Development and Validation of a Radiomics Nomogram Using Computed Tomography for Differentiating Immune Checkpoint Inhibitor-Related Pneumonitis From Radiation Pneumonitis for Patients With Non-Small Cell Lung Cancer

Abstract

BackgroundThe combination of immunotherapy and chemoradiotherapy has become the standard therapeutic strategy for patients with unresected locally advance-stage non-small cell lung cancer (NSCLC) and induced treatment-related adverse effects, particularly immune checkpoint inhibitor-related pneumonitis (CIP) and radiation pneumonitis (RP). The aim of this study is to differentiate between CIP and RP by pretreatment CT radiomics and clinical or radiological parameters.MethodsA total of 126 advance-stage NSCLC patients with pneumonitis were enrolled in this retrospective study and divided into the training dataset (n =88) and the validation dataset (n = 38). A total of 837 radiomics features were extracted from regions of interest based on the lung parenchyma window of CT images. A radiomics signature was constructed on the basis of the predictive features by the least absolute shrinkage and selection operator. A logistic regression was applied to develop a radiomics nomogram. Receiver operating characteristics curve and area under the curve (AUC) were applied to evaluate the performance of pneumonitis etiology identification.ResultsThere was no significant difference between the training and the validation datasets for any clinicopathological parameters in this study. The radiomics signature, named Rad-score, consisting of 11 selected radiomics features, has potential ability to differentiate between CIP and RP with the empirical and α-binormal-based AUCs of 0.891 and 0.896. These results were verified in the validation dataset with AUC = 0.901 and 0.874, respectively. The clinical and radiological parameters of bilateral changes (p < 0.001) and sharp border (p = 0.001) were associated with the identification of CIP and RP. The nomogram model showed good performance on discrimination in the training dataset (AUC = 0.953 and 0.950) and in the validation dataset (AUC = 0.947 and 0.936).ConclusionsCT-based radiomics features have potential values for differentiating between patients with CIP and patients with RP. The addition of bilateral changes and sharp border produced superior model performance on classifying, which could be a useful method to improve related clinical decision-making.

Radiation Recall Pneumonitis Anticipates Bilateral Immune-Induced Pneumonitis in Non-Small Cell Lung Cancer

“…Radiomics, a quantitative imaging analysis tool, has shown promising results in identifying the predominant pneumonitis etiology in patients receiving both RT and ICI [ 35 , 36 ]. Future studies are needed to confirm these preliminary results and make radiomics available at the bedside.…”

Immune-related pulmonary toxicities of checkpoint inhibitors in non-small cell lung cancer: Diagnosis, mechanism, and treatment strategies

“…Several studies have integrated imaging data, serological data, and clinical reports data with AI to diagnose and predict CIP in ICI-treated patients (43). In a retrospective study, by analyzing the CT radiomics data, Qiu et al distinguished CIP from radiation pneumonitis in 126 advanced-stage NSCLC pneumonitis (44). Similarly, by systematically analyzing the baseline chest computed tomography images of patients with or without CIP, Colen et al summarized the radiomics features that could distinguish and predict the risk of CIP with an accuracy of 100% (p=0.0033) (45).…”

“…In a retrospective study, by analyzing the CT radiomics data, Qiu et al. distinguished CIP from radiation pneumonitis in 126 advanced-stage NSCLC pneumonitis ( 44 ). Similarly, by systematically analyzing the baseline chest computed tomography images of patients with or without CIP, Colen et al.…”

Advances in CT features and radiomics of checkpoint inhibitor-related pneumonitis: A short review

“…included a larger sample (126 cases) and finally identified the Rad-score (11 imaging histological features) with the potential to distinguish between CIP and RIP, and also found that bilateral involvement and sharp border were associated with the distinguishment of CIP and RIP. Combining the Rad-score and the above two features, authors created a robust model showing good performance in both the training dataset (empirical-based AUCs of 0.953) and the validation dataset (AUC = 0.947) ( 20 ), which is also the model with the best recognition performance reported in the literature so far.…”