Prediction of EGFR mutations by conventional CT-features in advanced pulmonary adenocarcinoma

Predicting epidermal growth factor receptor (EGFR) mutation status in non-small cell lung cancer (NSCLC) patients through logistic regression: a model incorporating clinical characteristics, computed tomography (CT) imaging features, and tumor marker levels

Background

Approximately 60% of Asian populations with non-small cell lung cancer (NSCLC) harbor epidermal growth factor receptor (EGFR) gene mutations, marking it as a pivotal target for genotype-directed therapies. Currently, determining EGFR mutation status relies on DNA sequencing of histological or cytological specimens. This study presents a predictive model integrating clinical parameters, computed tomography (CT) characteristics, and serum tumor markers to forecast EGFR mutation status in NSCLC patients.

Methods

Retrospective data collection was conducted on NSCLC patients diagnosed between January 2018 and June 2019 at the First Affiliated Hospital of Zhengzhou University, with available molecular pathology results. Clinical information, CT imaging features, and serum tumor marker levels were compiled. Four distinct models were employed in constructing the diagnostic model. Model diagnostic efficacy was assessed through receiver operating characteristic (ROC) area under the curve (AUC) values and calibration curves. DeLong's test was administered to validate model robustness.

Results

Our study encompassed 748 participants. Logistic regression modeling, trained with the aforementioned variables, demonstrated remarkable predictive capability, achieving an AUC of 0.805 (95% confidence interval (CI) [0.766-0.844]) in the primary cohort and 0.753 (95% CI [0.687-0.818]) in the validation cohort. Calibration plots suggested a favorable fit of the model to the data.

Conclusions

The developed logistic regression model emerges as a promising tool for forecasting EGFR mutation status. It holds potential to aid clinicians in more precisely identifying patients likely to benefit from EGFR molecular testing and facilitating targeted therapy decision-making, particularly in scenarios where molecular testing is impractical or inaccessible.

Predictive value of spectral computed tomography parameters for EGFR gene mutation in non-small-cell lung cancer

AIM

To explore the predictive value of morphological signs and quantitative parameters from spectral CT for EGFR gene mutations in intermediate and advanced non-small-cell lung cancer (NSCLC).

MATERIALS AND METHODS

This retrospective observational study included patients with intermediate or advanced NSCLC at Xinjiang Medical University Affiliated Tumor Hospital between January 2017 and December 2019. The patients were divided into the EGFR gene mutation-positive and -negative groups.

RESULTS

Seventy-nine patients aged 60.75 ± 9.66 years old were included: 32 were EGFR mutation-positive, and 47 were negative. There were significant differences in pathological stage (P<0.001), tumor diameter (P=0.019), lobulation sign, intrapulmonary metastasis, mediastinal lymph node metastasis, distant metastasis (P<0.001), bone metastasis (P<0.001), arterial phase normalized iodine concentration (NIC) (P=0.001), venous phase NIC (P=0.001), slope of the energy spectrum curve (λ) (P<0.001), and CT value at 70 keV in arterial phase (P=0.004) and venous phase (P=0.003) between the EGFR mutation-positive and -negative patients. The multivariable logistic regression analysis showed that intrapulmonary metastasis, distant metastasis, venous phase NIC, venous phase λ, and pathological stage were independent factors predicting EGFR gene mutations, with high diagnostic power (AUC = 0.975, 91.5% sensitivity, and 90.6% specificity).

CONCLUSION

The pathological stage and the spectral CT parameters of intrapulmonary metastasis, distant metastasis, venous phase NIC, and venous phase λ might pre-operatively predict EGFR gene mutations in intermediate and advanced NSCLC.

Transfer learning-based PET/CT three-dimensional convolutional neural network fusion of image and clinical information for prediction of EGFR mutation in lung adenocarcinoma

BACKGROUND

To introduce a three-dimensional convolutional neural network (3D CNN) leveraging transfer learning for fusing PET/CT images and clinical data to predict EGFR mutation status in lung adenocarcinoma (LADC).

METHODS

Retrospective data from 516 LADC patients, encompassing preoperative PET/CT images, clinical information, and EGFR mutation status, were divided into training (n = 404) and test sets (n = 112). Several deep learning models were developed utilizing transfer learning, involving CT-only and PET-only models. A dual-stream model fusing PET and CT and a three-stream transfer learning model (TS_TL) integrating clinical data were also developed. Image preprocessing includes semi-automatic segmentation, resampling, and image cropping. Considering the impact of class imbalance, the performance of the model was evaluated using ROC curves and AUC values.

RESULTS

TS_TL model demonstrated promising performance in predicting the EGFR mutation status, with an AUC of 0.883 (95%CI = 0.849-0.917) in the training set and 0.730 (95%CI = 0.629-0.830) in the independent test set. Particularly in advanced LADC, the model achieved an AUC of 0.871 (95%CI = 0.823-0.919) in the training set and 0.760 (95%CI = 0.638-0.881) in the test set. The model identified distinct activation areas in solid or subsolid lesions associated with wild and mutant types. Additionally, the patterns captured by the model were significantly altered by effective tyrosine kinase inhibitors treatment, leading to notable changes in predicted mutation probabilities.

CONCLUSION

PET/CT deep learning model can act as a tool for predicting EGFR mutation in LADC. Additionally, it offers clinicians insights for treatment decisions through evaluations both before and after treatment.

A clinical-radiological predictive model for solitary pulmonary nodules and the relationship between radiological features and pathological subtype

AIM

To develop a clinical-radiological model to predict the malignancy of solitary pulmonary nodules (SPNs) and to evaluate the accuracy of chest computed tomography imaging characteristics of SPN in diagnosing pathological type.

MATERIALS AND METHODS

The predictive model was developed using a retrospective cohort of 601 SPN patients (Group A) between July 2015 and July 2020. The established model was tested using a second retrospective cohort of 124 patients between August 2020 and August 2021 (Group B). The radiological characteristics of all adenocarcinomas in two groups were analysed to determine the correlation between radiological and pathological characteristics.

RESULTS

Malignant nodules were found in 78.87% of cases and benign in 21.13%. Two clinical characteristics (age and gender) and four radiological characteristics (calcification, vascular convergence, pleural retraction sign, and density) were identified as independent predictors of malignancy in patients with SPN using logistic regression analysis. The area under the receiver operating characteristic curve (0.748) of the present model was greater than the other two reported models. Diameter, spiculation, lobulation, vascular convergence, and pleural retraction signs differed significantly among pre-invasive lesions, minimally invasive adenocarcinoma, and invasive adenocarcinoma. Only diameter and density were significantly different among invasive adenocarcinoma subtypes.

CONCLUSIONS

Older age, male gender, no calcification, vascular convergence, pleural contraction sign, and lower density were independent malignancy predictors of SPNs. Furthermore, the pathological classification can be clarified based on the radiological characteristics of SPN, providing a new option for the prevention and treatment of early lung cancer.

Establishing and validation of the VBV score for assessing Lung ground-glass nodules based on high-resolution computed tomography

BACKGROUND

The widespread utilization of chest High-resolution Computed Tomography (HRCT) has prompted detection of pulmonary ground-glass nodules (GGNs) in otherwise asymptomatic individuals. We aimed to establish a simple clinical risk score model for assessing GGNs based on HRCT.

METHODS

We retrospectively analyzed 574 GGNs in 574 patients undergoing HOOK-WIRE puncture and pulmonary nodule surgery from January 2014 to November 2018. Clinical characteristics and imaging features of the GGNs were assessed. We analyzed the differences between malignant and benign nodules using binary logistic regression analysis and constructed a simple risk score model, the VBV Score, for predicting the malignancy status of GGNs. Then, we validated this model via other 1200 GGNs in 1041 patients collected from three independent clinical centers in 2022.

RESULTS

For the exploratory phase of this study, out of the 574 GGNs, 481 were malignant and 93 were benign. Vacuole sign, air bronchogram, and intra-nodular vessel sign were important indicators of malignancy in GGNs. Then, we derived a VBV Score = vacuole sign + air bronchogram + intra-nodular vessel sign, to predict the malignancy of GGNs, with a sensitivity, specificity, and accuracy of 95.6%, 80.6%, and 93.2%, respectively. We also validated it on other 1200 GGNs, with a sensitivity, specificity, and accuracy of 96.0%, 82.6%, and 95.0%, respectively.

CONCLUSIONS

Vacuole sign, air bronchogram, and intra-nodular vessel sign were important indicators of malignancy in GGNs. VBV Score showed good sensitivity, specificity, and accuracy for differentiating benign and malignant pulmonary GGNs.

Establishment and Evaluation of EGFR Mutation Prediction Model Based on Tumor Markers and CT Features in NSCLC

Background

Lung cancer has become one of the leading causes of cancer deaths worldwide. EGFR gene mutation has been reported in up to 60% of Asian populations and is currently one of the main targets for genotype-targeted therapy for NSCLC.

Objective

The objective is to determine if a complex model combining serum tumor makers and computed tomographic (CT) features can predict epidermal growth factor receptor (EGFR) mutation with higher accuracy. Material and Methods. Retrospective analysis of the data of patients diagnosed with in nonsmall cell lung cancer (NSCLC) by EGFR gene testing was carried out in the Department of Thoracic Surgery, Jinan Central Hospital. Multivariate logistic regression analysis was used to determine the independent predictors of EGFR mutations, and logistic regression prediction models were developed. The subject operating characteristic curve (ROC) was plotted, and the area under the curve (AUC) was calculated to assess the accuracy and clinical application of the EGFR mutation prediction model.

Results

Logistic regression analysis identified the predictive factors of EGFR mutation including nonsmoking, high expression level of Carcinoembryonic Antigen (CEA), low expression level of cytokeratin 19 fragments (CYFRA21-1), and subsolid density containing ground-glass opacity (GGO) component. Using the results of multivariate logistic regression analysis, we built a statistically determined clinical prediction model. The AUC of the complex prediction model increased significantly from 0.735 to 0.813 (p = 0.014) when CT features are added and from 0.612 to 0.813 (p < 0.001) when serum variables are added. When P was 0.441, the sensitivity was 86.7% and the specificity was 65.8%.

Conclusion

A complex model combining serum tumor makers and CT features is more accurate in predicting EGFR mutation status in NSCLC patients than using either serum variables or imaging features alone. Our finding for EGFR mutation is urgently needed and helpful in clinical practice.

Accurate prediction of epidermal growth factor receptor mutation status in early-stage lung adenocarcinoma, using radiomics and clinical features

OBJECTIVES

To develop a nomogram based on CT radiomics and clinical features to predict the epidermal growth factor receptor (EGFR) mutations in early-stage lung adenocarcinomas.

METHODS

A retrospective analysis of postoperative patients with pathologically confirmed lung adenocarcinoma, which had been tested for EGFR mutations was performed from January 2015 to December 2015. Patients were randomly assigned to training and validation cohorts. A total of 1,078 radiomics features were extracted. least absolute shrinkage and selection operator (LASSO) regression analysis was applied to select clinical and radiomics features, and to establish predictive models. The radiomics score (rad-score) of each patient was calculated. The discrimination of the model was evaluated with area under the curve.

RESULTS

1092 patients (444 men and 648 women; mean age: 59.59±9.6) were enrolled. The radiomics signature consisted of 28 radiomics features and emphysema. The mean validation cohort result of the rad-score for patients with EGFR mutations (0.814±0.988) was significantly higher than those with EGFR wild-type (0.315±1.237; p = 0.001). When combined with clinical features, LASSO regression analysis revealed four radiomics features, emphysema, and three clinical features including sex, age, and histologic subtype as associated with to EGFR mutation status. The nomogram that combined radiomics and clinical features significantly improved the predictive discrimination (AUC: 0.723), which is better than that of the radiomics signature alone (AUC: 0.646).

CONCLUSION

A relationship between selected radiomics features and EGFR mutant lung adenocarcinomas is demonstrated. A nomogram, combining radiomics features and clinical features for EGFR prediction in early-stage lung adenocarcinomas, has shown a moderate discriminatory efficiency and high sensitivity, providing additional information for clinicians.

Clinical and CT patterns to predict EGFR mutation in patients with non-small cell lung cancer: A systematic literature review and meta-analysis

Purpose

This study aims to determine if the presence of specific clinical and computed tomography (CT) patterns are associated with epidermal growth factor receptor (EGFR) mutation in patients with non-small cell lung cancer.

Methods

A systematic literature review and meta-analysis was carried out in 6 databases between January 2002 and July 2021. The relationship between clinical and CT patterns to detect EGFR mutation was measured and pooled using odds ratios (OR). These results were used to build several mathematical models to predict EGFR mutation.

Results

34 retrospective diagnostic accuracy studies met the inclusion and exclusion criteria. The results showed that ground-glass opacities (GGO) have an OR of 1.86 (95%CI 1.34 −2.57), air bronchogram OR 1.60 (95%CI 1.38 – 1.85), vascular convergence OR 1.39 (95%CI 1.12 – 1.74), pleural retraction OR 1.99 (95%CI 1.72 – 2.31), spiculation OR 1.42 (95%CI 1.19 – 1.70), cavitation OR 0.70 (95%CI 0.57 – 0.86), early disease stage OR 1.58 (95%CI 1.14 – 2.18), non-smoker status OR 2.79 (95%CI 2.34 – 3.31), female gender OR 2.33 (95%CI 1.97 – 2.75). A mathematical model was built, including all clinical and CT patterns assessed, showing an area under the curve (AUC) of 0.81.

Conclusions

GGO, air bronchogram, vascular convergence, pleural retraction, spiculated margins, early disease stage, female gender, and non-smoking status are significant risk factors for EGFR mutation. At the same time, cavitation is a protective factor for EGFR mutation. The mathematical model built acts as a good predictor for EGFR mutation in patients with lung adenocarcinoma.

•

GGO, air bronchogram, vascular convergence, pleural retraction, and spiculated margins, are risk factors for EGFR mutation.

•

Early disease stage, female gender and non-smoking status are risk factors for EGFR mutation.

•

Cavitation is a protective factor for EGFR mutation.

Computed Tomography Morphological Classification of Lung Adenocarcinoma and Its Correlation with Epidermal Growth Factor Receptor Mutation Status: A Report of 1075 Cases

Background

Many delayed diagnoses of lung adenocarcinoma (LADC) are identified due to poor understanding of protean imaging findings. Moreover, clarifying the relationship between computed tomography (CT) morphological classification and epidermal growth factor receptor (EGFR) mutations of LADC might inform therapeutic decision-making while obtaining pathological specimens is difficult. Here, we retrospectively analyzed CT manifestations of LADC and investigated the morphological classification of tumors in relation to EGFR mutation status.

Methods

We included 1075 LADC patients undergoing chest CT and EGFR genotype examinations from January 2013 to January 2019. CT morphological characteristics of tumors were carefully evaluated and their correlation with EGFR mutation status was analyzed using the chi-squared test.

Results

Tumors were divided into eight types: I (peripheral solid nodule/mass; 526/1075, 48.93%), II (central solid nodule/mass; 220/1075, 20.47%), III (subsolid nodule/mass; 92/1075, 8.56%), IV (focal consolidation; 32/1075, 2.98%), V (cystic airspace; 14/1075, 1.30%), VI (multiple lesions with similar appearances to I–V; 85/1075, 7.91%), VII (diffuse consolidation; 53/1075, 4.93%), VIII (occult lesion usually obscured by nonobstructive atelectasis; 53/1075, 4.93%). Type III and IV tumors were more frequent in patients with EGFR mutation, whereas type II and VII tumors were more common in patients without EGFR mutation (all P < 0.05). However, we did not identify any significant associations between other tumor types and EGFR mutation status (all P > 0.05). Among patients with type VI tumors, EGFR mutation status was closely related to tumor density (all P < 0.05). Furthermore, type VII tumors were associated with 19 deletion mutation positive and non-L858R mutation positive (all P < 0.05).

Conclusion

LADC can be categorized into eight types based on CT imaging. Improving our understanding of the morphological classification and correlation with EGFR mutation status may contribute to the accurate diagnosis of LADC, while suggesting the presence of underlying EGFR genetic mutations.

Value of radiomics model based on multi-parametric magnetic resonance imaging in predicting epidermal growth factor receptor mutation status in patients with lung adenocarcinoma

BACKGROUND

The epidermal growth factor receptor (EGFR) is an important therapeutic target for patients with non-small-cell lung cancer (NSCLC). Radiomics and radiogenomics have emerged as attractive research topics aiming to extract mineable high-dimensional features from medical images and show potential to correlate with the gene mutation. Herein, we aim to develop a magnetic resonance imaging (MRI)-based radiomics model for pretreatment prediction of the EGFR status in patients with lung adenocarcinoma.

METHODS

A total of 92 patients with pathologically confirmed lung adenocarcinoma were retrospectively enrolled in this study. EGFR genotype was analyzed by sequence testing. All patients were randomized into training and test group in a 7:3 ratio using the R software. Radiomics features were extracted from T2 weighted imaging (T2WI), diffusion-weighted imaging (DWI), and apparent diffusion coefficient (ADC); radiomics signatures were built using the least absolute shrinkage and selection operator (LASSO) and logistic regression. Preoperative clinical factors and image features associated with EGFR were also evaluated. A nomogram including sex, smoking status, and radiomics signatures was constructed. A total of five radiomics models were built, and the area under the curve (AUC) was used to evaluate their performance of EGFR mutation prediction.

RESULTS

Among the three single-sequence models, the ADC model showed the best prediction performance. The AUCs of the ADC, DWI, T2WI prediction model in the test cohort were 0.805 (95% CI: 0.610 to 1.000), 0.722 (95% CI: 0.519 to 0.924), and 0.655 (95% CI: 0.438 to 0.872), respectively. Compared with the single-sequence model, the multi-sequence prediction model showed better performed [AUCtest =0.838 (95% CI: 0.685 to 0.992)]. The AUC of the nomogram in the training group was 0.925 (95% CI: 0.855 to 0.994) and 0.727 (95% CI: 0.531 to 0.924) in the test group, respectively.

CONCLUSIONS

The radiomics model based on MRI might have the potential to predict EGFR mutation in patients with lung adenocarcinoma. The multi-sequence model had better performance than other models.

Radiogenomic Models Using Machine Learning Techniques to Predict EGFR Mutations in Non-Small Cell Lung Cancer

BACKGROUND

The purpose of this study was to build radiogenomics models from texture signatures derived from computed tomography (CT) and ¹⁸F-FDG PET-CT (FDG PET-CT) images of non-small cell lung cancer (NSCLC) with and without epidermal growth factor receptor (EGFR) mutations.

METHODS

Fifty patients diagnosed with NSCLC between 2011 and 2015 and with known EGFR mutation status were retrospectively identified. Texture features extracted from pretreatment CT and FDG PET-CT images by manual contouring of the primary tumor were used to develop multivariate logistic regression (LR) models to predict EGFR mutations in exon 19 and exon 20.

RESULTS

An LR model evaluating FDG PET-texture features was able to differentiate EGFR mutant from wild type with an area under the curve (AUC), sensitivity, specificity, and accuracy of 0.87, 0.76, 0.66, and 0.71, respectively. The model derived from CT texture features had an AUC, sensitivity, specificity, and accuracy of 0.83, 0.84, 0.73, and 0.78, respectively. FDG PET-texture features that could discriminate between mutations in EGFR exon 19 and 21 demonstrated AUC, sensitivity, specificity, and accuracy of 0.86, 0.84, 0.73, and 0.78, respectively. Based on CT texture features, the AUC, sensitivity, specificity, and accuracy were 0.75, 0.81, 0.69, and 0.75, respectively.

CONCLUSION

Non-small cell lung cancer texture analysis using FGD-PET and CT images can identify tumors with mutations in EGFR. Imaging signatures could be valuable for pretreatment assessment and prognosis in precision therapy.