CT and clinical characteristics that predict risk of EGFR mutation in non-small cell lung cancer: a systematic review and meta-analysis. Int J Clin Oncol. 2019;24:649-659. [PMID: 30835006 DOI: 10.1007/s10147-019-01403-3]

Prediction of EGFR mutations in non-small cell lung cancer: a nomogram based on 18F-FDG PET and thin-section CT radiomics with machine learning

Background

This study aimed to develop and validate radiomics-based nomograms for the identification of EGFR mutations in non-small cell lung cancer (NSCLC).

Methods

A retrospective analysis was performed on 313 NSCLC patients, who were randomly divided into training (n = 250) and validation (n = 63) groups. Radiomic features were extracted from 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) and thin-section computed tomography (CT) scans. After selecting optimal radiomic features, four machine learning algorithms, including logistic regression (LR), random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGBoost), were used to develop and validate radiomics models. A combined model, incorporating the Rad score from the best performing radiomics model with clinical and radiological features, was then formulated. Finally, the integrated nomogram was generated. Its predictive performance and clinical utility were evaluated using receiver operating characteristic curves, calibration curves, and decision curve analysis.

Results

Among the radiomics models, the RF model showed the best performance with AUCs of 0.785 (95% CI, 0.726-0.844) and 0.776 (95% CI, 0.662-0.889) in the training and validation groups, respectively. The AUCs of the clinical and radiological models in both groups were 0.711 (95% CI, 0.645-0.776) and 0.758 (95% CI, 0.627-0.890), and 0.632 (95% CI, 0.564-0.699) and 0.677 (95% CI, 0.531-0.822), respectively. The combined model achieved the highest AUCs of 0.872 (95% CI, 0.829-0.915) and 0.831 (95% CI, 0.723-0.940) in the training and validation groups, respectively. The DeLong test confirmed the superiority of the combined model over the other three models. Both the calibration curve and the DCA indicated that the radiomics nomogram was consistent and clinically useful.

Conclusions

Radiomics combined with machine learning and based on 18F-FDG PET/CT images can effectively determine EGFR mutation status in NSCLC patients. Radiomics-based nomograms provide a non-invasive and visually intuitive prediction tool for screening NSCLC patients with EGFR mutations in a clinical setting.

CT and MRI bimodal radiomics for predicting EGFR status in NSCLC patients with brain metastases: A multicenter study

BACKGROUND

Leveraging the radiomics information from non-small cell lung cancer (NSCLC) primary lesion and brain metastasis (BM) to develop and validate a bimodal radiomics nomogram that can accurately predict epidermal growth factor receptor (EGFR) status.

METHODS

A total of 309 NSCLC patients with BM from three independent centers were recruited. Among them, the patients of Center I were randomly allocated into the training and internal test cohorts in a 7:3 ratio. Meanwhile, the patients from Center Ⅱ and Center Ⅲ collectively constitute the external test cohort. All chest CT and brain MRI images of each patient were obtained for image registration and sequence combination within a single modality. After image preprocessing, 1037 radiomics features were extracted from each single sequence. Six machine learning algorithms were used to construct radiomics signatures for CT and MRI respectively. The best CT and MRI radiomics signatures were fitted to establish the bimodal radiomics nomogram for predicting the EGFR status.

RESULTS

The contrast-enhanced (CE) eXtreme gradient boosting (XG Boost) and T2-weighted imaging (T2WI) + T1-weighted contrast-enhanced imaging (T1CE) random forest models were chosen as the radiomics signature representing primary lesion and BM. Both models were found to be independent predictors of EGFR mutation. The bimodal radiomics nomogram, which incorporated CT radiomics signature and MRI radiomics signature, demonstrated a good calibration and discrimination in the internal test cohort [area under curve (AUC), 0.866; 95 % confidence intervals (CI), 0.778-0.950) and the external test cohort (AUC, 0.818; 95 % CI, 0.691-0.938).

CONCLUSIONS

Our CT and MRI bimodal radiomics nomogram could timely and accurately evaluate the likelihood of EGFR mutation in patients with limited access to necessary materials, thus making up for the shortcoming of plasma sequencing and promoting the advancement of precision medicine.

Topological radiogenomics based on persistent lifetime images for identification of epidermal growth factor receptor mutation in patients with non-small cell lung tumors

We hypothesized that persistent lifetime (PLT) images could represent tumor imaging traits, locations, and persistent contrasts of topological components (connected and hole components) corresponding to gene mutations such as epidermal growth factor receptor (EGFR) mutant signs. We aimed to develop a topological radiogenomic approach using PLT images to identify EGFR mutation-positive patients with non-small cell lung cancer (NSCLC). The PLT image was newly proposed to visualize the locations and persistent contrasts of the topological components for a sequence of binary images with consecutive thresholding of an original computed tomography (CT) image. This study employed 226 NSCLC patients (94 mutant and 132 wildtype patients) with pretreatment contrast-enhanced CT images obtained from four datasets from different countries for training and testing prediction models. Two-dimensional (2D) and three-dimensional (3D) PLT images were assumed to characterize specific imaging traits (e.g., air bronchogram sign, cavitation, and ground glass nodule) of EGFR-mutant tumors. Seven types of machine learning classification models were constructed to predict EGFR mutations with significant features selected from 2D-PLT, 3D-PLT, and conventional radiogenomic features. Among the means and standard deviations of the test areas under the receiver operating characteristic curves (AUCs) of all radiogenomic approaches in a four-fold cross-validation test, the 2D-PLT features showed the highest AUC with the lowest standard deviation of 0.927 ± 0.08. The best radiogenomic approaches with the highest AUC were the random forest model trained with the Betti number (BN) map features (AUC = 0.984) in the internal test and the adapting boosting model trained with the BN map features (AUC = 0.717) in the external test. PLT features can be used as radiogenomic imaging biomarkers for the identification of EGFR mutation status in patients with NSCLC.

Explainable 18F-FDG PET/CT radiomics model for predicting EGFR mutation status in lung adenocarcinoma: a two-center study

PURPOSE

To establish an explainable 18F-FDG PET/CT-derived prediction model to identify EGFR mutation status and subtypes (EGFR wild, EGFR-E19, and EGFR-E21) in lung adenocarcinoma (LUAD).

METHODS

Baseline 18F-FDG PET/CT images of 478 patients with LUAD from 2 hospitals were collected. Data from hospital A (n = 390) was randomly split into a training group (n = 312) and an internal test group (n = 78), with data from hospital B (n = 88) utilized for external test. Further, a total of 4,760 handcrafted radiomics features (HRFs) were extracted from PET/CT scans. Candidates for the prediction model were constructed by cross-combinations of 11 feature selection methods and 7 classifiers. The optimal model was determined by combining the results of cross-center data validation and model visualization (Yellowbrick). The predictive performance was assessed via receiver operating characteristic curve, confusion matrix and classification report. Four explainable artificial intelligence technologies were used for optimal model interpretation.

RESULTS

Sex and SUVmax were selected as clinical risk factors, which were then combined with 8 robust PET/CT HRFs to establish the models. The optimal performance was obtained by combining a light gradient boosting machine classifier with random forest feature selection method achieving an optimal performance with a macro-average AUC of 0.75 in the internal test group and 0.81 in the external test group.

CONCLUSION

The explainable EGFR mutation status prediction model have certain clinical practicability and good generalization performance, which may help in the timely selection of treatment options and prognosis prediction in patients with LUAD.

A predictive model of computed tomography and clinical features of EGFR gene mutation in lung adenocarcinoma

Purpose: This study aims to develop a predictive model for epidermal growth factor receptor (EGFR) mutations in lung adenocarcinoma by integrating computed tomography (CT) imaging features with clinical characteristics. Methods: A retrospective analysis was conducted using electronic medical records from 194 patients diagnosed with lung adenocarcinoma between January 2016 and December 2020, with approval from the institutional review board. Features were selected using LASSO regression, and predictive models were built using logistic regression, support vector machine, and random forest methods. Individual models were created for clinical features, CT imaging features, and a combined model to predict EGFR mutations. Results: The training set revealed that alcohol consumption, intrapulmonary metastasis, and pleural effusion were statistically significant in distinguishing between wild-type and mutation groups (p < 0.05). In the testing set, hilar and mediastinal lymphadenopathy showed statistical significance (p < 0.05). The combined model outperformed the individual clinical and CT imaging feature models. In the testing set, the logistic regression model achieved the highest AUC of 0.827, with sensitivity, specificity, and accuracy of 0.714, 0.712, and 0.712, respectively. Nomogram analysis identified lobulation as an important feature, with a predicted probability of up to 0.9. The decision curve analysis showed that the CT imaging feature model provided a higher net benefit compared to both the clinical feature model and the combined model. Conclusion: In summary, while the combined model outperformed the individual feature models in the testing set, the CT imaging feature model demonstrated the greatest clinical net benefit. Lobulation was identified as an important predictor of EGFR mutations in lung adenocarcinoma.

Using Vision Transformer for high robustness and generalization in predicting EGFR mutation status in lung adenocarcinoma

BACKGROUND

Lung adenocarcinoma is a common cause of cancer-related deaths worldwide, and accurate EGFR genotyping is crucial for optimal treatment outcomes. Conventional methods for identifying the EGFR genotype have several limitations. Therefore, we proposed a deep learning model using non-invasive CT images to predict EGFR mutation status with robustness and generalizability.

METHODS

A total of 525 patients were enrolled at the local hospital to serve as the internal data set for model training and validation. In addition, a cohort of 30 patients from the publicly available Cancer Imaging Archive Data Set was selected for external testing. All patients underwent plain chest CT, and their EGFR mutation status labels were categorized as either mutant or wild type. The CT images were analyzed using a self-attention-based ViT-B/16 model to predict the EGFR mutation status, and the model's performance was evaluated. To produce an attention map indicating the suspicious locations of EGFR mutations, Grad-CAM was utilized.

RESULTS

The ViT deep learning model achieved impressive results, with an accuracy of 0.848, an AUC of 0.868, a sensitivity of 0.924, and a specificity of 0.718 on the validation cohort. Furthermore, in the external test cohort, the model achieved comparable performances, with an accuracy of 0.833, an AUC of 0.885, a sensitivity of 0.900, and a specificity of 0.800.

CONCLUSIONS

The ViT model demonstrates a high level of accuracy in predicting the EGFR mutation status of lung adenocarcinoma patients. Moreover, with the aid of attention maps, the model can assist clinicians in making informed clinical decisions.

The radiological characteristics, tertiary lymphoid structures, and survival status associated with EGFR mutation in patients with subsolid nodules like stage I-II LUAD

BACKGROUND

Epidermal growth factor receptor tyrosine kinase inhibitors (EGFR-TKIs) recommended for the patients with subsolid nodule in early lung cancer stage is not routinely. The clinical value and impact in patients with EGFR mutation on survival outcomes is further needed to be elucidated to decide whether the application of EGFR-TKIs was appropriate in early lung adenocarcinoma (LUAD) stage appearing as subsolid nodules.

MATERIALS AND METHODS

The inclusion of patients exhibiting clinical staging of IA-IIB subsolid nodules. Clinical information, computed tomography (CT) features before surgical resection and pathological characteristics including tertiary lymphoid structures of the tumors were recorded for further exploration of correlation with EGFR mutation and prognosis.

RESULTS

Finally, 325 patients were enrolled into this study, with an average age of 56.8 ± 9.8 years. There are 173 patients (53.2%) harboring EGFR mutation. Logistic regression model analysis showed that female (OR = 1.944, p = 0.015), mix ground glass nodule (OR = 2.071, p = 0.003, bubble-like lucency (OR = 1.991, p = 0.003) were significant risk factors of EGFR mutations. Additionally, EGFR mutations were negatively correlated with TLS presence and density. Prognosis analysis showed that the presence of TLS was associated with better recurrence-free survival (RFS)(p = 0.03) while EGFR mutations were associated with worse RFS(p = 0.01). The RFS in patients with TLS was considerably excel those without TLS within EGFR wild type group(p = 0.018). Multivariate analyses confirmed that EGFR mutation was an independent prognostic predictor for RFS (HR = 3.205, p = 0.037).

CONCLUSIONS

In early-phase LUADs, subsolid nodules with EGFR mutation had specific clinical and radiological signatures. EGFR mutation was associated with worse survival outcomes and negatively correlated with TLS, which might weaken the positive impact of TLS on prognosis. Highly attention should be paid to the use of EGFR-TKI for further treatment as agents in early LUAD patients who carrying EGFR mutation.

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.

Efficient 18F-fluorodeoxyglucose positron emission tomography/computed tomography-based machine learning model for predicting epidermal growth factor receptor mutations in non-small cell lung cancer

BACKGROUND

Beyond the human eye's limitations, radiomics provides more information that can be used for diagnosis. We develop a personalized and efficient model based on 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT) to predict epidermal growth factor receptor (EGFR) mutations to help identify which non-small cell cancer (NSCLC) patients are candidates for EGFR-tyrosine kinase inhibitors (TKIs) therapy.

METHODS

We retrospectively included 100 patients with NSCLC and randomized them according to 70 patients in the training group and 30 patients in the validation group. The least absolute shrinkage and selection operator logistic regression (LLR) algorithm and support vector machine (SVM) classifier were used to build the models and predict whether EGFR is mutated or not. The predictive efficacy of the LLR algorithm-based model and the SVM classifier-based model was evaluated by plotting the receiver operating characteristic (ROC) curves and calculating the area under the curve (AUC).

RESULTS

The AUC, sensitivity and specificity of our radiomics model by LLR algorithm were 0.792, 0.967, and 0.600 for the training group and 0.643, 1.00, and 0.378 for the validation group, respectively, in predicting EGFR mutations. The AUC was 0.838 for the training group and 0.696 for the validation group after combining radiomics features with clinical features. The prediction results based on the SVM classifier showed that the validation group had the best performance when based on radial kernel function with AUC, sensitivity, and specificity of 0.741, 0.667, and 0.825, respectively.

CONCLUSIONS

Radiomics models based on 18F-FDG PET/CT modeled with different machine learning algorithms can improve the predictive efficacy of the models. Models that combine clinical features are more clinically valuable.

The predictive value of [18F]FDG PET/CT radiomics combined with clinical features for EGFR mutation status in different clinical staging of lung adenocarcinoma

BACKGROUND

This study aims to construct radiomics models based on [¹⁸F]FDG PET/CT using multiple machine learning methods to predict the EGFR mutation status of lung adenocarcinoma and evaluate whether incorporating clinical parameters can improve the performance of radiomics models.

METHODS

A total of 515 patients were retrospectively collected and divided into a training set (n = 404) and an independent testing set (n = 111) according to their examination time. After semi-automatic segmentation of PET/CT images, the radiomics features were extracted, and the best feature sets of CT, PET, and PET/CT modalities were screened out. Nine radiomics models were constructed using logistic regression (LR), random forest (RF), and support vector machine (SVM) methods. According to the performance in the testing set, the best model of the three modalities was kept, and its radiomics score (Rad-score) was calculated. Furthermore, combined with the valuable clinical parameters (gender, smoking history, nodule type, CEA, SCC-Ag), a joint radiomics model was built.

RESULTS

Compared with LR and SVM, the RF Rad-score showed the best performance among the three radiomics models of CT, PET, and PET/CT (training and testing sets AUC: 0.688, 0.666, and 0.698 vs. 0.726, 0.678, and 0.704). Among the three joint models, the PET/CT joint model performed the best (training and testing sets AUC: 0.760 vs. 0.730). The further stratified analysis found that CT_RF had the best prediction effect for stage I-II lesions (training set and testing set AUC: 0.791 vs. 0.797), while PET/CT joint model had the best prediction effect for stage III-IV lesions (training and testing sets AUC: 0.722 vs. 0.723).

CONCLUSIONS

Combining with clinical parameters can improve the predictive performance of PET/CT radiomics model, especially for patients with advanced lung adenocarcinoma.

Association Analysis of Maximum Standardized Uptake Values Based on 18F-FDG PET/CT and EGFR Mutation Status in Lung Adenocarcinoma

(1) Background: To investigate the association between maximum standardized uptake value (SUVmax) based on 18F-FDG PET/CT and EGFR mutation status in lung adenocarcinoma. (2) Methods: A total of 366 patients were retrospectively collected and divided into the EGFR mutation group (n = 228) and EGFR wild-type group (n = 138) according to their EGFR mutation status. The two groups’ general information and PET/CT imaging parameters were compared. A hierarchical binary logistic regression model was used to assess the interaction effect on the relationship between SUVmax and EGFR mutation in different subgroups. Univariate and multivariate logistic regression was used to analyze the association between SUVmax and EGFR mutation. After adjusting for confounding factors, a generalized additive model and smooth curve fitting were applied to address possible non-linearities. (3) Results: Smoking status significantly affected the relationship between SUVmax and EGFR mutation (p for interaction = 0.012), with an interaction effect. After adjusting for age, gender, nodule type, bronchial sign, and CEA grouping, in the smoking subgroup, curve fitting results showed that the relationship between SUVmax and EGFR mutation was approximately linear (df = 1.000, c2 = 3.897, p = 0.048); with the increase in SUVmax, the probability of EGFR mutation gradually decreased, and the OR value was 0.952 (95%CI: 0.908–0.999; p = 0.045). (4) Conclusions: Smoking status can affect the relationship between SUVmax and EGFR mutation status in lung adenocarcinoma, especially in the positive smoking history subgroup. Fully understanding the effect of smoking status will help to improve the accuracy of SUVmax in predicting EGFR mutations.

Role of intratumoral and peritumoral CT radiomics for the prediction of EGFR gene mutation in primary lung cancer

Objectives

To determine the added value of combining intratumoral and peritumoral CT radiomics for the prediction of epidermal growth factor receptor (EGFR) gene mutations in primary lung cancer (PLC).

Methods

This study included 478 patients with PLC (348 adenocarcinomas and 130 other histological types) who underwent surgical resection and EGFR gene testing. Two radiologists performed segmentation of tumors and peritumoral regions using precontrast high-resolution CT images, and 398 radiomic features (212 intra- and 186 peritumoral features) were extracted. The peritumoral region was defined as the lung parenchyma within a distance of 3 mm from the tumor border. Model performance was estimated using Random Forest, a machine-learning algorithm.

Results

EGFR mutations were found in 162 tumors; 161 adenocarcinomas, and one pleomorphic carcinoma. After exclusion of poorly reproducible and redundant features, 32 radiomic features remained (14 intra- and 18 peritumoral features) and were included in the model building. For predicting EGFR mutations, combining intra- and peritumoral radiomics significantly improved the performance compared to intratumoral radiomics alone (AUC [area under the receiver operating characteristic curve], 0.774 vs 0.730; p < 0.001). Even in adenocarcinomas only, adding peritumoral radiomics significantly increased performance (AUC, 0.687 vs 0.630; p < 0.001). The predictive performance using radiomics and clinical features was significantly higher than that of clinical features alone (AUC, 0.826 vs 0.777; p = 0.005).

Conclusions

Combining intra- and peritumoral radiomics improves the predictive accuracy of EGFR mutations and could be used to aid in decision-making of whether to perform biopsy for gene tests.

Advances in knowledge

Adding peritumoral to intratumoral radiomics yields greater accuracy than intratumoral radiomics alone in predicting EGFR mutations and may serve as a non-invasive method of predicting of the gene status in PLC.

Artificial intelligence-based prediction of clinical outcome in immunotherapy and targeted therapy of lung cancer

Lung cancer accounts for the main proportion of malignancy-related deaths and most patients are diagnosed at an advanced stage. Immunotherapy and targeted therapy have great advances in application in clinics to treat lung cancer patients, yet the efficacy is unstable. The response rate of these therapies varies among patients. Some biomarkers have been proposed to predict the outcomes of immunotherapy and targeted therapy, including programmed cell death-ligand 1 (PD-L1) expression and oncogene mutations. Nevertheless, the detection tests are invasive, time-consuming, and have high demands on tumor tissue. The predictive performance of conventional biomarkers is also unsatisfactory. Therefore, novel biomarkers are needed to effectively predict the outcomes of immunotherapy and targeted therapy. The application of artificial intelligence (AI) can be a possible solution, as it has several advantages. AI can help identify features that are unable to be used by humans and perform repetitive tasks. By combining AI methods with radiomics, pathology, genomics, transcriptomics, proteomics, and clinical data, the integrated model has shown predictive value in immunotherapy and targeted therapy, which significantly improves the precision treatment of lung cancer patients. Herein, we reviewed the application of AI in predicting the outcomes of immunotherapy and targeted therapy in lung cancer patients, and discussed the challenges and future directions in this field.

Extracellular Vesicle-Based Bronchoalveolar Lavage Fluid Liquid Biopsy for EGFR Mutation Testing in Advanced Non-Squamous NSCLC

To overcome the limitations of the tissue biopsy and plasma cfDNA liquid biopsy, we performed the EV-based BALF liquid biopsy of 224 newly diagnosed stage III-IV NSCLC patients and compared it with tissue genotyping and 110 plasma liquid biopsies. Isolation of EVs from BALF was performed by ultracentrifugation. EGFR genotyping was performed through peptide nucleic acid clamping-assisted fluorescence melting curve analysis. Compared with tissue-based genotyping, BALF liquid biopsy demonstrated a sensitivity, specificity, and concordance rates of 97.8%, 96.9%, and 97.7%, respectively. The performance of BALF liquid biopsy was almost identical to that of standard tissue-based genotyping. In contrast, plasma cfDNA-based liquid biopsy (n = 110) demonstrated sensitivity, specificity, and concordance rates of 48.5%, 86.3%, and 63.6%, respectively. The mean turn-around time of BALF liquid biopsy was significantly shorter (2.6 days) than that of tissue-based genotyping (13.9 days; p < 0.001). Therefore, the use of EV-based BALF shortens the time for confirmation of EGFR mutation status for starting EGFR-TKI treatment and can hence potentially improve clinical outcomes. As a result, we suggest that EV-based BALF EGFR testing in advanced lung NSCLC is a highly accurate rapid method and can be used as an alternative method for lung tissue biopsy.

Towards Machine Learning-Aided Lung Cancer Clinical Routines: Approaches and Open Challenges

Advancements in the development of computer-aided decision (CAD) systems for clinical routines provide unquestionable benefits in connecting human medical expertise with machine intelligence, to achieve better quality healthcare. Considering the large number of incidences and mortality numbers associated with lung cancer, there is a need for the most accurate clinical procedures; thus, the possibility of using artificial intelligence (AI) tools for decision support is becoming a closer reality. At any stage of the lung cancer clinical pathway, specific obstacles are identified and "motivate" the application of innovative AI solutions. This work provides a comprehensive review of the most recent research dedicated toward the development of CAD tools using computed tomography images for lung cancer-related tasks. We discuss the major challenges and provide critical perspectives on future directions. Although we focus on lung cancer in this review, we also provide a more clear definition of the path used to integrate AI in healthcare, emphasizing fundamental research points that are crucial for overcoming current barriers.

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.

The value of CT radiomics features to predict visceral pleural invasion in ≤3 cm peripheral type early non-small cell lung cancer

OBJECTIVE

To investigate predictive value of CT-based radiomics features on visceral pleural invasion (VPI) in ≤3.0 cm peripheral type early non-small cell lung cancer (NSCLC).

METHODS

A total of 221 NSCLC cases were collected. Among them, 115 are VPI-positive and 106 are VPI-negative. Using a stratified random sampling method, 70% cases were assigned to training dataset (n = 155) and 30% cases (n = 66) were assigned to validation dataset. First, CT findings, imaging features, clinical data and pathological findings were retrospectively analyzed, the size, location and density characteristics of nodules and lymph node status, the relationship between lesions and pleura (RAP) were assessed, and their mean CT value and the shortest distance between lesions and pleura (DLP) were measured. Next, the minimum redundancy-maximum relevance (mRMR) and least absolute shrinkage and selection operator (LASSO) features were extracted from the imaging features. Then, CT imaging prediction model, texture feature prediction model and joint prediction model were built using multifactorial logistic regression analysis method, and the area under the ROC curve (AUC) was applied to evaluate model performance in predicting VPI.

RESULTS

Mean diameter, density, fractal relationship with pleura, and presence of lymph node metastasis were all independent predictors of VPI. When applying to the validation dataset, the CT imaging model, texture feature model, and joint prediction model yielded AUC = 0.882, 0.824 and 0.894, respectively, indicating that AUC of the joint prediction model was the highest (p < 0.05).

CONCLUSION

The study demonstrates that the joint prediction model containing CT morphological features and texture features enables to predict the presence of VPI in early NSCLC preoperatively at the highest level.

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.

Can 18F-FDG PET/CT predict EGFR status in patients with non-small cell lung cancer? A systematic review and meta-analysis

OBJECTIVES

This study aimed to explore the diagnostic significance of ¹⁸F-fluorodeoxyglucose (¹⁸F-FDG) positron emission tomography (PET)/CT for predicting the presence of epidermal growth factor receptor (EGFR) mutations in patients with non-small cell lung cancer (NSCLC).

DESIGN

A systematic review and meta-analysis.

DATA SOURCES

The PubMed, EMBASE and Cochrane library databases were searched from the earliest available date to December 2020.

ELIGIBILITY CRITERIA FOR SELECTING STUDIES

The review included primary studies that compared the mean maximum of standard uptake value (SUV_max) between wild-type and mutant EGFR, and evaluated the diagnostic value of ¹⁸F-FDG PET/CT using SUV_max for prediction of EGFR status in patients with NSCLC.

DATA EXTRACTION AND SYNTHESIS

The main analysis was to assess the sensitivity and specificity, the positive diagnostic likelihood ratio (DLR+) and DLR-, as well as the diagnostic OR (DOR) of SUV_max in prediction of EGFR mutations. Each data point of the summary receiver operator characteristic (SROC) graph was derived from a separate study. A random effects model was used for statistical analysis of the data, and then diagnostic performance for prediction was further assessed.

RESULTS

Across 15 studies (3574 patients), the pooled sensitivity for ¹⁸F-FDG PET/CT was 0.70 (95% CI 0.60 to 0.79) with a pooled specificity of 0.59 (95% CI 0.52 to 0.66). The overall DLR+ was 1.74 (95% CI 1.49 to 2.03) and DLR- was 0.50 (95% CI 0.38 to 0.65). The pooled DOR was 3.50 (95% CI 2.37 to 5.17). The area under the SROC curve was 0.68 (95% CI 0.64 to 0.72). The likelihood ratio scatter plot based on average sensitivity and specificity was in the lower right quadrant.

CONCLUSION

Meta-analysis results showed ¹⁸F-FDG PET/CT had low pooled sensitivity and specificity. The low DOR and the likelihood ratio scatter plot indicated that ¹⁸F-FDG PET/CT should be used with caution when predicting EGFR mutations in patients with NSCLC.

Machine Learning and Feature Selection Methods for EGFR Mutation Status Prediction in Lung Cancer

The evolution of personalized medicine has changed the therapeutic strategy from classical chemotherapy and radiotherapy to a genetic modification targeted therapy, and although biopsy is the traditional method to genetically characterize lung cancer tumor, it is an invasive and painful procedure for the patient. Nodule image features extracted from computed tomography (CT) scans have been used to create machine learning models that predict gene mutation status in a noninvasive, fast, and easy-to-use manner. However, recent studies have shown that radiomic features extracted from an extended region of interest (ROI) beyond the tumor, might be more relevant to predict the mutation status in lung cancer, and consequently may be used to significantly decrease the mortality rate of patients battling this condition. In this work, we investigated the relation between image phenotypes and the mutation status of Epidermal Growth Factor Receptor (EGFR), the most frequently mutated gene in lung cancer with several approved targeted-therapies, using radiomic features extracted from the lung containing the nodule. A variety of linear, nonlinear, and ensemble predictive classification models, along with several feature selection methods, were used to classify the binary outcome of wild-type or mutant EGFR mutation status. The results show that a comprehensive approach using a ROI that included the lung with nodule can capture relevant information and successfully predict the EGFR mutation status with increased performance compared to local nodule analyses. Linear Support Vector Machine, Elastic Net, and Logistic Regression, combined with the Principal Component Analysis feature selection method implemented with 70% of variance in the feature set, were the best-performing classifiers, reaching Area Under the Curve (AUC) values ranging from 0.725 to 0.737. This approach that exploits a holistic analysis indicates that information from more extensive regions of the lung containing the nodule allows a more complete lung cancer characterization and should be considered in future radiogenomic studies.

Clinical and radiological predictors of epidermal growth factor receptor mutation in nonsmall cell lung cancer

Purpose

To determine the prognostic factors of epidermal growth factor receptor (EGFR) mutation status in a group of patients with nonsmall cell lung cancer (NSCLC) by analyzing their clinical and radiological features.

Materials and methods

Patients with NSCLC who underwent EGFR mutation detection between 2014 and 2017 were included. Clinical features and general imaging features were collected, and radiomic features were extracted from CT data by 3D Slicer software. Prognostic factors of EGFR mutation status were selected by least absolute shrinkage and selection operator (LASSO) logistic regression analysis, and receiver operating characteristic (ROC) curves were drawn for each prediction model of EGFR mutation.

Results

A total of 118 patients were enrolled in this study. The smoking index (P = 0.028), pleural retraction (P = 0.041), and three radiomic features were significantly associated with EGFR mutation status. The areas under the ROC curve (AUCs) for prediction models of clinical features, general imaging features, and radiomic features were 0.284, 0.703, and 0.815, respectively, and the AUC for the combined prediction model of the three models was 0.894. Finally, a nomogram was established for individualized EGFR mutation prediction.

Conclusions

The combination of radiomic features with clinical features and general imaging features can enable discrimination of EGFR mutation status better than the use of any group of features alone. Our study may help develop a noninvasive biomarker to identify EGFR mutation status by using a combination of the three group features.

Role of imaging biomarkers in mutation-driven non-small cell lung cancer

Lung cancer remains the leading cause of cancer-related deaths worldwide. The treatment of non-small cell lung cancer (NSCLC), which accounts for a vast majority of lung cancers, has shifted to personalized, targeted therapy following discoveries of several targetable oncogenic mutations. Targeting of specific mutations has improved outcomes in many patients. This success has led to several target-specific agents replacing chemotherapy as first-line treatment in certain mutated NSCLC. Several researchers have reported that there may be imaging biomarkers that may be predictive of the presence of these mutations. These features, when present, have the potential in triaging patients into the most appropriate diagnostic and treatment algorithms. Distinct imaging features and patterns of metastases that have been associated with NSCLC with various targetable oncogenic mutations are presented in this review.

Development and validation of a predictive model for estimating EGFR mutation probabilities in patients with non-squamous non-small cell lung cancer in New Zealand

BACKGROUND

Targeted treatment with Epidermal Growth Factor Receptor (EGFR) tyrosine kinase inhibitors (TKIs) is superior to systemic chemotherapy in non-small cell lung cancer (NSCLC) patients with EGFR gene mutations. Detection of EGFR mutations is a challenge in many patients due to the lack of suitable tumour specimens for molecular testing or for other reasons. EGFR mutations are more common in female, Asian and never smoking NSCLC patients.

METHODS

Patients were from a population-based retrospective cohort of 3556 patients diagnosed with non-squamous non-small cell lung cancer in northern New Zealand between 1 Feb 2010 and 31 July 2017. A total of 1694 patients were tested for EGFR mutations, of which information on 1665 patients was available for model development and validation. A multivariable logistic regression model was developed based on 1176 tested patients, and validated in 489 tested patients. Among 1862 patients not tested for EGFR mutations, 129 patients were treated with EGFR-TKIs. Their EGFR mutation probabilities were calculated using the model, and their duration of benefit and overall survival from the start of EGFR-TKI were compared among the three predicted probability groups: < 0.2, 0.2-0.6, and > 0.6.

RESULTS

The model has three predictors: sex, ethnicity and smoking status, and is presented as a nomogram to calculate EGFR mutation probabilities. The model performed well in the validation group (AUC = 0.75). The probability cut-point of 0.2 corresponds 68% sensitivity and 78% specificity. The model predictions were related to outcome in a group of TKI-treated patients with no biopsy testing available (n = 129); in subgroups with predicted probabilities of < 0.2, 0.2-0.6, and > 0.6, median overall survival times from starting EGFR-TKI were 4.0, 5.5 and 18.3 months (p = 0.02); and median times remaining on EGFR-TKI treatment were 2.0, 4.2, and 14.0 months, respectively (p < 0.001).

CONCLUSION

Our model may assist clinical decision making for patients in whom tissue-based mutation testing is difficult or as a supplement to mutation testing.

Imaging Features and Metastatic Patterns of Advanced ALK-Rearranged Non-Small Cell Lung Cancer

OBJECTIVE.ALK rearrangements are an established targetable oncogenic driver in non-small cell lung cancer (NSCLC). The goal of this study was to determine the imaging features of the primary tumor and metastatic patterns in advanced ALK-rearranged (ALK+) NSCLC that may be different from those in EGFR-mutant (EGFR+) or EGFR/ALK wild-type (EGFR-/ALK-) NSCLC. MATERIALS AND METHODS. Patients with advanced ALK+, EGFR+, or EGFR-/ALK- NSCLC were retrospectively identified. Two radiologists concurrently assessed the imaging features of the primary tumor and the distribution of metastases in these patients. RESULTS. We identified a cohort of 333 patients with metastatic NSCLC (119 ALK+ cases, 116 EGFR+ cases, and 98 EGFR-/ALK- cases). Compared with EGFR+ and EGFR-/ALK- NSCLC, the primary tumor in ALK+ NSCLC was more likely to be located in the lower lobes (53% of ALK+, 34% of EGFR+, and 36% of EGFR-/ALK- tumors; p < 0.05), less likely to be subsolid (1% of ALK+, 11% of EGFR+, and 8% of EGFR-/ALK- tumors; p < 0.02), and less likely to have air bronchograms (7% of ALK+, 28% of EGFR+, and 29% of EGFR-/ALK- tumors; p < 0.01). Compared with EGFR+ and EGFR-/ALK- tumors, ALK+ tumors had higher frequencies of distant nodal metastasis (20% of ALK+ tumors vs 2% of EGFR+ and 9% of EGFR-/ALK- tumors; p < 0.05) and lymphangitic carcinomatosis (37% of ALK+ tumors vs 12% of EGFR+ and 12% of EGFR-/ALK- tumors; p < 0.01), but ALK+ tumors had a lower frequency of brain metastasis compared with EGFR+ tumors (24% vs 41%; p = 0.01). Although there was no statistically significant difference in the frequencies of bone metastasis among the three groups, sclerotic bone metastases were more common in the ALK+ tumors (22% vs 7% of EGFR+ tumors and 6% of EGFR-/ALK- tumors; p < 0.01). CONCLUSION. Advanced ALK+ NSCLC has primary tumor imaging features and patterns of metastasis that are different from those of EGFR+ or EGFR-/ALK- wild type NSCLC at the time of initial presentation.

Identifying relationships between imaging phenotypes and lung cancer-related mutation status: EGFR and KRAS

EGFR and KRAS are the most frequently mutated genes in lung cancer, being active research topics in targeted therapy. The biopsy is the traditional method to genetically characterise a tumour. However, it is a risky procedure, painful for the patient, and, occasionally, the tumour might be inaccessible. This work aims to study and debate the nature of the relationships between imaging phenotypes and lung cancer-related mutation status. Until now, the literature has failed to point to new research directions, mainly consisting of results-oriented works in a field where there is still not enough available data to train clinically viable models. We intend to open a discussion about critical points and to present new possibilities for future radiogenomics studies. We conducted high-dimensional data visualisation and developed classifiers, which allowed us to analyse the results for EGFR and KRAS biological markers according to different combinations of input features. We show that EGFR mutation status might be correlated to CT scans imaging phenotypes; however, the same does not seem to hold for KRAS mutation status. Also, the experiments suggest that the best way to approach this problem is by combining nodule-related features with features from other lung structures.

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.

Computed Tomography Imaging Characteristics of Non-Small-Cell Lung Cancer With Anaplastic Lymphoma Kinase Rearrangements: A Systematic Review and Meta-Analysis

INTRODUCTION

Several studies have suggested that non-small-cell lung cancer (NSCLC) patients who harbor anaplastic lymphoma kinase (ALK) rearrangement might have different imaging features compared with those without the rearrangement. The goal of this work was to systematically investigate the computed tomography (CT) imaging features of ALK-rearranged NSCLC.

MATERIALS AND METHODS

We searched published studies that investigated CT imaging features of ALK-rearranged NSCLC compared with ALK-negative, including epidermal growth factor receptor (EGFR)-mutant and ALK/EGFR-negative, NSCLC. We extracted clinicopathologic characteristics and CT imaging features of patients in the included studies. Features were compared and tested in the form of odds ratios (ORs) or weighted mean differences at a 95% confidence interval.

RESULTS

Twelve studies with 2210 patients with NSCLC were included. Compared with ALK-negative NSCLC, ALK-rearranged NSCLC was more likely to be solid (OR, 2.37; P < .001) and less likely to have cavitation (OR, 0.45; P = .002). In advanced stages, patients with ALK-rearranged NSCLC, compared with EGFR-mutant NSCLC, were more likely to have lymphadenopathy (OR, 3.47; P < .001), pericardial metastasis (OR, 2.18; P = .04), pleural metastasis (OR, 2.07; P = .004), and lymphangitic carcinomatosis (OR, 3.41; P = .02), but less likely to have lung metastasis (OR, 0.52; P = .003). Compared with ALK/EGFR-negative NSCLC, ALK-rearranged NSCLC was more likely to have lymphangitic carcinomatosis (OR, 3.88; P = .03), pleural metastasis (OR, 1.89; P = .02), and pleural effusion (OR, 2.94; P = .003).

CONCLUSION

ALK-rearranged NSCLC has imaging features that are different compared with EGFR-mutant and ALK/EGFR-negative NSCLC. These imaging features might provide clues as to the presence of ALK rearrangement and help in the selection of patients who might benefit from expedited molecular testing or repeat testing after a negative assay.