Predictive Radiomic Models for the Chemotherapy Response in Non-Small-Cell Lung Cancer based on Computerized-Tomography Images

Abstract

The heterogeneity and complexity of non-small cell lung cancer (NSCLC) tumors mean that NSCLC patients at the same stage can have different chemotherapy prognoses. Accurate predictive models could recognize NSCLC patients likely to respond to chemotherapy so that they can be given personalized and effective treatment. We propose to identify predictive imaging biomarkers from pre-treatment CT images and construct a radiomic model that can predict the chemotherapy response in NSCLC. This single-center cohort study included 280 NSCLC patients who received first-line chemotherapy treatment. Non-contrast CT images were taken before and after the chemotherapy, and clinical information were collected. Based on the Response Evaluation Criteria in Solid Tumors and clinical criteria, the responses were classified into two categories: response (n = 145) and progression (n = 135), then all data were divided into two cohorts: training cohort (224 patients) and independent test cohort (56 patients). In total, 1629 features characterizing the tumor phenotype were extracted from a cube containing the tumor lesion cropped from the pre-chemotherapy CT images. After dimensionality reduction, predictive models of the chemotherapy response of NSCLC with different feature selection methods and different machine-learning classifiers (support vector machine, random forest, and logistic regression) were constructed. For the independent test cohort, the predictive model based on a random-forest classifier with 20 radiomic features achieved the best performance, with an accuracy of 85.7% and an area under the receiver operating characteristic curve of 0.941 (95% confidence interval, 0.898–0.982). Of the 20 selected features, four were first-order statistics of image intensity and the others were texture features. For nine features, there were significant differences between the response and progression groups (p < 0.001). In the response group, three features, indicating heterogeneity, were overrepresented and one feature indicating homogeneity was underrepresented. The proposed radiomic model with pre-chemotherapy CT features can predict the chemotherapy response of patients with non-small cell lung cancer. This radiomic model can help to stratify patients with NSCLC, thereby offering the prospect of better treatment.

Predicting chemotherapy response in non-small-cell lung cancer via computed tomography radiomic features: Peritumoral, intratumoral, or combined?

“…Second, the segmentation of intra-and peritumoral regions is semi-automatic, and some features might be dependent on segmentation results. Automatic segmentation by deep learning and extraction of features from the bounding box may address this problem ( 42 ). Third, only machine learning methods are employed.…”

Early COPD Risk Decision for Adults Aged From 40 to 79 Years Based on Lung Radiomics Features

“…Compared with PFT, computed tomography (CT) has been regarded as the most effective modality for characterizing and quantifying COPD ( 24 ), for example, quantitatively analyzing airway disease and emphysema in patients with COPD. Since the concept of radiomics was formally proposed in 2012 ( 25 ), radiomics of the chest CT images has been widely used for the chemotherapy response prediction in non-small-cell lung cancer ( 26 ) and pathology invasiveness prediction in patients with solitary pulmonary nodules ( 27 ). Recently, radiomics also has been used in COPD for survival prediction ( 28 , 29 ), COPD presence prediction ( 30 ), and the COPD exacerbations ( 31 ).…”

Development and Validation of a Radiomics Nomogram for Differentiating Pulmonary Cryptococcosis and Lung Adenocarcinoma in Solitary Pulmonary Solid Nodule

“…Additionally, the segmentation of ROI in our study was only confined to the nodule itself, which only provided a limited intra-lesion information for differentiation. However, there were previous studies that indicated that the extra-nodule region contained massive biological information that was instrumental to predict the treatment response and overall survival ( 35 , 36 ). The information may also assist to determine the nature of the nodule, which needs to extract external radiomics features of the lesion in further research to confirm.…”