Radiomic Phenotypes for Improving Early Prediction of Survival in Stage III Non-Small Cell Lung Cancer Adenocarcinoma after Chemoradiation

Abstract

We evaluate radiomic phenotypes derived from CT scans as early predictors of overall survival (OS) after chemoradiation in stage III primary lung adenocarcinoma. We retrospectively analyzed 110 thoracic CT scans acquired between April 2012−October 2018. Patients received a median radiation dose of 66.6 Gy at 1.8 Gy/fraction delivered with proton (55.5%) and photon (44.5%) beam treatment, as well as concurrent chemotherapy (89%) with carboplatin-based (55.5%) and cisplatin-based (36.4%) doublets. A total of 56 death events were recorded. Using manual tumor segmentations, 107 radiomic features were extracted. Feature harmonization using ComBat was performed to mitigate image heterogeneity due to the presence or lack of intravenous contrast material and variability in CT scanner vendors. A binary radiomic phenotype to predict OS was derived through the unsupervised hierarchical clustering of the first principal components explaining 85% of the variance of the radiomic features. C-scores and likelihood ratio tests (LRT) were used to compare the performance of a baseline Cox model based on ECOG status and age, with a model integrating the radiomic phenotype with such clinical predictors. The model integrating the radiomic phenotype (C-score = 0.69, 95%CI = (0.62, 0.77)) significantly improved (p < 0.005) upon the baseline model (C-score = 0.65, CI = (0.57, 0.73)). Our results suggest that harmonized radiomic phenotypes can significantly improve OS prediction in stage III NSCLC after chemoradiation.

FDG PET and CT radiomics in diagnosis and prognosis of non-small-cell lung cancer

“…It is similar for older studies ( 29 , 30 ). Finally, two studies ( 31 , 32 ) have concluded to an improvement of prognostic with radiomics compared to conventional data on special patients. Moreover, the high prognosis value of stage in our study, at least equal to that of some RFs, must be emphasized.…”

PixelPrint: Three-dimensional printing of realistic patient-specific lung phantoms for validation of computed tomography post-processing and inference algorithms

“…Radiomics and clinical decision-supporting AI are emerging as the next frontier for diagnostic and prognostic medical imaging in the new era of precision medicine 2 . The aim of these tools is to automatically extract quantitative information from medical images for assisting evidence-based clinical decision-making [4][5][6]8 . However, several major challenges hamper the widespread clinical translation of these promising new capabilities.…”

“…However, several major challenges hamper the widespread clinical translation of these promising new capabilities. The problem of data variability , which stems from differences in image acquisition and reconstruction settings among medical institutions, and scanner models, is recognized by many as a critical hurdle that requires dedicated solutions to enable the scalability of developed algorithms [6][7][8] . While recent studies made significant progress with solutions to account for some of the data variability, i.e., normalizations of image quality or imaging features, there is a critical need for lifelike phantoms that will enable the affirmations of these solutions without introducing additional risk to patients or logistical restrictions.…”

“…Despite ongoing efforts to account for factors originating from the recognized lack of imaging standardization , the problem of biases and variability persists. Experimental validation of image cohort normalization methods, such as ComBat [8][9][10] , is currently limited due to an inability to repeat patient scans on multiple scanners or with multiple imaging protocols given logistical and risk-related considerations, e.g., the risks of ionizing radiation in CT and PET. There is therefore a growing need for realistic patient-based volumetric phantoms that can accurately mimic human anatomy and disease manifestations to provide consistent imaging ground-truth targets when comparing post-processing image cohort normalization and feature extraction techniques.…”

More than Meets the Eye: Integration of Radiomics with Transcriptomics for Reconstructing the Tumor Microenvironment and Predicting Response to Therapy

“…This approach showed superiority as compared to conventional diagnostic methods, thereby putting forth a tool that may aid radiologists for early breast cancer detection in regular clinical practice settings [ 2 ]. Moreover, a team led by Dr. Kontos at the University of Pennsylvania extracted and analyzed retrospectively the radiomic phenotypes from 110 CTs of lung adenocarcinoma patients and showed that integration with clinical data significantly improved the prediction of overall survival in stage III non-small-cell lung cancer (NSCLC) after chemoradiation [ 3 ]. Interestingly, the same group demonstrated that the readers’ level of training and clinical experience (e.g., data scientist, medical student, radiology trainee, or specialty-trained radiologist) does not influence the ability to extract accurate radiomic features for NSCLC on CT, suggesting that the method is user-friendly and can be reliably applied by a variety of health care professionals [ 4 ].…”