagnostic CT scans and corresponding survival information. We used radiomic texture features derived from within and outside the primary lung nodule on chest CT scans of patients from the Cleveland Clinic Foundation (Cleveland, OH, USA; cohort D 1 ) to develop QuRiS. A least absolute shrinkage and selection operator-Cox regularisation model was used for data dimension reduction, feature selection, and QuRiS construction. QuRiS was independently validated on a cohort of patients from the University of Pennsylvania (Philadephia, PA, USA; cohort D 2 ) and a cohort of patients whose CT scans were derived from The Cancer Imaging Archive (cohort D 3 ). QuRNom was constructed by integrating QuRiS with tumour and node descriptors (according to the tumour, node, metastasis staging system) and lymphovascular invasion. The primary endpoint of the study was the assessment of the performance of QuRiS and QuRNom in predicting disease-free survival. The added benefit of adjuvant chemotherapy estimated using QuRiS and QuRNom was validated by comparing patients who received adjuvant chemotherapy versus patients who underwent surgery alone in cohorts D 1 -D 3 . Findings We included: 329 patients in cohort D 1 (73 [22%] had surgery plus adjuvant chemotherapy and 256 (78%) had surgery alone); 114 patients in cohort D 2 (33 [29%] had surgery plus adjuvant chemotherapy and 81 (71%) had surgery alone); and 82 patients in cohort D 3 (24 [29%] had surgery plus adjuvant chemotherapy and 58 (71%) had surgery alone). QuRiS comprised three intratumoral and 10 peritumoral CT-radiomic features and was found to be significantly associated with disease-free survival (ie, prognostic validation of QuRiS; hazard ratio for predicted high-risk vs predicted low-risk groups 1•56, 95% CI 1•08-2•23, p=0•016 for cohort D 1 ; 2•66, 1•24-5•68, p=0•011 for cohort D 2 ; and 2•67, 1•39-5•11, p=0•0029 for cohort D 3 ). To validate the predictive performance of QuRiS, patients were partitioned into three risk groups (high, intermediate, and low risk) on the basis of their corresponding QuRiS. Patients in the high-risk group were observed to have significantly longer survival with adjuvant chemotherapy than patients who underwent surgery alone (0•27, 0•08-0•95, p=0•042, for cohort D 1 ; 0•08, 0•01-0•42, p=0•0029, for cohorts D 2 and D 3 combined). As concerns...

A Clinical-Radiomics Nomogram Based on Computed Tomography for Predicting Risk of Local Recurrence After Radiotherapy in Nasopharyngeal Carcinoma

“…It has been confirmed that image-based phenotypes can be used to quantify the spatial heterogeneity of tumors (7). Recently, some studies have indicated that radiomics signature generated by using radiomics features which are extracted from high-quality imaging data might be served as imaging markers to predict treatment outcome (8)(9)(10)(11).…”

The International Radiomics Platform – An Initiative of the German and Austrian Radiological Societies – First Application Examples

“…Today, machine learning and the extraction of statistical features make it possible to predict mutations and micrometastases [1]. In addition to this sub-level acquired by machine learning and the extraction of statistical features, there is a diagnostic meta-level that allows conclusions regarding treatment response and survival due to interdisciplinary data integration [2,3]. Oncology is also undergoing a fundamental change in previous diagnostic-therapeutic procedures.…”

Novel, non-invasive imaging approach to identify patients with advanced non-small cell lung cancer at risk of hyperprogressive disease with immune checkpoint blockade

“…Radiomic features have shown prognostic and predicting response to multiple different treatments across a wide variety of cancers, including lung, [12][13][14][15][16][17] breast, 18-21 21 brain, [22][23][24][25][26] prostate 27 28 and colorectal 29 cancers. Specifically, in lung cancer, 9 radiomics approaches have been used to predict the benefit of adjuvant chemotherapy, prognosticate disease risk in early-stage lung cancer, 30 predict treatment response to concurrent chemoradiation in locally advanced disease 15 and to predict response to immune checkpoint inhibition in advanced NSCLC. 31 32 These features are sought to capture the extent of heterogeneity and other biologically relevant features, such as interaction with stromal or vascular components within the given region of interest.…”