CT characteristics of non-small cell lung cancer with epidermal growth factor receptor mutation: a systematic review and meta-analysis

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.

Gene mutation, clinical characteristics and pathology in resectable lung adenocarcinoma

OBJECTIVE

With the wide use of CT scan in clinical practice, more lung cancer was diagnosed in resectable stage. Pathological examination and genetic testing have become a routine procedure for lung adenocarcinoma following radical resection. This study analyzed special pathological components and gene mutations to explore their relationship with clinical characteristics and overall survival.

METHODS

Clinical, pathological, and gene mutation data from 1,118 patients were collected. All patients underwent surgery at the Department of Thoracic Surgery, the Second Xiangya Hospital of Central South University. Patients were grouped based on pathological components and gene mutations. Differences in clinical features and overall survival were analyzed as well.

RESULTS

Patients with mucinous, neuroendocrine, and poor-differentiated components were presented with more prognostic risk factors, including pleural invasion, carcinothrombosis, STAS, and advanced stages, along with varying frequencies of gene mutations. These factors significantly shortened overall survival. ALK and KRAS mutations were also associated with risk factors such as solid nodules, pleural invasion, STAS, and later stages. However, a significant reduction in overall survival was observed only in patients with the KRAS mutation. Relationship between gene mutations and pathological components still requires further investigation.

CONCLUSION

Special pathological components (mucinous, neuroendocrine, and poor-differentiated) and gene mutations had an influence on biological behavior of tumors, resulting in different clinical characteristics and prognosis.

A nomogram for predicting lymphovascular invasion in lung adenocarcinoma: a retrospective study

BACKGROUD

Lymphovascular invasion (LVI) was histological factor that was closely related to prognosis of lung adenocarcinoma (LAC).The primary aim was to investigate the value of a nomogram incorporating clinical and computed tomography (CT) factors to predict LVI in LAC, and validating the predictive efficacy of a clinical model for LVI in patients with lung adenocarcinoma with lesions ≤ 3 cm.

METHODS

A total of 450 patients with LAC were retrospectively enrolled. Clinical data and CT features were analyzed to identify independent predictors of LVI. A nomogram incorporating the independent predictors of LVI was built. The performance of the nomogram was evaluated by assessing its discriminative ability and clinical utility.We took 321 patients with tumours ≤ 3 cm in diameter to continue constructing the clinical prediction model, which was labelled subgroup clinical model.

RESULTS

Carcinoembryonic antigen (CEA) level, maximum tumor diameter, spiculation, and vacuole sign were independent predictors of LVI. The LVI prediction nomogram showed good discrimination in the training set [area under the curve (AUC), 0.800] and the test set (AUC, 0.790), the subgroup clinical model also owned the stable predictive efficacy for preoperative prediction of LVI in lung adenocarcinoma patients, and both training and test set AUC reached 0.740.

CONCLUSIONS

The nomogram developed in this study could predict the risk of LVI in LAC patients, facilitate individualized risk-stratification, and help inform treatment decision-makin, and the subgroup clinical model also had good predictive performance for lung cancer patients with lesion ≤ 3 cm in diameter.

Unusual presentation of ROS1 rearranged metastatic non-small cell lung cancer

The spectrum of clinical and radiographic presentations of lung adenocarcinoma is increasingly broad, including in the metastatic setting. Here, we report on a patient who initially presented with a mild chronic cough that remained stable over a decade, with serial CT scans showing gradual worsening of multifocal areas of consolidation and ground-glass opacities of the bilateral lungs. The patient was ultimately diagnosed with ROS1 rearranged lung adenocarcinoma and achieved a dramatic response with entrectinib. This case highlights the variable presentation of non-small cell lung cancer (NSCLC) and the importance of comprehensive molecular testing for newly diagnosed metastatic NSCLC.

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.

Multiple instance learning for lung pathophysiological findings detection using CT scans

Lung diseases affect the lives of billions of people worldwide, and 4 million people, each year, die prematurely due to this condition. These pathologies are characterized by specific imagiological findings in CT scans. The traditional Computer-Aided Diagnosis (CAD) approaches have been showing promising results to help clinicians; however, CADs normally consider a small part of the medical image for analysis, excluding possible relevant information for clinical evaluation. Multiple Instance Learning (MIL) approach takes into consideration different small pieces that are relevant for the final classification and creates a comprehensive analysis of pathophysiological changes. This study uses MIL-based approaches to identify the presence of lung pathophysiological findings in CT scans for the characterization of lung disease development. This work was focus on the detection of the following: Fibrosis, Emphysema, Satellite Nodules in Primary Lesion Lobe, Nodules in Contralateral Lung and Ground Glass, being Fibrosis and Emphysema the ones with more outstanding results, reaching an Area Under the Curve (AUC) of 0.89 and 0.72, respectively. Additionally, the MIL-based approach was used for EGFR mutation status prediction - the most relevant oncogene on lung cancer, with an AUC of 0.69. The results showed that this comprehensive approach can be a useful tool for lung pathophysiological characterization.

[Relationship between EGFR, ALK Gene Mutation and Imaging and Pathological Features in Invasive Lung Adenocarcinoma]

BACKGROUND

At present, the research progress of targeted therapy for epidermal growth factor receptor (EGFR) and anaplastic lymphoma kinase (ALK) gene mutations in lung adenocarcinoma is very rapid, which brings new hope for the treatment of advanced lung adenocarcinoma patients. However, the specific imaging and pathological features of EGFR and ALK gene mutations in adenocarcinoma are still controversial. This study will further explore the correlation between EGFR, ALK gene mutations and imaging and pathological features in invasive lung adenocarcinoma.

METHODS

A total of 525 patients with lung adenocarcinoma who underwent surgery in our center from January 2018 to December 2019 were included. According to the results of postoperative gene detection, the patients were divided into EGFR gene mutation group, ALK gene mutation group and wild group, and the EGFR gene mutation group was divided into exon 19 and exon 21 subtypes. The pathological features of the mutation group and wild group, such as histological subtype, lymph node metastasis, visceral pleural invasion (VPI) and imaging features such as tumor diameter, consolidation tumor ratio (CTR), lobulation sign, spiculation sign, pleural retraction sign, air bronchus sign and vacuole sign were analyzed by univariate analysis and multivariate Logistic regression analysis to explore whether the gene mutation group had specific manifestations.

RESULTS

EGFR gene mutation group was common in women (OR=2.041, P=0.001), with more pleural traction sign (OR=1.506, P=0.042), and had little correlation with lymph node metastasis and VPI (P>0.05). Among them, exon 21 subtype was more common in older (OR=1.022, P=0.036), women (OR=2.010, P=0.007), and was associated with larger tumor diameter (OR=1.360, P=0.039) and pleural traction sign (OR=1.754, P=0.029). Exon 19 subtype was common in women (OR=2.230, P=0.009), with a high proportion of solid components (OR=1.589, P=0.047) and more lobulation sign (OR=2.762, P=0.026). ALK gene mutations were likely to occur in younger patients (OR=2.950, P=0.045), with somking history (OR=1.070, P=0.002), and there were more micropapillary components (OR=4.184, P=0.019) and VPI (OR=2.986, P=0.034) in pathology.

CONCLUSIONS

The EGFR and ALK genes mutated adenocarcinomas have specific imaging and clinicopathological features, and the mutations in exon 19 or exon 21 subtype have different imaging features, which is of great significance in guiding the clinical diagnosis and treatment of pulmonary nodules.

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.

High-resolution computed tomography findings independently predict epidermal growth factor receptor mutation status in ground-glass nodular lung adenocarcinoma

BACKGROUND

For lung adenocarcinoma with epidermal growth factor receptor (EGFR) gene mutation, small molecule tyrosine kinase inhibitors are more effective. Some patients could not obtain enough histological specimens for EGFR gene mutation detection. Specific imaging features can predict EGFR mutation status to a certain extent.

AIM

To assess the associations of EGFR mutations with high-resolution computerized tomography (HRCT) features in ground-glass nodular lung adenocarcinoma.

METHODS

This study retrospectively assessed patients with ground-glass nodular lung adenocarcinoma diagnosed between January 2011 and March 2017. EGFR gene mutations in exons 18-21 were detected. The patients were classified into mutant EGFR and wild-type groups, and general data and HRCT image characteristics were assessed.

RESULTS

Among 98 patients, 31 (31.6%) and 67 (68.4%) had mutated and wild-type EGFR in exons 18-21, respectively. Gender, age, smoking history, location of lesions, morphology, edges, borders, pleural indentations, and associations of nodules with bronchus and blood vessels were comparable in both groups (all P > 0.05). Patients with mutant EGFR had larger nodules than those with the wild-type (17.19 ± 6.79 and 14.37 ± 6.30 mm, respectively; P = 0.047). Meanwhile, the vacuole/honeycomb sign was more frequent in the mutant EGFR group (P = 0.011). The logistic regression prediction model included the combination of nodule size and vacuole/honeycomb sign (OR = 1.120, 95%CI: 1.023-1.227, P = 0.014) revealed a sensitivity of 83.9%, a specificity of 52.2% and an AUC of 0.698 (95%CI: 0.589-0.806; P = 0.002).

CONCLUSION

Nodule size and vacuole/honeycomb features could independently predict EGFR mutation status in ground-glass nodular lung adenocarcinoma.

Ensemble Strategies for EGFR Mutation Status Prediction in Lung Cancer

Lung cancer treatments that are accurate and effective are urgently needed. The diagnosis of advanced-stage patients accounts for the majority of the cases, being essential to provide a specialized course of treatment. One emerging course of treatment relies on target therapy through the testing of biomarkers, such as the Epidermal Growth Factor Receptor (EGFR) gene. Such testing can be obtained from invasive methods, namely through biopsy, which may be avoided by applying machine learning techniques to the imaging phenotypes extracted from Computerized Tomography (CT). This study aims to explore the contribution of ensemble methods when applied to the prediction of EGFR mutation status. The obtained results translate in a direct correlation between the semantic predictive model and the outcome of the combined ensemble methods, showing that the utilized features do not have a positive contribution to the predictive developed models.

Computed Tomography Imaging Characteristics: Potential Indicators of Epidermal Growth Factor Receptor Mutation in Lung Adenocarcinoma

PURPOSE

The purpose of this study was to investigate the correlation between computed tomography imaging characteristics in lung adenocarcinoma and epidermal growth factor receptor (EGFR) mutations.

METHODS

A total of 124 patients with lung adenocarcinoma and known EGFR mutation status were collected in this retrospective study. Computed tomography quantitative parameters of each tumor, including total volume, total surface, surface-to-volume ratio (SVR), average diameter, maximum diameter, and average density, were determined using computer-aided detection software. The correlation between the EGFR mutation status and imaging characteristics was assessed. The predictive value of these imaging characteristics for EGFR mutation was calculated using the area under the receiver operating characteristic curve.

RESULT

Fifty-eight of 124 patients showed EGFR mutations. Patients who are female (P < 0.001) and nonsmokers (P < 0.001) and those with serum carcinoembryonic antigen (CEA) level of ≥5 (P = 0.035) were likely to have EGFR mutation. Computed tomography features including air bronchogram (P = 0.035), absence of cavitation (P = 0.010), and absence of pulmonary emphysema (P = 0.002) and quantitative parameters, such as smaller total surface (P = 0.002), smaller total volume (P = 0.001), higher SVR (P = 0.003), and smaller average diameter (P = 0.001), were associated with EGFR mutation. Logistic regression analysis revealed that the most significant independent prognostic factors of EGFR mutation for the model were nonsmoking (P = 0.035), CEA level of ≥5 (P = 0.004), presence of air bronchogram (P = 0.040), absence of cavitation (P = 0.021), and high SVR (P = 0.014). The area under the receiver operating characteristic curve, sensitivity, and specificity of the model for predicting EGFR mutation were 0.827, 75.8%, and 82.8%, respectively.

CONCLUSIONS

EGFR-mutated adenocarcinoma showed significantly increased CEA level, presence of air bronchogram, absence of cavitation, and higher quantitative parameter SVR than those with wild-type EGFR.

Prognostic influence of epidermal growth factor receptor mutation and radiological ground glass appearance in patients with early-stage lung adenocarcinoma

OBJECTIVES

The ADAURA demonstrated the efficacy of osimertinib as adjuvant therapy in patients with resected stage IB-IIIA adenocarcinoma harboring epidermal growth factor receptor (EGFR) mutations. However, it is controversial whether adjuvant therapy should be applied to all these patients because of their heterogeneities. This study aimed to examine the influence of GGO and EGFR mutations on the prognosis and to identify optimal targets for the development of perioperative therapy.

MATERIAL AND METHODS

Among the patients who underwent complete resection between 2003 and 2014 and had pathological stage IA3-IIA adenocarcinoma, 505 consecutive patients were examined for EGFR mutation status. The prognosis was analyzed among the clinicopathological factors including EGFR status and presence or absence of GGO.

RESULTS

Of the 489 patients, 193 (39.5%) showed EGFR mutations. The recurrence-free survival (RFS) and overall survival (OS) of the EGFR mutant were slightly better than those of the EGFR wild type. There was no difference in RFS and OS between EGFR mutant and wild type in patients with GGO; however, EGFR mutant showed better OS than EGFR wild type in patients without GGO. The presence of GGO was a strong independent prognostic predictor in OS and RFS, but EGFR mutations was not predictors. In patients without GGO, EGFR mutants showed slightly higher recurrence, especially with a hazard ratio of 1.427 in stage IB.

CONCLUSIONS

Adenocarcinoma with GGO show a very good prognosis, so may not require adjuvant therapy. It will be necessary to further develop perioperative therapy in patients with poor prognosis.

Biological Significance of 18F-FDG PET/CT Maximum Standard Uptake Value for Predicting EGFR Mutation Status in Non-Small Cell Lung Cancer Patients

Purpose

To investigate the potential of maximum standardized uptake value (SUVmax) in predicting epidermal growth factor receptor (EGFR) mutation status in non-small cell lung cancer (NSCLC) patients.

Methods

Clinical data of 311 NSCLC patients who had undergone both EGFR mutation test and ¹⁸F-FDG PET/CT scans between January 2013 and December 2017 at our hospital were retrospectively analyzed. Patients were sub-grouped by their origin of SUVmax. Univariate and multivariate analyses were performed to investigate the association between clinical factors and EGFR mutations. Receiver operating characteristic curve (ROC) analysis was performed to confirm the predictive value of clinical factors. In vitro experiments were performed to confirm the correlation between EGFR mutations and glycolysis.

Results

EGFR-mutant patients had higher SUVmax than the wild-type patients in both primary tumors and metastases. In the multivariate analysis, SUVmax, gender and histopathologic type were determined as independent predictors of EGFR mutation status for patients whose SUVmax were obtained from the primary tumors; while for patients whose SUVmax were obtained from the metastases, SUVmax, smoking status and histopathologic type were regarded as independent predictors. ROC analysis showed that SUVmax of the primary tumors (cut off >10.92), not of the metastases, has better predictive value than other clinical factors in predicting EGFR mutation status. The predict performance was improved after combined SUVmax with other independent predictors. In addition, our in vitro experiments demonstrated that lung cancer cells with EGFR mutations have higher aerobic glycolysis level than wild-type cells.

Conclusion

SUVmax of the primary tumors has the potential to serve as a biomarker to predict EGFR mutation status in NSCLC patients.

Lung radiofrequency ablation: post-procedure imaging patterns and late follow-up

•

RFA is an effective minimally invasive treatment for selected patients with primary and secondary lung tumors.

•

We described the expected imaging features after RFA of lung tumors, and their frequency over time after the procedure.

•

Radiologists should be familiar with these features in order to avoid misinterpretation and inadequate treatments.

•

These normal post-procedure imaging features must be considered in future post-ablation follow-up protocols.

Purpose

To describe expected imaging features on chest computed tomography (CT) after percutaneous radiofrequency ablation (RFA) of lung tumors, and their frequency over time after the procedure.

Methods

In this double-center retrospective study, we reviewed CT scans from patients who underwent RFA for primary or secondary lung tumors. Patients with partial ablation or tumor recurrence during the imaging follow-up were not included. The imaging features were assessed in pre-defined time points: immediate post-procedure, ≤4 weeks, 5−24 weeks, 25−52 weeks and ≥52 weeks. Late follow-up (3 and 5 years after procedure) was assessed clinically in 48 patients.

Results

The study population consisted of 69 patients and 144 pulmonary tumors. Six out of 69 (9%) patients had primary lung nodules (stage I) and 63/69 (91 %) had metastatic pulmonary nodules. In a patient-level analysis, immediately after lung RFA, the most common CT features were ground glass opacities (66/69, 96 %), consolidation (56/69, 81 %), and hyperdensity within the nodule (47/69, 68 %). Less than 4 weeks, ground glass opacities (including reversed halo sign) was demonstrated in 20/22 (91 %) patients, while consolidation and pleural thickening were detected in 17/22 patients (77 %). Cavitation, pneumatocele, pneumothorax and pleural effusions were less common features. From 5 weeks onwards, the most common imaging features were parenchymal bands.

Conclusions

Our study demonstrated the expected CT features after lung RFA, a safe and effective minimally invasive treatment for selected patients with primary and secondary lung tumors. Diagnostic and interventional radiologists should be familiar with the expected imaging features immediately after RFA and their change over time in order to avoid misinterpretation and inadequate treatments.

Clinical and Imaging Features of Non-Small-Cell Lung Cancer in Young Patients

BACKGROUND

Non-small-cell lung cancer (NSCLC) in young adult patients is rare, with scarce data available in patients aged < 40 years and even less in those aged < 35 years. Our goal was to determine the presenting symptoms, clinicopathologic characteristics, and imaging features of young patients with NSCLC at time of diagnosis and compare them to those of older adults.

PATIENTS AND METHODS

We retrospectively analyzed the medical records and imaging of young patients (≤ 40 years old) with NSCLC treated at our institution between 1998 and 2018. Patients < 35 years old were compared to those between 35 and 40 years old. Characteristics of patients ≤ 40 years old were compared to older patients (> 40 years) from publicly available data sets.

RESULTS

We identified 166 young patients with NSCLC (median age, 36.6 years; range, 18-40 years). Most presented with nonspecific respiratory symptoms and were diagnosed with pneumonia (84/136, 62%). Compared to patients < 35 years old, patients 35-40 years old were more likely to have malignancy detected incidentally (15% vs. 5%, P = .04). Patients < 35 years old were more likely to have central tumors (55% vs. 33%, P = .02) and to have bone (38% vs. 19%, P = .007) and lung (39% vs. 24%, P = .03) metastases. Compared to older patients (> 40 years), young patients were more likely to be never smokers (65.0% vs. 14.7%, P < .001) and to have advanced disease (88% vs. 66%, P < .001).

CONCLUSION

Young patients with NSCLC often present with nonspecific symptoms and have advanced disease at diagnosis, often mimicking other pathologies. Awareness of the clinical presentation and imaging features of NSCLC in young patients may help minimize delays in diagnoses.

Survival prediction model for non-small cell lung cancer based on somatic mutations

BACKGROUND

The 5-year survival rate of non-small cell lung cancer (NSCLC) is only 15%. Screening some combined gene mutations could predict the survival of NSCLC patients and also provide new ideas for the diagnosis and treatment of NSCLC. The present study aimed to identify signature mutations for survival prediction of NSCLC.

METHODS

Clinical and gene mutation information for 949 NSCLC patients was downloaded from TCGA. High frequency mutation and common mutation genes were analyzed based on 1000 cancer related genes. The LASSO-COX model was used to screen gene mutation points and analyze their survival, and then a survival prediction model was established. Fifty NSCLC patients were collected and 1000 targeted genes were enriched by targeted next generation sequencing. The results were used to verify the combination of common mutation genes and the function of the survival model, and then to clarify their clinical significance.

RESULTS

Ten variables were screened out after LASSO-COX analysis, including age, tumor stage, EGFR c.[2,573 T>G], PIK3CA c.[1624G>A], TP53 c.[375G>T], TP53 c.[527G>T], TP53 c.[733G>T], TP53 c.[734G>T], TP53 c.[743G>T], NFE2L2 c.[100C>G]. Except for TP53 c.[743G>T] and NFE2L2 c.[100C>G], the residual six hot spot mutations of EGFR, PIK3CA and TP53 could be regarded as a signature mutations for forecasting the survival time of NSCLC.

CONCLUSIONS

The combination of six hot spot mutations of EGFR, PIK3CA and TP53 is expected to be used for predicting the survival time of NSCLC.

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.

The Potential of Radiomics Nomogram in Non-invasively Prediction of Epidermal Growth Factor Receptor Mutation Status and Subtypes in Lung Adenocarcinoma

Purpose: Up to 50% of Asian patients with NSCLC have EGFR gene mutations, indicating that selecting eligible patients for EGFR-TKIs treatments is clinically important. The aim of the study is to develop and validate radiomics-based nomograms, integrating radiomics, CT features and clinical characteristics, to non-invasively predict EGFR mutation status and subtypes.

Materials and Methods: We included 637 patients with lung adenocarcinomas, who performed the EGFR mutations analysis in the current study. The whole dataset was randomly split into a training dataset (n = 322) and validation dataset (n = 315). A sub-dataset of EGFR-mutant lesions (EGFR mutation in exon 19 and in exon 21) was used to explore the capability of radiomic features for predicting EGFR mutation subtypes. Four hundred seventy-five radiomic features were extracted and a radiomics sore (R-score) was constructed by using the least absolute shrinkage and selection operator (LASSO) regression in the training dataset. A radiomics-based nomogram, incorporating clinical characteristics, CT features and R-score was developed in the training dataset and evaluated in the validation dataset.

Results: The constructed R-scores achieved promising performance on predicting EGFR mutation status and subtypes, with AUCs of 0.694 and 0.708 in two validation datasets, respectively. Moreover, the constructed radiomics-based nomograms excelled the R-scores, clinical, CT features alone in terms of predicting EGFR mutation status and subtypes, with AUCs of 0.734 and 0.757 in two validation datasets, respectively.

Conclusions: Radiomics-based nomogram, incorporating clinical characteristics, CT features and radiomic features, can non-invasively and efficiently predict the EGFR mutation status and thus potentially fulfill the ultimate purpose of precision medicine. The methodology is a possible promising strategy to predict EGFR mutation subtypes, providing the support of clinical treatment scenario.

Clinicopathologic and Imaging Features of Non-Small-Cell Lung Cancer with MET Exon 14 Skipping Mutations

MET exon 14 (METex14) skipping mutations are an emerging potentially targetable oncogenic driver mutation in non-small-cell lung cancer (NSCLC). The imaging features and patterns of metastasis of NSCLC with primary METex14 skipping mutations (METex14-mutated NSCLC) are not well described. Our goal was to determine the clinicopathologic and imaging features that may suggest the presence of METex14 skipping mutations in NSCLC. This IRB-approved retrospective study included NSCLC patients with primary METex14 skipping mutations and pre-treatment imaging data between January 2013 and December 2018. The clinicopathologic characteristics were extracted from electronic medical records. The imaging features of the primary tumor and metastases were analyzed by two thoracic radiologists. In total, 84 patients with METex14-mutated NSCLC (mean age = 71.4 ± 10 years; F = 52, 61.9%, M = 32, 38.1%; smokers = 47, 56.0%, nonsmokers = 37, 44.0%) were included in the study. Most tumors were adenocarcinoma (72; 85.7%) and presented as masses (53/84; 63.1%) that were peripheral in location (62/84; 73.8%). More than one in five cancers were multifocal (19/84; 22.6%). Most patients with metastatic disease had only extrathoracic metastases (23/34; 67.6%). Fewer patients had both extrathoracic and intrathoracic metastases (10/34; 29.4%), and one patient had only intrathoracic metastases (1/34, 2.9%). The most common metastatic sites were the bones (14/34; 41.2%), the brain (7/34; 20.6%), and the adrenal glands (7/34; 20.6%). Four of the 34 patients (11.8%) had metastases only at a single site. METex14-mutated NSCLC has distinct clinicopathologic and radiologic features.

Dual-energy spectral CT characteristics in surgically resected lung adenocarcinoma: comparison between Kirsten rat sarcoma viral oncogene mutations and epidermal growth factor receptor mutations

BACKGROUND

Kirsten rat sarcoma viral oncogene homolog (KRAS) and epidermal growth factor receptor (EGFR) are the two most frequent and well-known oncogene of lung adenocarcinoma. The purpose of this study is to compare the characteristics measured with dual-energy spectral computed tomography (DESCT) in lung adenocarcinoma patients who have KRAS and EGFR gene mutations.

METHODS

Patients with surgically resected lung adenocarcinoma (n = 72) were enrolled, including 12 patients with KRAS mutations and 60 patients with EGFR mutations. DESCT quantitative parameters, including the CT number at 70 keV, the slopes of the spectral attenuation curves (slope λ HU), normalized iodine concentration (NIC), normalized water concentration (NWC), and effective atomic number (effective Z), were analyzed. A multiple logistic regression model was applied to discriminate clinical and DESCT characteristics between the types of mutations.

RESULTS

The KRAS mutation was more common in people who smoked than the EGFR mutation. Nodule type differed significantly between the KRAS and EGFR groups (P = 0.035), and all KRAS mutation adenocarcinomas were solid nodules. Most DESCT quantitative parameters differed significantly between solid nodules and subsolid nodules. CT number at 70 keV, slope λ HU, NIC, and effective Z differed significantly between the KRAS and EGFR groups (P = 0.006, 0.017, 0.013 and 0.010) with solid lung adenocarcinoma. Multivariate logistic analysis of DESCT and clinical features indicated that besides smoking history, the CT value at 70 keV (OR = 0.938, P = 0.009) was significant independent factor that could be used to differentiate KRAS and EGFR mutations in solid lung adenocarcinoma.

CONCLUSIONS

DESCT would be a potential tool to differentiate lung adenocarcinoma patients with a KRAS mutation from those with an EGFR mutation.

Cancer genome landscape: a radiologist's guide to cancer genome medicine with imaging correlates

The introduction of high throughput sequence analysis in the past decade and the decrease in sequencing costs has made available an enormous amount of genomic data. These data have shaped the landscape of cancer genome, which encompasses mutations determining tumorigenesis, the signaling pathways involved in cancer growth, the tumor heterogeneity, and its role in development of metastases. Tumors develop acquiring a series of driver mutations over time. Of the many mutated genes present in cancer, only few specific mutations are responsible for invasiveness and metastatic potential, which, in many cases, have characteristic imaging appearance. Ten signaling pathways, each with targetable components, have been identified as responsible for cancer growth. Blockage of any of these pathways form the basis for molecular targeted therapies, which are associated with specific pattern of response and toxicities. Tumor heterogeneity, responsible for the different mutation pattern of metastases and primary tumor, has been classified in intratumoral, intermetastatic, intrametastatic, and interpatient heterogeneity, each with specific imaging correlates. The purpose of this article is to introduce the key components of the landscapes of cancer genome and their imaging counterparts, describing the types of mutations associated with tumorigenesis, the pathways of cancer growth, the genetic heterogeneity involved in metastatic disease, as well as the current challenges and opportunities for cancer genomics research.

Computed Tomography Imaging Features and Distribution of Metastases in ROS1-rearranged Non-Small-cell Lung Cancer

BACKGROUND

ROS proto-oncogene 1 (ROS1) rearrangements are a known molecular target in non-small-cell lung cancer (NSCLC). Our goal was to determine whether ROS1-rearranged NSCLC has imaging features and patterns of metastasis, which differ from those of anaplastic lymphoma kinase (ALK)-rearranged or epidermal growth factor receptor (EGFR)-mutant NSCLC.

PATIENTS AND METHODS

We retrospectively identified patients with metastatic ROS1-rearranged, ALK-rearranged, or EGFR-mutant NSCLC from January 2014 to June 2018 and included those with pretreatment imaging studies available. We assessed the imaging features of the primary tumor and the distribution of metastases in these patients. The Wilcoxon rank-sum test and Fisher exact test were used to compare the imaging features.

RESULTS

We identified 257 patients (167 women and 90 men; median age, 56 years; range, 19-90 years) with metastatic NSCLC (ROS1, 53; ALK, 87; EGFR, 117). Compared with ALK-rearranged or EGFR-mutant NSCLC, ROS1-rearranged NSCLC was less likely to present with extrathoracic metastases (ROS1, 49%; ALK, 75%; EGFR, 72%; P < .01), including brain metastases (ROS1, 9%; ALK, 25%; EGFR, 40%; P < .04). Compared with EGFR-mutant NSCLC, ROS1-rearranged tumors were more likely to exhibit imaging features of lymphangitic carcinomatosis (ROS1, 42%; EGFR, 12%; P < .01) and less likely to have air bronchograms in the primary tumor (ROS1, 2%; EGFR, 28%; P < .01). ROS1-rearranged tumors were also more likely to present with distant nodal metastases (ROS1, 15%; EGFR, 2%; P < .01) and sclerotic-type bone metastases (ROS1, 17%; EGFR, 6%; P < .01).

CONCLUSION

Although considerable overlap exists in the imaging features of ROS1-rearranged, ALK-rearranged, and EGFR-mutant NSCLC, we found that ROS1-rearranged NSCLC has certain distinct imaging features and patterns of spread.

Diffuse Lung Metastases in EGFR-Mutant Non-Small Cell Lung Cancer

Diffuse lung metastases have been reported in non-small cell lung cancer (NSCLC) harboring epidermal growth factor receptor (EGFR) mutations. The purpose of our study was to compare the incidence of diffuse lung metastases in EGFR-mutant NSCLC and EGFR-wild type NSCLC and to assess other imaging features that may be associated with diffuse lung metastases in EGFR-mutant NSCLC. Two radiologists retrospectively reviewed pre-treatment imaging of metastatic NSCLC cases with known EGFR mutation status. We assessed the imaging features of the primary tumor and patterns of metastases. The cohort consisted of 217 patients (117 EGFR-mutant, 100 EGFR wild-type). Diffuse lung metastasis was significantly more common in EGFR-mutant NSCLC compared with wild-type (18% vs. 3%, p < 0.01). Among the EGFR-mutant group, diffuse lung metastases were inversely correlated with the presence of a nodule greater than 6 mm other than the primary lung lesion (OR: 0.13, 95% CI: 0.04–0.41, p < 0.01). EGFR mutations in NSCLC are associated with increased frequency of diffuse lung metastases. The presence of diffuse lung metastases in EGFR-mutant NSCLC is also associated with a decreased presence of other larger discrete lung metastases. EGFR mutations in NSCLC should be suspected in the setting of a dominant primary lung mass associated with diffuse lung metastases.

CT Characteristics of Non-Small Cell Lung Cancer With Anaplastic Lymphoma Kinase Rearrangement: A Systematic Review and Meta-Analysis

OBJECTIVE. The purpose of this study was to perform a systematic review and meta-analysis regarding CT features of non-small cell lung cancer (NSCLC) with anaplastic lymphoma kinase (ALK) rearrangement. MATERIALS AND METHODS. The PubMed and Embase databases were searched up to February 20, 2019. Studies that evaluated CT features of NSCLC with and without ALK rearrangement was included. Methodologic quality was assessed using Quality Assessment of Diagnostic Accuracy Studies-2. The association between CT features and ALK rearrangement was pooled in the form of the odds ratio (OR) or the mean difference (MD) using the random-effects model. Heterogeneity was examined using the inconsistency index (I²). Publication bias was examined using funnel plots and Egger tests. RESULTS. Sixteen studies were included, consisting of 3113 patients with NSCLC. The overall prevalence of patients with ALK rearrangement was 17% (528/3113). Compared with NSCLC without ALK rearrangement, on CT images those with ALK rearrangement were more frequently solid (OR = 2.86), central in location (OR = 2.72), and 3 cm or smaller (OR = 0.57); had lower contrast-enhanced CT attenuation (MD = -4.79 HU); more frequently had N2 or N3 disease (OR = 5.63), lymphangitic carcinomatosis (OR = 3.46), pleural effusion (OR = 1.91), or pleural metastasis (OR = 1.81); and less frequently had lung metastasis (OR = 0.66). Heterogeneity varied among CT features (I² = 0-80%). No significant publication bias was seen (p = 0.15). CONCLUSION. NSCLC with ALK rearrangement had several distinctive CT features compared with that without ALK rearrangement. These CT biomarkers may help identify patients likely to have ALK rearrangement.

A Radiologist's Guide to the Changing Treatment Paradigm of Advanced Non-Small Cell Lung Cancer: The ASCO 2018 Molecular Testing Guidelines and Targeted Therapies

OBJECTIVE. The purpose of this article is to provide an imaging-based guide of the modern genomic classifications and targeted therapies for advanced non-small cell lung cancer (NSCLC) with an emphasis on the relevance of the 2018 American Society of Clinical Oncology molecular testing guidelines for radiologists. CONCLUSION. Knowledge of the radiologic relevance of lung cancer driver mutations and modern targeted agents is essential for imaging interpretation of advanced NSCLC in the modern age of precision medicine.

Machine learning-based radiomics strategy for prediction of cell proliferation in non-small cell lung cancer

PURPOSE

To explore the feasibility and performance of machine learning-based radiomics classifier to predict the cell proliferation(Ki-67)in non-small cell lung cancer (NSCLC).

METHODS

245 histopathological confirmed NSCLC patients who underwent CT scans were retrospectively included. The Ki-67 proliferation index (Ki-67 PI) were measured within 2 weeks after CT scans. A lesion volume of interest (VOI) was manually delineated and radiomics features were extracted by MaZda software from CT images. A random forest feature selection algorithm (RFFS) was used to reduce features. Six kinds of machine learning methods were used to establish radiomics classifiers, subjective imaging feature classifiers and combined classifiers, respectively. The performance of these classifiers was evaluated by the receiver operating characteristic curve (ROC) and compared with Delong test.

RESULTS

103 radiomics features were extracted and 20 optimal features were selected using RFFS. Among the radiomics classifiers established by six machine learning methods, random forest-based radiomics classifier achieved the best performance (AUC = 0.776) in predicting the Ki-67 expression level with sensitivity and specificity of 0.726 and 0.661, which was better than that of subjective imaging classifiers (AUC = 0.625, P < 0.05). However, the combined classifiers did not improve the predictive performance (AUC = 0.780, P > 0.05), with sensitivity and specificity of 0.752 and 0.633.

CONCLUSIONS

The machine learning-based CT radiomics classifier in NSCLC can facilitate the prediction of the expression level of Ki-67 and provide a novel non-invasive strategy for assessing the cell proliferation.

The role of the ground-glass opacity ratio in resected lung adenocarcinoma

OBJECTIVES

The goal of this study was to investigate the role of the ground-glass opacity (GGO) ratio in lung adenocarcinoma in predicting surgical outcomes.

METHODS

Patients who underwent surgical resection for pulmonary adenocarcinoma between January 2004 and December 2013 were reviewed. The clinical data, imaging characteristics of nodules, surgical approaches and outcomes were analysed with a mean follow-up of 87 months.

RESULTS

Of 789 enrolled patients, 267 cases were categorized as having a GGO ratio ≥0.75; 522 cases were categorized as having a GGO ratio <0.75. The gender, tumour differentiation, epidermal growth factor receptor mutation, smoking habits, lymphovascular space invasion, tumour size, maximum standard uptake value and carcinoembryonic antigen levels were significantly different in the 2 groups. In the group with a GGO ratio ≥0.75, 63.3% of the patients underwent sublobar resection (18.8% with a GGO ratio < 0.75, P <0.001). These patients had fewer relapses (2.2% for GGO ratio ≥0.75, 26.8% for GGO ratio <0.75, P < 0.001) and a better 5-year survival rate (95.5% for GGO ratio ≥0.75, 77.4% for GGO ratio <0.75, P < 0.001). None of the patients with a GGO ratio ≥0.75 had lymph node involvement. The multivariable Cox regression analysis revealed that a GGO ratio <0.75 was an independent factor for postoperative relapse with a hazard ratio of 3.96.

CONCLUSIONS

A GGO ratio ≥0.75 provided a favourable prognostic prediction in patients with resected lung adenocarcinoma. Sublobar resection and lymph node sampling revealed a fair outcome regardless of tumour size. However, anatomical resection is still the standard approach for patients with tumours with a GGO ratio <0.75, size >2 cm.

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.

Mutational pressure and natural selection in epidermal growth factor receptor gene during germline and somatic mutagenesis in cancer cells

In this study we investigated nucleotide usage biases along the length of a gene encoding human epidermal growth factor receptor (EGFR) and found out that there had been mutational GC-pressure with stronger asymmetric C-pressure in that gene before the preferable direction of nucleotide mutations changed. Current preferable direction of germline mutations in EGFR gene has been estimated with the help of Ensembl data base of gene variations. Preferable direction of somatic mutations in EGFR gene from cancer cells has been estimated with the help of COSMIC data base. Both germline and somatic mutations in cancer cells have the same GC to AT preferable direction in EGFR gene. These data have been used with the aim to find fragments of EGFR gene that have lower probability of missense C to T and G to A transitions to occur. So, the less mutable parts of extracellular EGFR domain are: C-terminal part of the first beta barrel and the central part of the second beta barrel. The less mutable parts of tyrosine kinase EGFR domain are: ATP-binding site (partially), regulatory alpha helix, and fragments that change their secondary structure during the activation process. These parts of EGFR should be considered as the best targets for new types of therapy development. Such criterion as low mutability is especially important for the selection of targets for anti-tumor therapy, since we have detected positive selection of amino acid replacements during somatic mutagenesis of EGFR gene in cancer cells.

Computed Tomography-Based Radiomics Signature: A Potential Indicator of Epidermal Growth Factor Receptor Mutation in Pulmonary Adenocarcinoma Appearing as a Subsolid Nodule

BACKGROUND

Lung adenocarcinoma (LADC) with epidermal growth factor receptor (EGFR) mutation is considered a subgroup of lung cancer sensitive to EGFR-targeted tyrosine kinase inhibitors. We aimed to develop and validate a computed tomography (CT)-based radiomics signature for prediction of EGFR mutation status in LADC appearing as a subsolid nodule.

MATERIALS AND METHODS

A total of 467 eligible patients were divided into training and validation cohorts (n = 306 and 161, respectively). Radiomics features were extracted from unenhanced CT images by using Pyradiomics. A CT-based radiomics signature for distinguishing EGFR mutation status was constructed using the random forest (RF) method in the training cohort and then tested in the validation cohort. A combination of the radiomics signature with a clinical factors model was also constructed using the RF method. The performance of the model was evaluated using the area under the curve (AUC) of a receiver operating characteristic curve.

RESULTS

In this study, 64.2% (300/467) of the patients showed EGFR mutations. L858R mutation of exon 21 was the most common mutation type (185/301). We identified a CT-based radiomics signature that successfully discriminated between EGFR positive and EGFR negative in the training cohort (AUC = 0.831) and the validation cohort (AUC = 0.789). The radiomics signature combined with the clinical factors model was not superior to the simple radiomics signature in the two cohorts (p > .05).

CONCLUSION

As a noninvasive method, the CT-based radiomics signature can be used to predict the EGFR mutation status of LADC appearing as a subsolid nodule.

IMPLICATIONS FOR PRACTICE

Lung adenocarcinoma (LADC) with epidermal growth factor receptor (EGFR) mutation is considered a subgroup of lung cancer that is sensitive to EGFR-targeted tyrosine kinase inhibitors. However, some patients with inoperable subsolid LADC are unable to undergo tissue sampling by biopsy for molecular analysis in clinical practice. A computed tomography-based radiomics signature may serve as a noninvasive biomarker to predict the EGFR mutation status of subsolid LADCs when mutational profiling is not available or possible.

CT and clinical characteristics that predict risk of EGFR mutation in non-small cell lung cancer: a systematic review and meta-analysis

INTRODUCTION

To systematically analyze CT and clinical characteristics to find out the risk factors of epidermal growth factor receptor (EGFR) mutation in non-small cell lung cancer (NSCLC). Then the significant characteristics were used to set up a mathematic model to predict EGFR mutation in NSCLC.

MATERIALS AND METHODS

PubMed, Web of Knowledge and EMBASE up to August 17, 2018 were systematically searched for relevant studies that investigated the evidence of association between CT and clinical characteristics and EGFR mutation in NSCLC. After study selection, data extraction, and quality assessment, the pooled odds ratios (ORs) were calculated. Then from May 2017 to August 2018, all NSCLC received EGFR mutation examination and CT examination in our hospital were chosen to test the prediction model by receiver operating characteristic (ROC) curves.

RESULTS

Seventeen original studies met the inclusion criteria. The results showed that the ORs of ground-glass opacity (GGO), air bronchogram, pleural retraction, vascular convergence, smoking history, female gender were, respectively, 1.93 (P = 0.003), 2.09 (P = 0.03), 1.59 (P < 0.01), 1.61 (P = 0.001), 0.28 (P < 0.01), 0.35 (P < 0.01). The result of speculation, cavitation/bubble-like lucency, lesion shape, margin, pathological stage were, respectively, 1.19 (P = 0.32), 0.99 (P = 0.97), 0.82 (P = 0.42), 1.02 (P = 0.90), 0.77 (P = 0.30). 121 NSCLC received EGFR mutation test were included to test the prediction model. The mathematical model based on the results of meta-analysis was: 0.74 × air bronchogram + 0.46 × pleural retraction + 0.48 × vascular convergence - 1.27 × non-smoking history - 1.05 × female. The area under the ROC curve was 0.68.

CONCLUSION

Based on the current evidence, GGO presence, air bronchogram, pleural retraction, vascular convergence were significant risk factors of EGFR mutation in NSCLC. And the prediction model can help to predict EGFR mutation status.

Imaging characteristics of BRAF-mutant non-small cell lung cancer by functional class

OBJECTIVES

Mutations in the BRAF gene have emerged as a validated molecular target in the treatment of non-small cell lung cancer (NSCLC). These mutations can be classified into three functional classes based on their mechanisms of oncogenesis. The relationship between these functional classes and their imaging features has not been systematically investigated. The goal of this work is to determine if imaging features of the primary tumor and the pattern of metastasis correlate with the functional class of BRAF mutation.

METHODS

We reviewed pre-treatment computed tomography (CT) images of patients with BRAF-mutated NSCLC with known functional class. We assessed and recorded the features of the primary tumor and the patterns of lymphadenopathy and distant metastasis. Wilcoxon rank-sum test and Kruskal-Wallis test were performed to compare continuous characteristics, and Fisher's exact test was used to compare categorical features between groups.

RESULTS AND CONCLUSIONS

105 patients with BRAF-mutant NSCLC had pre-treatment imaging available for review (n = 43 class I, n = 40 class II, and n = 22 class III). Approximately half of the primary tumors were considered masses (n = 54/105, 51%) and most were solid (n = 81/105, 77%). There were no statistically significant differences in imaging features of the primary tumor among the three functional classes. Intrathoracic metastases occurred more frequently in class I tumors compared to tumors with class II and III mutations (p = 0.03). The odds of class I mutation were higher among tumors involving the pleural space (OR: 4.39, 95% CI: 1.11-17.4) and lower among tumors disseminating to the abdomen (OR: 0.25, 95% CI: 0.07-0.92). Our findings suggest that class I (V600) mutated NSCLC may be more likely to have intrathoracic metastases, while classes II and III (non-V600) mutated NSCLC may be more likely to have intra-abdominal metastases at the time of presentation.

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

OBJECTIVE

This study assessed the ability of conventional computed tomography (CT) features (including primary tumors, metastatic lesions, lymph nodes, and emphysema) to predict epidermal growth factor receptor (EGFR) mutations in advanced pulmonary adenocarcinoma.

METHODS

Patients who were diagnosed with advanced pulmonary adenocarcinoma between January 2017 and August 2017 and had undergone a chest CT and EGFR mutation testing were enrolled in this retrospective study. Qualitative and quantitative CT-features and clinical characteristics evaluated in this study included: primary tumor location, size, and morphology (including degree of lobulation, density, calcification, cavitation, vacuole sign, and air bronchogram), size and distribution of lung and pleural metastatic nodules, size and status of hilar and mediastinal lymph nodes, emphysema, organs with distant metastasis, and patient age, sex, and smoking history.

RESULTS

Of 201 patients, 107 (53.23%) were EGFR-mutation positive. The multivariate logistic regression indicated that EGFR mutations were significantly associated with smaller lymph nodes, a lower percentage of deep lobulation of the primary tumor and partial fusion of lymph nodes, and absence of emphysema. The area under the curve of logistic regression model for predicting EGFR mutations was 0.898.

CONCLUSIONS

Conventional CT-features, including emphysema, degree of primary tumor lobulation, and lymph node size and status, help to predict the presence or absence of EGFR mutations in advanced pulmonary adenocarcinoma. Additionally, these same CT-features demonstrated that the CT manifestations of the EGFR mutant group were of relatively lower malignancy and less invasive as compared to the wild-type EGFR group.

Epidermal growth factor receptor mutation accelerates radiographic progression in lung adenocarcinoma presented as a solitary ground-glass opacity

Background

We aimed to investigate the impact of epidermal growth factor receptor (EGFR) mutation in the progression of lung adenocarcinoma presented as a solitary ground-glass opacity (GGO) by retrospectively evaluating the correlation between EGFR mutation status and the radiographic features.

Methods

One hundred fifty-six cases of lung adenocarcinoma presented as a solitary GGO were enrolled between 2013 and 2015. Chest CT scans were performed 3 times (1st ≥3 months, 2nd ≤1 week preoperatively and 3rd ≥3 months postoperatively) in each patient. The diameter and volume of every lesion was measured by semiautomated algorithm. EGFR mutation hotspots from exons 18, 19 and 21 were detected by real-time PCR.

Results

In the 156 patients who were enrolled in our study, tumors in 75 patients (48.1%) were pathologically diagnosed with EGFR-mutant, with 1, 29 and 45 cases harboring tumors with mutation in exon 18, 19 and 21, respectively. EGFR mutation occurred more frequently in women (P=0.005) and non-smokers (P=0.019). Comparison between the 1st and 2nd preoperative CT scans showed that 28 (37.3%) of 75 patients with EGFR mutations had an over 50% increment of tumor size and 38 (52.0%) displayed a growth of solid component. On the other hand, we found only 9 (11.1%) and 14 (17.3%) in 81 lesions without EGFR mutation had a distinct volume growth and component solidification, respectively, which is significantly less than that in EGFR mutation lesions (P<0.001). Further, in the postoperative CT scan, recurrent GGOs or nodes were identified in 6 (8%) EGFR-mutant patients and 6 (7.4%) in wild-type patients (P=0.89), which indicates no overt statistically difference. At last, we found that EGFR amplification is more frequent as GGO volume percentage decreases and diameter increases.

Conclusions

We found GGOs with EGFR mutation grew faster in volume and solidified more quickly in component than wild-type GGOs. Moreover, in the follow-up after surgery, patients in the EGFR mutation group and EGFR wild-type group showed no significant difference in the imaging evolvement.

Identification of epidermal growth factor receptor mutations in pulmonary adenocarcinoma using dual-energy spectral computed tomography

OBJECTIVES

To explore the role of dual-energy spectral computed tomography (DESCT) quantitative characteristics for the identification of epidermal growth factor receptor (EGFR) mutation status in a cohort of East Asian patients with pulmonary adenocarcinoma.

MATERIALS AND METHODS

Patients with lung adenocarcinoma who underwent both DESCT chest examination and EGFR test were retrospectively selected from our institution's database. The DESCT visual morphological features and quantitative parameters, including the CT number at 70 keV, normalized iodine concentration (NIC), normalized water concentration, and slopes of the spectral attenuation curves (slope λ HU [Hounsfield unit]), were evaluated or calculated. The patients were divided into two groups: the EGFR mutation group and EGFR wild-type group. Statistical analyses were performed to identify the DESCT quantitative parameters for diagnosis of EGFR mutation status.

RESULTS

EGFR mutations were detected in 66 (55.0%) of the 120 enrolled patients. The univariate analysis revealed that sex, smoking history, CT texture, NIC, and slope λ HU were significantly associated with EGFR mutation status (p = 0.037, 0.001, 0.047, 0.010, and 0.018, respectively). The multivariate logistic analysis revealed that smoking history (odds ratio [OR] = 3.23, p = 0.005) and NIC (OR = 58.026, p = 0.049) were the two significant predictive factors associated with EGFR mutations. Based on this analysis, the smoking history and NIC were combined to determine the predictive value for EGFR mutations with the area under the curve of 0.702.

CONCLUSIONS

NIC may be a potential quantitative DESCT parameter for predicting EGFR mutations in patients with pulmonary adenocarcinoma.

KEY POINTS

• DESCT can provide multiple quantitative image parameters compared to conventional CT. • Identification of the radio-genomic relation between DESCT and EGFR status can help to define molecular subcategories of lung adenocarcinoma, which is valuable for personalized clinical targeted therapy. • NIC may be a potential DESCT quantitative parameter for predicting EGFR mutations in pulmonary adenocarcinoma.

Computed tomography characteristics of lung adenocarcinomas with epidermal growth factor receptor mutation: A propensity score matching study

OBJECTIVES

We investigated the relationship between computed tomography (CT) characteristics and epidermal growth factor receptor (EGFR) mutations in a large Asian cohort who received surgical resection of invasive lung adenocarcinoma.

MATERIALS AND METHODS

We retrospectively included 864 patients (524 with EGFR mutation and 340 with EGFR wild-type) who received surgical resections for invasive lung adenocarcinomas. After applying propensity score matching, 312 patients with mutated EGFR were matched with 312 patients with wild-type EGFR. CT characteristics, predominant histologic subtype, and CT measurement parameters (volume and estimated diameter of the total tumor and inner solid portion and ground-glass opacity [GGO] proportion) were compared within matched pairs.

RESULTS

Tumors in the EGFR mutation group showed higher proportions of pure ground-glass nodules (4.1% vs 1.3%), GGO-predominant (23.7% vs 14.7%), and solid-predominant part-solid nodules (37.2% vs 31.7%) CT characteristics, whereas EGFR wild-type tumors predominantly presented as pure solid nodules (34.6% vs 52.2%, P < 0.0001). EGFR mutation tumors more frequently had a lepidic-predominant subtype than did EGFR wild-type tumors (20.2% and 11.9%; P < 0.0001), and showed a smaller whole tumor size and solid portion (P < 0.0001) with a higher GGO proportion (P < 0.0001). Tumors with exon 21 missense mutations showed the highest GGO proportion and the smallest inner solid portion size, followed by tumors harboring an exon 19 deletion, compared with EGFR wild-type tumors (posthoc P < 0.01).

CONCLUSION

Adenocarcinomas with EGFR mutations had a higher GGO proportion than those with wild-type EGFR after matching of clinical variables. Lesions with an exon 21 mutation had a higher GGO proportion than lesions with other mutations.

Ground-glass opacity heralding invasive lung adenocarcinoma with prodromal dermatomyositis: a case report

Background

Dermatomyositis, an inflammatory myopathy with cutaneous involvement, is associated with malignancy and often manifests paraneoplastically. While co-occurrence with small cell carcinoma is well attested, primary lung adenocarcinoma, which may present as focal ground-glass opacification on computed tomography of the thorax, is less frequently coincident.

Case presentation

We report the case of a 72-year-old female patient with dermatomyositis — treated with a combination of prednisone, methotrexate, and intravenous immunoglobulin — and an indolent, subsolid, non-hypermetabolic pulmonary lesion, which was determined to be invasive primary lung adenocarcinoma. Supporting a paraneoplastic basis, immunosuppressive therapy was discontinued following tumor excision without relapse of signs or symptoms of dermatomyositis.

Conclusions

While dermatomyositis prodromal to lung adenocarcinoma is not without precedent, association with an indolent, subsolid lesion has, to the best of our knowledge, not been reported. The case described herein illustrates the importance of maintaining a high index of suspicion for malignancy in the setting of dermatomyositis.