Background: To establish a radiomic approach to identify epidermal growth factor receptor (EGFR) mutation status in lung adenocarcinoma patients based on CT images, and to distinguish exon-19 deletion and exon-21 L858R mutation.Methods: Two hundred sixty-three patients who underwent pre-surgical contrast-enhanced CT and molecular testing were included, and randomly divided into the training (80%) and test (20%) cohort.Tumor images were three-dimensionally segmented to extract 1,672 radiomic features. Clinical features (age, gender, and smoking history) were added to build classification models together with radiomic features.Subsequently, the top-10 most relevant features were used to establish classifiers. For the classifying tasks including EGFR mutation, exon-19 deletion, and exon-21 L858R mutation, four logistic regression models were established for each task. Results:The training and test cohort consisted of 210 and 53 patients, respectively. Among the established models, the highest accuracy and sensitivity among the four models were 75.5% (61.7-86.2%) and 92.9% (76.5-99.1%) to classify EGFR mutation, respectively. The highest specificity values were 86.7% (69.3-96.2%) and 70.4% (49.8-86.3%) to classify exon-19 deletion and exon-21 L858R mutation, respectively.Conclusions: CT radiomics can sensitively identify the presence of EGFR mutation, and increase the certainty of distinguishing exon-19 deletion and exon-21 L858R mutation in lung adenocarcinoma patients.CT radiomics may become a helpful non-invasive biomarker to select EGFR mutation patients for invasive sampling.

Purpose: To develop a machine learning-derived radiomics approach to simultaneously discriminate epidermal growth factor receptor (EGFR), Kirsten rat sarcoma viral oncogene (KRAS), Erb-B2 receptor tyrosine kinase 2 (ERBB2), and tumor protein 53 (TP53) genetic mutations in patients with non-small cell lung cancer (NSCLC). Methods: This study included consecutive patients from April 2018 to June 2020 who had histologically confirmed NSCLC, and underwent pre-surgical contrast-enhanced CT and post-surgical next-generation sequencing (NGS) tests to determine the presence of EGFR, KRAS, ERBB2, and TP53 mutations. A dedicated radiomics analysis package extracted 1672 radiomic features in three dimensions. Discriminative models were established using the least absolute shrinkage and selection operator to determine the presence of EGFR, KRAS, ERBB2, and TP53 mutations, based on radiomic features and relevant clinical factors. Results: In 134 patients (63.6 ± 8.9 years), the 20 most relevant radiomic features (13 for KRAS) to mutations were selected to construct models. The areas under the curve (AUCs) of the combined model (radiomic features and relevant clinical factors) for discriminating EGFR, KRAS, ERBB2, and TP53 mutations were 0.78 (95% CI: 0.70–0.86), 0.81 (0.69–0.93), 0.87 (0.78–0.95), and 0.84 (0.78–0.91), respectively. In particular, the specificity to exclude EGFR mutations was 0.96 (0.87–0.99). The sensitivity to determine KRAS, ERBB2, and TP53 mutations ranged from 0.82 (0.69–90) to 0.92 (0.62–0.99). Conclusions: Machine learning-derived 3D radiomics can simultaneously discriminate the presence of EGFR, KRAS, ERBB2, and TP53 mutations in patients with NSCLC. This noninvasive and low-cost approach may be helpful in screening patients before invasive sampling and NGS testing.

ObjectivesThe aim was to determine whether the dual-energy CT radiomics model derived from an iodine map (IM) has incremental diagnostic value for the model based on 120-kV equivalent mixed images (120 kVp) in preoperative restaging of serosal invasion with locally advanced gastric cancer (LAGC) after neoadjuvant chemotherapy (NAC).MethodsA total of 155 patients (110 in the training cohort and 45 in the testing cohort) with LAGC who had standard NAC before surgery were retrospectively enrolled. All CT images were analyzed by two radiologists for manual classification. Volumes of interests (VOIs) were delineated semi-automatically, and 1,226 radiomics features were extracted from every segmented lesion in both IM and 120 kVp images, respectively. Spearman’s correlation analysis and the least absolute shrinkage and selection operator (LASSO) penalized logistic regression were implemented for filtering unstable and redundant features and screening out vital features. Two predictive models (120 kVp and IM-120 kVp) based on 120 kVp selected features only and 120 kVp combined with IM selected features were established by multivariate logistic regression analysis. We then build a combination model (ComModel) developed with IM-120 kVp signature and ycT. The performance of these three models and manual classification were evaluated and compared.ResultThree radiomics models showed great predictive accuracy and performance in both the training and testing cohorts (ComModel: AUC: training, 0.953, testing, 0.914; IM-120 kVp: AUC: training, 0.953, testing, 0.879; 120 kVp: AUC: training, 0.940, testing, 0.831). All these models showed higher diagnostic accuracy (ComModel: 88.9%, IM-120 kVp: 84.4%, 120 kVp: 80.0%) than manual classification (68.9%) in the testing group. ComModel and IM-120 kVp model had better performances than manual classification both in the training (both p<0.001) and testing cohorts (p<0.001 and p=0.034, respectively).ConclusionsDual-energy CT-based radiomics models demonstrated convincible diagnostic performance in differentiating serosal invasion in preoperative restaging for LAGC. The radiomics features derived from IM showed great potential for improving the diagnostic capability.

ObjectiveTo develop and validate a dual-energy computed tomography (DECT) derived radiomics model to predict peritoneal metastasis (PM) in patients with gastric cancer (GC).MethodsThis retrospective study recruited 239 GC (non-PM = 174, PM = 65) patients with histopathological confirmation for peritoneal status from January 2015 to December 2019. All patients were randomly divided into a training cohort (n = 160) and a testing cohort (n = 79). Standardized iodine-uptake (IU) images and 120-kV-equivalent mixed images (simulating conventional CT images) from portal-venous and delayed phases were used for analysis. Two regions of interest (ROIs) including the peritoneal area and the primary tumor were independently delineated. Subsequently, 1691 and 1226 radiomics features were extracted from the peritoneal area and the primary tumor from IU and mixed images on each phase. Boruta and Spearman correlation analysis were used for feature selection. Three radiomics models were established, including the R_IU model for IU images, the R_MIX model for mixed images and the combined radiomics model (the R_comb model). Random forest was used to tune the optimal radiomics model. The performance of the clinical model and human experts to assess PM was also recorded.ResultsFourteen and three radiomics features with low redundancy and high importance were extracted from the IU and mixed images, respectively. The R_IU model showed significantly better performance to predict PM than the R_MIX model in the training cohort (AUC, 0.981 vs. 0.917, p = 0.034). No improvement was observed in the R_comb model (AUC = 0.967). The R_IU model was the optimal radiomics model which showed no overfitting in the testing cohort (AUC = 0.967, p = 0.528). The R_IU model demonstrated significantly higher predictive value on peritoneal status than the clinical model and human experts in the testing cohort (AUC, 0.785, p = 0.005; AUC, 0.732, p <0.001, respectively).ConclusionDECT derived radiomics could serve as a non-invasive and easy-to-use biomarker to preoperatively predict PM for GC, providing opportunity for those patients to tailor appropriate treatment.

PurposeThis study aimed to evaluate the feasibility of differentiating the atrial fibrillation (AF) subtype and preliminary explore the prognostic value of AF recurrence after ablation using radiomics models based on epicardial adipose tissue around the left atrium (LA-EAT) of cardiac CT images.MethodThe cardiac CT images of 314 patients were collected wherein 251 and 63 cases were randomly enrolled in the training and validation cohorts, respectively. Mutual information and the random forest algorithm were used to screen for the radiomic features and construct the radiomics signature. Radiomics models reflecting the features of LA-EAT were built to differentiate the AF subtype, and the multivariable logistic regression model was adopted to integrate the radiomics signature and volume information. The same methodology and algorithm were applied to the radiomic features to explore the ability for predicting AF recurrence.ResultsThe predictive model constructed by integrating the radiomic features and volume information using a radiomics nomogram showed the best ability in differentiating AF subtype in the training [AUC, 0.915; 95% confidence interval (CI), 0.880–0.951] and validation (AUC, 0.853; 95% CI, 0.755–0.951) cohorts. The radiomic features have shown convincible predictive ability of AF recurrence in both training (AUC, 0.808; 95% CI, 0.750–0.866) and validation (AUC, 0.793; 95% CI, 0.654–0.931) cohorts.ConclusionsThe LA-EAT radiomic signatures are a promising tool in the differentiation of AF subtype and prediction of AF recurrence, which may have clinical implications in the early diagnosis of AF subtype and disease management.

No abstract

Objectives: The purpose is to establish and validate a machine-learning-derived radiomics approach to determine the existence of atrial fibrillation (AF) by analyzing epicardial adipose tissue (EAT) in CT images. Methods: Patients with AF based on electrocardiographic tracing who underwent contrast-enhanced (n = 200) or non-enhanced (n = 300) chest CT scans were analyzed retrospectively. After EAT segmentation and radiomics feature extraction, the segmented EAT yielded 1,691 radiomics features. The most contributive features to AF were selected by the Boruta algorithm and machine-learning-based random forest algorithm, and combined to construct a radiomics signature (EAT-score). Multivariate logistic regression was used to build clinical factor and nested models. Results: In the test cohort of contrast-enhanced scanning (n = 60/200), the AUC of EAT-score for identifying patients with AF was 0.92 (95%CI:0.84–1.00), higher than 0.71 (0.58–0.85) of the clinical factor model (total cholesterol and body mass index) (DeLong’s p = 0.01), and higher than 0.73 (0.61–0.86) of the EAT volume model (p = 0.01). In the test cohort of non-enhanced scanning (n = 100/300), the AUC of EAT-score was 0.85 (0.77–0.92), higher than that of the CT attenuation model (p < 0.001). The two nested models (EAT-score +volume and EAT-score +volume+clinical factors) for contrast-enhanced scan and one (EAT-score +CT attenuation) for non-enhanced scan showed similar AUCs with that of EAT-score (all p > 0.05). Conclusion: EAT-score generated by machine-learning-based radiomics achieved high performance in identifying patients with AF. Advances in knowledge: A radiomics analysis based on machine learning allows for the identification of AF on the EAT in contrast-enhanced and non-enhanced chest CT.

No abstract