Comparison of prediction models with radiological semantic features and radiomics in lung cancer diagnosis of the pulmonary nodules: a case-control study

Abstract

Purpose To compare the ability of radiological semantic and quantitative texture features in lung cancer diagnosis of pulmonary nodules. Materials and methods A total of N = 121 subjects with confirmed non-small-cell lung cancer were matched with 117 controls based on age and gender. Radiological semantic and quantitative texture features were extracted from CT images with or without contrast enhancement. Three different models were compared using LASSO logistic regression: “CS” using clinical and semantic variables, “T” using texture features, and “CST” using clinical, semantic, and texture variables. For each model, we performed 100 trials of fivefold cross-validation and the average receiver operating curve was accessed. The AUC of the cross-validation study (AUCCV) was calculated together with its 95% confidence interval. Results The AUCCV (and 95% confidence interval) for models T, CS, and CST was 0.85 (0.71–0.96), 0.88 (0.77–0.96), and 0.88 (0.77–0.97), respectively. After separating the data into two groups with or without contrast enhancement, the AUC (without cross-validation) of the model T was 0.86 both for images with and without contrast enhancement, suggesting that contrast enhancement did not impact the utility of texture analysis. Conclusions The models with semantic and texture features provided cross-validated AUCs of 0.85–0.88 for classification of benign versus cancerous nodules, showing potential in aiding the management of patients.

Value of Shape and Texture Features from 18F-FDG PET/CT to Discriminate between Benign and Malignant Solitary Pulmonary Nodules: An Experimental Evaluation

“…In our experiments, shape and texture features were able to improve the overall accuracy of the prediction models by 2.2-11.2 pp. The increase in CT accuracy found here is comparable, in magnitude, with that reported by Wu et al [25] and Balagurunathan et al [23]. However, our overall accuracy was, in absolute terms, lower than that reported in the above references, most probably because those results were obtained with standard CT scans, ours with low-dose ones.…”

“…Few studies, however, have addressed the problem of quantifying the gain that shape and texture features from CT and/or PET/CT may provide compared with conventional imaging features alone. Among them, Wu et al [25] reported that adding texture features from CT to clinical and semantic variables could lead to a 0.03 increase of the area under the curve (AUC), whereas Balagurunathan et al [23] determined that a combination of size, shape, and texture features could increment the AUC from 0.87 to 0.90 compared with a model based on longest diameter and volume of the nodule only.…”

A diagnostic model for coronavirus disease 2019 (COVID-19) based on radiological semantic and clinical features: a multi-center study

“…The decision curve shows that if the threshold probability is over 10%, the application of the combination of clinical and radiological model (CR model) to diagnose COVID-19 adds more benefit than the clinical model (C model) and radiological model (R model) radiological semantic features can overcome the image discrepancy caused by different scanning parameters and/or different CT vendors. A previous study [28] also indicated that models based on semantic features determined by an experienced thoracic radiologist slightly outperformed models based on computed texture features alone.…”

PET/CT Radiomics in Lung Cancer: An Overview

“…Traditionally, the evaluation involved manual assessment of some key image characteristics at CT that are considered strong indicators of benignity or malignancy [60]. In this scenario, recent studies have shown that prediction models based on quantitative imaging features can help differentiate between benign, malignant, and inflammatory pulmonary nodules [37,50,[61][62][63][64].…”