Epidermal Growth Factor Receptor Mutation Status Research Articles

Predicting epidermal growth factor receptor mutations in non-small cell lung cancer through dual-layer spectral CT: a prospective study

ObjectiveTo determine whether quantitative parameters of detector-derived dual-layer spectral computed tomography (DLCT) can reliably identify epidermal growth factor receptor (EGFR) mutation status in patients with non-small cell lung cancer (NSCLC).MethodsPatients with NSCLC who underwent arterial phase (AP) and venous phase (VP) DLCT between December 2021 and November 2022 were subdivided into the mutated and wild-type EGFR groups following EGFR mutation testing. Their baseline clinical data, conventional CT images, and spectral images were obtained. Iodine concentration (IC), iodine no water (INW), effective atomic number (Zeff), virtual monoenergetic images, the slope of the spectral attenuation curve (λHU), enhancement degree (ED), arterial enhancement fraction (AEF), and normalized AEF (NAEF) were measured for each lesion.ResultsNinety-two patients (median age, 61 years, interquartile range [51, 67]; 33 men) were evaluated. The univariate analysis indicated that IC, normalized IC (NIC), INW and ED for the AP and VP, as well as Zeff and λHU for the VP were significantly associated with EGFR mutation status (all p < 0.05). INW(VP) showed the best diagnostic performance (AUC, 0.892 [95% confidence interval {CI}: 0.823, 0.960]). However, neither AEF (p = 0.156) nor NAEF (p = 0.567) showed significant differences between the two groups. The multivariate analysis showed that INW(AP) and NIC(VP) were significant predictors of EGFR mutation status, with the latter showing better performance (p = 0.029; AUC, 0.897 [95% CI: 0.816, 0.951] vs. 0.774 [95% CI: 0.675, 0.855]).ConclusionQuantitative parameters of DLCT can help predict EGFR mutation status in patients with NSCLC.Critical relevance statementQuantitative parameters of DLCT, especially NIC(VP), can help predict EGFR mutation status in patients with NSCLC, facilitating appropriate and individualized treatment for them.Key PointsDetermining EGFR mutation status in patients with NSCLC before starting therapy is essential.Quantitative parameters of DLCT can predict EGFR mutation status in NSCLC patients.NIC in venous phase is an important parameter to guide individualized treatment selection for NSCLC patients.Graphical

Abstract CT154: Phase 1/2 clinical trial of JIN-A02, a 4th generation EGFR-TKI, in patients with 3rd generation EGFR-TKI resistance in EGFR mutated advanced/metastatic non-small cell lung cancer (NSCLC)

Abstract Background: Epidermal growth factor receptor (EGFR) mutations are the most common driver mutations in NSCLC. EGFR tyrosine kinase inhibitors (TKIs) are the recommended front-line option for EGFR-mutant advanced NSCLC patients, but patients invariably develop acquired resistance and face disease progression. JIN-A02, a 4th generation EGFR-TKI intended for oral administration, selectively and reversibly binds to EGFR mutations, including the C797S and/or T790M mutation that causes resistance to 3rd generation of EGFR-TKIs. Pre-clinical studies with EGFR C797S and/or T790M mutated cell lines showed that JIN-A02 can inhibit cell growth in a dose dependent manner and has a high degree of selectivity over wild-type EGFR. In vivo studies showed that administration of JIN-A02 dose-dependently inhibited tumor growth in the C797S+ xenograft mice model. Moreover, JIN-A02 shown to penetrate blood-brain barrier and exhibit anti-tumor activity in an intracranial tumor model. The strong potency and high selectivity of JIN-A02 for mutant EGFR may offer improved therapeutic window in the clinical setting vs available EGFR-TKIs. Methods: JIN-A02 is being evaluated in this Phase 1/2, multicenter, an open-label trial (NCT05394831) for subjects with advanced NSCLC harboring C797S and/or T790M mutation as a monotherapy. The primary object of this study is to assess safety, tolerability, pharmacokinetics, and anti-tumor effect for determining the recommended phase 2 dose (RP2D) of JIN-A02. The inclusion criteria are that the subject (≥ 18 years) must have an advanced or metastatic NSCLC showed progress disease (PD) after receiving approved standard EGFR-TKI therapies and/or platinum-based anticancer chemotherapy is allowed up to 1 time after using EGFR-TKI treatment with ECOG status 0 or 1. Before enrollment in the study, the EGFR mutation status is determined using either tumor tissue and/or plasma ctDNA. This study comprises three parts, dose escalation (Part A), dose exploration (Part B), and dose expansion (Part C). In Part A, dose escalation, comprised of 5 cohorts ranged from a starting dose of 12.5 mg P.O, QD to a top dose of 150 mg P.O, QD with every three subjects, is carried out where the maximum tolerated dose (MTD) is evaluated in subjects with 28-day cycles. Dose-limiting toxicities (DLT) are evaluated for 21 days. In Part B, dose exploration is carried out to evaluate the safety of JIN-A02 further and to determine the RP2D using 2 preliminary effective dose levels from Part A in subjects. In Part C dose-expansion study, subjects (n=36 for each cohort) are divided into 5 different cohorts based on the EGFR mutation (both or single positive of C797S and T790M), and the anti-tumor activity of JIN-A02 is evaluated according to RECIST v1.1 at RP2D. Citation Format: Sun Min Lim, Byoung Chul Cho, Ji Youn Han, Sang We Kim, Ki Hyeong Lee, Misako Nagasaka, Anna Jo, Ethan Seah, Choonok Kim, Thanyanan Reungwetwattana. Phase 1/2 clinical trial of JIN-A02, a 4th generation EGFR-TKI, in patients with 3rd generation EGFR-TKI resistance in EGFR mutated advanced/metastatic non-small cell lung cancer (NSCLC) [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 2 (Late-Breaking, Clinical Trial, and Invited Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(7_Suppl):Abstract nr CT154.

Imaging Genomics of Glioma Revisited: Analytic Methods to Understand Spatial and Temporal Heterogeneity.

An improved understanding of the cellular and molecular biologic processes responsible for brain tumor development, growth, and resistance to therapy is fundamental to improving clinical outcomes. Imaging genomics is the study of the relationships between microscopic, genetic, and molecular biologic features and macroscopic imaging features. Imaging genomics is beginning to shift clinical paradigms for diagnosing and treating brain tumors. This article provides an overview of imaging genomics in gliomas, in which imaging data including hallmarks such as IDH-mutation, MGMT methylation, and EGFR-mutation status can provide critical insights into the pretreatment and posttreatment stages. This article will accomplish the following: 1) review the methods used in imaging genomics, including visual analysis, quantitative analysis, and radiomics analysis; 2) recommend suitable analytic methods for imaging genomics according to biologic characteristics; 3) discuss the clinical applicability of imaging genomics; and 4) introduce subregional tumor habitat analysis with the goal of guiding future radiogenetics research endeavors toward translation into critically needed clinical applications.

Abstract 6149: Polygenic risk score and lung adenocarcinoma risk among never-smokers by EGFR mutation status

Abstract Background: Lung cancer is the leading cause of cancer mortality worldwide, and incidence rates for the disease in never-smokers is among the highest in East Asian (EAS) women. Epidermal growth factor receptor (EGFR) is a transmembrane protein that regulates cellular proliferation and apoptosis, and mutations in the EGFR gene have been found to be a defining hallmark of lung adenocarcinoma (LUAD). We investigated if overall genetic susceptibility to LUAD, defined as a polygenic risk score (PRS), is differentially associated with LUAD by EGFR mutation status. Methods: The study consists of 998 female never-smoking histologically confirmed LUAD cases with data on EGFR mutation status and 4,544 female never-smoking controls from the Female Lung Cancer Consortium in Asia. Germline DNA samples were genotyped using the 370K, 610Q, or 660W microarrays. Genomic DNA extracted from fresh, frozen or formalin-fixed paraffin-embedded tumor tissue samples of LUAD cases were genotyped for EGFR mutations on exons 19 and 21. We defined cases with EGFR mutation on either exon as EGFR+ (n=518) and cases without such EGFR mutation as EGFR- (n=480). Weights from 942,592 single nucleotide variants derived from a previously conducted genome-wide association study were used in a Bayesian-based approach, LDpred2, to derive a PRS for all participants. We estimated the odds ratios (OR) and 95% confidence intervals (CI) for the association between continuous PRS, PRS quartiles and tumor EGFR mutation status using logistic regression models in a case-case analysis, as well as using a multinomial logistic regression treating controls as the reference. All models were adjusted for age, study and the top 10 principal components. Results: In case-case comparisons, compared to EGFR- LUAD, we found a positive association between continuous PRS and risk of EGFR+ LUAD (OR=1.17, 95% CI: 1.02, 1.34), as well as a dose-response relationship between quartiles of the PRS and EGFR+ LUAD (p-trend=0.003). We further found that the association between the fourth quartile of the PRS with EGFR+ LUAD (OR=8.63, 95% CI: 5.67, 13.14) was significantly higher than the association between the fourth quartile of the PRS with EGFR- LUAD (OR=3.50, 95% CI: 2.44, 5.00) compared to controls (p-heterogeneity=0.004). Conclusions: We found that the PRS developed for LUAD in EAS individuals was more strongly associated with EGFR+ LUAD compared to EGFR- LUAD, suggesting that germline genetic susceptibility may be differentially associated with LUAD in never-smoking female EAS patients depending on the cancer’s mutation status. Given that patients with LUAD respond differently to treatments that are used as targeted therapy depending on their EGFR mutation status, our findings may have important public health and clinical implications, which may guide risk stratification, screening, and treatment. Citation Format: Batel Blechter, Chao Agnes Hsiung, Keitaro Matsuo, Kouya Shiraishi, Kevin Wang, Haoyu Zhang, Wei Jie Seow, Jianxin Shi, Nilanjan Chatterjee, Jason Y.Y. Wong, Juncheng Dai, H. Dean Hosgood, I-Shou Chang, Jiyeon Choi, Wei Hu, Wei Zheng, Young Tae Kim, Xiao-Ou Shu, Qiuyin Cai, Pan-Chyr Yang, Dongxin Lin, Kexin Chen, Yi-Long Wu, Hongbin Shen, Takashi Kohno, Stephen J. Chanock, Nathaniel Rothman, Qing Lan. Polygenic risk score and lung adenocarcinoma risk among never-smokers by EGFR mutation status [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 6149.

Abstract 4084: Potent anti-tumor activity of ABN202 (anti-EGFR antibody-interferon-beta mutein) through direct cytotoxicity and indirect immune activation against non-small cell lung cancer, regardless of EGFR mutation status

Abstract Epidermal growth factor receptor (EGFR) is overexpressed or mutated in many patients with non-small cell lung cancer (NSCLC). Targeting EGFR mutation by tyrosine kinase inhibitors (TKIs) has significantly improved overall survival (OS) in patients with EGFR mutations. However, many patients experience tumor recurrence due to various resistance mechanisms. Therefore, there is an unmet medical need for new treatment strategies for patients with EGFR-positive NSCLC, regardless of EGFR mutation status. ABN202 is an antibody-cytokine fusion protein (ACFP) that serves as a platform technology compromising the IFN-β mutein (ABN102) fused to various antibodies for specific tumor targeting. In a previous study, we designed ABN202 (αEGFR) to comprise an EGFR targeting antibody (Cetuximab) and IFN-β mutein (ABN102) and we confirmed anti-cancer activities of ABN202 against EGFR-positive NSCLC. In this study, the direct cytotoxicity of ABN202 (αEGFR) was evaluated in human NSCLC cell lines with various driving mutations and EGFR expression levels. The indirect immune activation was tested in human peripheral blood mononuclear cells (PBMCs) and human IFNAR1/2 knock-in (KI) mice. The in vivo efficacy was evaluated in human NSCLC xenograft mouse models and human IFNAR1/2 KI mouse models. ABN202 (αEGFR) demonstrates potent anti-tumor activity through direct cytotoxicity and indirect immune activation in NSCLC, regardless of EGFR mutation status. Taken together, we suggest that ABN202 (αEGFR) is a promising drug candidate against NSCLC, regardless of EGFR mutation status. Citation Format: Hee Geon Park, Sung Hun Cho, Ha Yeon Park, Mi Gyoung Jo, Ji Hyun Park, Myeung Ryun Seo, Ji Hyun Kim, Sung Youl Hong, Kyoung Song, Chan Gyu Lee, Hae Min Jeong, Sae Hyung Lee, Na Young Kim, Jun Young Choi, Young Kee Shin. Potent anti-tumor activity of ABN202 (anti-EGFR antibody-interferon-beta mutein) through direct cytotoxicity and indirect immune activation against non-small cell lung cancer, regardless of EGFR mutation status [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 4084.

Improved Prediction of Epidermal Growth Factor Receptor Status by Combined Radiomics of Primary Nonsmall-Cell Lung Cancer and Distant Metastasis.

This study aimed to investigate radiomics based on primary nonsmall-cell lung cancer (NSCLC) and distant metastases to predict epidermal growth factor receptor (EGFR) mutation status. A total of 290 patients (mean age, 58.21 ± 9.28) diagnosed with brain (BM, n = 150) or spinal bone metastasis (SM, n = 140) from primary NSCLC were enrolled as a primary cohort. An external validation cohort, consisting of 69 patients (mean age, 59.87 ± 7.23; BM, n = 36; SM, n = 33), was enrolled from another center. Thoracic computed tomography-based features were extracted from the primary tumor and peritumoral area and selected using the least absolute shrinkage and selection operator regression to build a radiomic signature (RS-primary). Contrast-enhanced magnetic resonance imaging-based features were calculated and selected from the BM and SM to build RS-BM and RS-SM, respectively. The RS-BM-Com and RS-SM-Com were developed by integrating the most important features from the primary tumor, BM, and SM. Six computed tomography-based features showed high association with EGFR mutation status: 3 from intratumoral and 3 from peritumoral areas. By combination of features from primary tumor and metastases, the developed RS-BM-Com and RS-SM-Com performed well with areas under curve in the training (RS-BM-Com vs RS-BM, 0.936 vs 0.885, P = 0.177; RS-SM-Com vs RS-SM, 0.929 vs 0.843, P = 0.003), internal validation (RS-BM-Com vs RS-BM, 0.920 vs 0.858, P = 0.492; RS-SM-Com vs RS-SM, 0.896 vs 0.859, P = 0.379), and external validation (RS-BM-Com vs RS-BM, 0.882 vs 0.805, P = 0.263; RS-SM-Com vs RS-SM, 0.865 vs 0.816, P = 0.312) cohorts. This study indicates that the accuracy of detecting EGFR mutations significantly enhanced in the presence of metastases in primary NSCLC. The established radiomic signatures from this approach may be useful as new predictors for patients with distant metastases.

Deep-Learning-Based Predictive Imaging Biomarker Model for EGFR Mutation Status in Non-Small Cell Lung Cancer from CT Imaging.

The authors aimed to develop and validate deep-learning-based radiogenomic (DLR) models and radiomic signatures to predict the EGFR mutation in patients with NSCLC, and to assess the semantic and clinical features that can contribute to detecting EGFR mutations. Using 990 patients from two NSCLC trials, we employed an end-to-end pipeline analyzing CT images without precise segmentation. Two 3D convolutional neural networks segmented lung masses and nodules. The combined radiomics and DLR model achieved an AUC of 0.88 ± 0.03 in predicting EGFR mutation status, outperforming individual models. Semantic features further improved the model's accuracy, with an AUC of 0.88 ± 0.05. CT semantic features that were found to be significantly associated with EGFR mutations were pure solid tumours with no associated ground glass component (p < 0.03), the absence of peripheral emphysema (p < 0.03), the presence of pleural retraction (p = 0.004), the presence of fissure attachment (p = 0.001), the presence of metastatic nodules in both the tumour-containing lobe (p = 0.001) and the non-tumour-containing lobe (p = 0.001), the presence of ipsilateral pleural effusion (p = 0.04), and average enhancement of the tumour mass above 54 HU (p < 0.001). This AI-based radiomics and DLR model demonstrated high accuracy in predicting EGFR mutation, serving as a non-invasive and user-friendly imaging biomarker for EGFR mutation status prediction.

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

BackgroundTo 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).MethodsRetrospective 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.ResultsTS_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.ConclusionPET/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.

Impact of central nervous system metastasis after complete resection of lung adenocarcinomas harboring common EGFR mutation – A real-world database study in Japan: The CReGYT-01 EGFR study

ObjectivesTo clarify the impact of central nervous system (CNS) metastasis on performance status (PS) at relapse, on subsequent treatment(s), and on survival of patients with lung adenocarcinoma harboring common epidermal growth factor receptor (EGFR) mutation. MethodsWe conducted the multicenter real-world database study for patients with radical resections for lung adenocarcinomas between 2015 and 2018 at 21 centers in Japan. EGFR mutational status was examined at each center. ResultsOf 4181 patients enrolled, 1431 underwent complete anatomical resection for lung adenocarcinoma harboring common EGFR mutations. Three-hundred-and-twenty patients experienced disease relapse, and 78 (24%) had CNS metastasis. CNS metastasis was significantly more frequent in patients with conventional adjuvant chemotherapy than those without (30% vs. 20%, P = 0.036). Adjuvant chemotherapy did not significantly improve relapse-free survival at any pathological stage (adjusted hazard ratio for stage IA2–3, IB, and II-III was 1.363, 1.287, and 1.004, respectively). CNS metastasis did not affect PS at relapse. Subsequent treatment, mainly consisting of EGFR-tyrosine kinase inhibitors (TKIs), could be equally given in patients with or without CNS metastasis (96% vs. 94%). Overall survival after relapse was equivalent between patients with and without CNS metastasis. ConclusionThe efficacy of conventional adjuvant chemotherapy may be limited in patients with lung adenocarcinoma harboring EGFR mutations. CNS metastasis is likely to be found in practice before deterioration in PS, and may have little negative impact on compliance with subsequent EGFR-TKIs and survival after relapse. In this era of adjuvant TKI therapy, further prospective observational studies are desirable to elucidate the optimal management of CNS metastasis.

The efficacy of furmonertinib in untreated advanced NSCLC patients with sensitive EGFR mutations in a real-world setting: a single institutional experience.

Furmonertinib is the standard treatment option in the first-line setting for advanced non-small cell lung cancer (NSCLC) with sensitive epidermal growth factor receptor (EGFR) mutations in China. However, there are limited real-world data available. We conducted a retrospective study at a single center, analyzing a cohort of 73 NSCLC patients who tested positive for EGFR mutations and were treated with furmonertinib as their initial therapy between August 2022 and December 2023. The primary endpoint was progression-free survival (PFS), with secondary endpoints including objective response rate (ORR), overall survival (OS), and safety profile. The median observation period was 9 months (95% confidence interval [CI], 8.0-20.0). The median PFS was 19.5 months (95% CI, 14.6-24.4). OS data were not yet mature. Univariate analysis showed no significant correlation between PFS and factors such as Eastern Cooperative Oncology Group performance status (ECOG PS) score, presence of brain or liver metastases, sex, age, EGFR mutation status, or number of metastatic sites. However, multivariate analysis indicated a potential trend toward extended PFS in patients younger than 65 years (p = 0.053, 95% CI, 0.10-1.02), although the p-value was only marginally significant. The most common adverse events were diarrhea (24%), anemia (36%), and liver injury (32%); however, only four cases experienced severe adverse events. In a real-world setting, furmonertinib appears to be a favorable treatment option for EGFR-mutated patients. The manageable nature of adverse events further supports its use in clinical practice.

Clinical impact of pleural fluid carcinoembryonic antigen on therapeutic strategy and efficacy in lung adenocarcinoma patients with malignant pleural effusion.

Epidermal growth factor receptor (EGFR) mutation is important in determining the treatment strategy for advanced lung cancer patients with malignant pleural effusion (MPE). Contrary to serum carcinoembryonic antigen (S-CEA) levels, the associations between pleural fluid CEA (PF-CEA) levels and EGFR mutation status as well as between PF-CEA levels and treatment efficacy have rarely been investigated in lung adenocarcinoma patients with MPE. This retrospective study enrolled lung adenocarcinoma patients with MPE and available PF-CEA levels and EGFR mutation results. The patients were categorized based on PF-CEA levels: < 10 ng/mL, 10-100 ng/mL, 100-500 ng/mL, and ≥ 500 ng/mL. The association between PF-CEA levels and EGFR mutation status as well as their therapeutic impact on overall survival was compared among the four groups. This study included 188 patients. PF-CEA level was found to be an independent predictor of EGFR mutation but not S-CEA level. The EGFR mutation rates were higher as the PF-CEA levels increased, regardless of cytology results or sample types. Among EGFR-mutant lung adenocarcinoma patients receiving EGFR-tyrosine kinase inhibitor (TKI) treatment, those with high PF-CEA levels had significantly better survival outcomes than those with low PF-CEA levels. High PF-CEA levels were associated with high EGFR mutation rate and may lead to a favorable clinical outcome of EGFR-TKI treatment in EGFR-mutant lung adenocarcinoma patients with MPE. These findings highlight the importance of actively investigating EGFR mutation detection in patients with suspected MPE and elevated PF-CEA levels despite negative cytology results.

Molecular alterations and clinical prognostic factors in resectable non-small cell lung cancer

BackgroundEGFR inhibitor and immunotherapy have been approved for adjuvant treatment in resectable non-small cell lung cancer (NSCLC). Limited reports of molecular and clinical characteristics as prognostic factors in NSCLC have been published.MethodsMedical records of patients with resectable NSCLC stage I–III diagnosed during 2015–2020 were reviewed. Real time-PCR (RT-PCR) was performed for EGFR mutations (EGFRm). Immunohistochemistry staining was conducted for ALK and PD-L1 expression. Categorical variables were compared using chi-square test and Fisher’s exact test. Survival analysis was done by cox-regression method.ResultsTotal 441 patients were included. The prevalence of EGFRm, ALK fusion, and PD-L1 expression were 57.8%, 1.9%, and 20.5% (SP263), respectively. The most common EGFRm were Del19 (43%) and L858R (41%). There was no significant difference of recurrence free survival (RFS) by EGFRm status whereas patients with PD-L1 expression (PD-L1 positive patients) had lower RFS compared to without PD-L1 expression (PD-L1 negative patients) (HR = 1.75, P = 0.036). Patients with both EGFRm and PD-L1 expression had worse RFS compared with EGFRm and PD-L1 negative patients (HR = 3.38, P = 0.001). Multivariable analysis showed higher CEA at cut-off 3.8 ng/ml, pT4, pN2, pStage II, and margin were significant poor prognostic factors for RFS in the overall population, which was similar to EGFRm population (exception of pT and pStage). Only pStage was a significant poor prognostic factor for PD-L1 positive patients. The predictive score for predicting of recurrence were 6 for all population (63% sensitivity and 86% specificity) and 5 for EGFRm population (62% sensitivity and 93% specificity).ConclusionThe prevalence and types of EGFRm were similar between early stage and advanced stage NSCLC. While lower prevalence of PD-L1 expression was found in early stage disease. Patients with both EGFRm and PD-L1 expression had poorer outcome. Thus PD-L1 expression would be one of the prognostic factor in EGFRm patients. Validation of the predictive score should be performed in a larger cohort.

Value of multi-center 18 F-FDG PET/CT radiomics in predicting EGFR mutation status in lung adenocarcinoma.

Accurate, noninvasive, and reliable assessment of epidermal growth factor receptor (EGFR) mutation status and EGFR molecular subtypes is essential for treatment plan selection and individualized therapy in lung adenocarcinoma (LUAD). Radiomics models based on 18 F-FDG PET/CT have great potential in identifying EGFR mutation status and EGFR subtypes in patients with LUAD. The validation of multi-center data, model visualization, and interpretation are significantly important for the management, application and trust of machine learning predictive models. However, few EGFR-related research involved model visualization and interpretation, and multi-center trial. To develop explainable optimal predictive models based on handcrafted radiomics features (HRFs) extracted from multi-center 18 F-FDG PET/CT to predict EGFR mutation status and molecular subtypes in LUAD. Baseline 18 F-FDG PET/CT images of 383 LUAD patients from three hospitals and one public data set were collected. Further, 1808 HRFs were extracted from the primary tumor regions using Pyradiomics. Predictive models were built based on cross-combination of seven feature selection methods and seven machine learning algorithms. Yellowbrick and explainable artificial intelligence technology were used for model visualization and interpretation. Receiver operating characteristic curve, classification report and confusion matrix were used for model performance evaluation. Clinical applicability of the optimal models was assessed by decision curve analysis. STACK feature selection method combined with light gradient boosting machine (LGBM) reached optimal performance in identifying EGFR mutation status ([area under the curve] AUC=0.81 in the internal test cohort; AUC=0.62 in the external test cohort). Random forest feature selection method combined with LGBM reached optimal performance in predicting EGFR mutation molecular subtypes (AUC=0.89 in the internal test cohort; AUC=0.61 in the external test cohort). Explainable machine learning models combined with radiomics features extracted from multi-center/scanner 18 F-FDG PET/CT have certain potential to identify EGFR mutation status and subtypes in LUAD, which might be helpful to the treatment of LUAD.

The correlation between pre-treatment CEA levels and the EGFR mutation status in advanced lung adenocarcinoma.

The discovery of the epidermal growth factor receptor (EGFR) mutation, especially in adenocarcinoma, has led to a major change in the treatment of non-small-cell lung cancer (NSCLC). This study investigated the relationship between the EGFR mutation status and the carcinoembryonic antigen (CEA) levels at the time of diagnosis. A total of 102 patients with EGFR mutation and tested CEA levels were recruited for this study. Of the patients, 24 were EGFR mutants (23.5%), while 78 patients (76.5%) did not harbor any EGFR mutations. The CEA levels did not differ across groups. Additionally, the CEA levels were analyzed between female and male patients separately due to EGFR mutations; no difference was observed. When the CEA levels were categorized as positive or negative based on different cut-off values, such as 5 and 10 ng/ml, no statistical difference was found between groups. In this study, no relationship between EGFR mutation and pre-treatment CEA levels was observed. Despite positive trials having shown a predictive value of CEA levels for EGFR mutation, more clinical trials are needed to elucidate the racial, clinical, and pathological differences of the study populations. Most studies have been located in the Far East, but new trials in Caucasian, African, and Hispanic populations are still lacking.

Prognostic significance of integrating total metabolic tumor volume and EGFR mutation status in patients with lung adenocarcinoma.

The objective of this study was to investigate the prognostic significance of total metabolic tumor volume (TMTV) derived from baseline 18F-2-fluoro-2-deoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT), in conjunction with epidermal growth factor receptor (EGFR) mutation status, among patients with lung adenocarcinoma (LUAD). We performed a retrospective analysis on 141 patients with LUAD (74 males, 67 females, median age 67 (range 34-86)) who underwent 18F-FDG PET/CT and had their EGFR mutation status determined. Optimal cutoff points for TMTV were determined using time-dependent receiver operating characteristic curve analysis. The survival difference was compared using Cox regression analysis and Kaplan‒Meier curves. The EGFR mutant patients (n = 79, 56.0%) exhibited significantly higher 2-year progression-free survival (PFS) and overall survival (OS) rates compared to those with EGFR wild-type (n = 62, 44.0%), with rates of 74.2% vs 69.2% (P = 0.029) and 86.1% vs 67.7% (P = 0.009), respectively. The optimal cutoff values of TMTV were 36.42 cm3 for PFS and 37.51 cm3 for OS. Patients with high TMTV exhibited significantly inferior 2-year PFS and OS, with rates of 22.4% and 38.1%, respectively, compared to those with low TMTV, who had rates of 85.8% and 95.0% (both P < 0.001). In both the EGFR mutant and wild-type groups, patients exhibiting high TMTV demonstrated significantly inferior 2-year PFS and OS compared to those with low TMTV. In multivariate analysis, EGFR mutation status (hazard ratio, HR, 0.41, 95% confidence interval, CI [0.18-0.94], P = 0.034) and TMTV (HR 8.08, 95% CI [2.34-28.0], P < 0.001) were independent prognostic factors of OS, whereas TMTV was also an independent prognosticator of PFS (HR 2.59, 95% CI [1.30-5.13], P = 0.007). Our study demonstrates that the integration of TMTV on baseline 18F-FDG PET/CT with EGFR mutation status improves the accuracy of prognostic evaluation for patients with LUAD.

Transformation to small cell lung cancer is irrespective of EGFR and accelerated by SMAD4-mediated ASCL1 transcription independently of RB1 in non-small cell lung cancer

ObjectivesHistological transformation to small cell lung cancer (SCLC) has been identified as a mechanism of TKIs resistance in EGFR-mutant non-small cell lung cancer (NSCLC). We aim to explore the prevalence of transformation in EGFR-wildtype NSCLC and the mechanism of SCLC transformation, which are rarely understood.MethodsWe reviewed 1474 NSCLC patients to investigate the NSCLC-to-SCLC transformed cases and the basic clinical characteristics, driver gene status and disease course of them. To explore the potential functional genes in SCLC transformation, we obtained pre- and post-transformation specimens and subjected them to a multigene NGS panel involving 416 cancer-related genes. To validate the putative gene function, we established knocked-out models by CRISPR-Cas 9 in HCC827 and A549-TP53-/- cells and investigated the effects on tumor growth, drug sensitivity and neuroendocrine phenotype in vitro and in vivo. We also detected the expression level of protein and mRNA to explore the molecular mechanism involved.ResultsWe firstly reported an incidence rate of 9.73% (11/113) of SCLC transformation in EGFR-wildtype NSCLC and demonstrated that SCLC transformation is irrespective of EGFR mutation status (P = 0.16). We sequenced 8 paired tumors and identified a series of mutant genes specially in transformed SCLC such as SMAD4, RICTOR and RET. We firstly demonstrated that SMAD4 deficiency can accelerate SCLC transition by inducing neuroendocrine phenotype regardless of RB1 status in TP53-deficient NSCLC cells. Further mechanical experiments identified the SMAD4 can regulate ASCL1 transcription competitively with Myc in NSCLC cells and Myc inhibitor acts as a potential subsequent treatment agent.ConclusionsTransformation to SCLC is irrespective of EFGR status and can be accelerated by SMAD4 in non-small cell lung cancer. Myc inhibitor acts as a potential therapeutic drug for SMAD4-mediated resistant lung cancer.9vNWjpNbo9djtsBQF6k7BHVideo

The HIF-1α/PKM2 Feedback Loop in Relation to EGFR Mutational Status in Lung Adenocarcinoma

Objective Gene mutations in tumor cells can lead to several unique metabolic phenotypes, which are crucial for the proliferation of cancer cells. EGFR mutation (EGFR-mt) is the main oncogenic driving mutation in lung adenocarcinoma (LUAD). HIF-1 α and PKM2 are two key metabolic regulatory proteins that can form a feedback loop and promote cancer growth by promoting glycolysis. Here, the linkage between EGFR mutational status and HIF-1α/PKM2 feedback loop in LUAD were evaluated. Methods Retrospective study were performed on LUAD patients (n = 89) undergoing first-time therapeutic surgical resection. EGFR mutation was analyzed by real-time PCR. Immunohistochemistry was used to measure the expressions of HIF-1α and PKM2. Results We found that the protein expressions of HIF-1α and PKM2 were significantly higher in LUAD than normal lung tissues. In adenocarcinomas, the two protein expressions were both correlated with worse pTNM stage. Moreover, the correlation between the proteins of HIF-1α/PKM2 feedback loop and the EGFR mutational status were also analyzed. We found that EGFR-mt tumors showed higher HIF-1α and PKM2 proteins compared to tumors with EGFR wild-type. Meanwhile, HIF-1α expression was significantly correlated with higher pTNM stage, and PKM2 showed a similar trend, only in EGFR-mutated tumors. The expression of HIF-1α was positively correlated with PKM2 in LUAD, furthermore, this correlation was mainly in patients with EGFR-mt. Conclusion Different expression and clinical features of HIF-1α/PKM2 feedback loop was existed between LUAD and normal lung tissues, especially in EGFR mutational tumors, supporting the relationship between EGFR mutation and the key related proteins of aerobic glycolysis (HIF-1α and PKM2) in lung adenocarcinomas.

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

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. 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. 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. 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.

Non-invasive decision support for clinical treatment of non-small cell lung cancer using a multiscale radiomics approach

BackgroundSelecting therapeutic strategies for cancer patients is typically based on key target-molecule biomarkers that play an important role in cancer onset, progression, and prognosis. Thus, there is a pressing need for novel biomarkers that can be utilized longitudinally to guide treatment selection. MethodsUsing data from 508 non-small cell lung cancer (NSCLC) patients across three institutions, we developed and validated a comprehensive predictive biomarker that distinguishes six genotypes and infiltrative immune phenotypes. These features were analyzed to establish the association between radiological phenotypes and tumor genotypes/immune phenotypes and to create a radiological interpretation of molecular features. In addition, we assessed the sensitivity of the models by evaluating their performance at five different voxel intervals, resulting in improved generalizability of the proposed approach.Findings: The radiomics model we developed, which integrates clinical factors and multi-regional features, outperformed the conventional model that only uses clinical and intratumoral features. Our combined model showed significant performance for EGFR, KRAS, ALK, TP53, PIK3CA, and ROS1 mutation status with AUCs of 0.866, 0.874, 0.902, 0.850, 0.860, and 0.900, respectively. Additionally, the predictive performance for PD-1/PD-L1 was 0.852. Although the performance of all models decreased to different degrees at five different voxel space resolutions, the performance advantage of the combined model did not change. ConclusionsWe validated multiscale radiomic signatures across tumor genotypes and immunophenotypes in a multi-institutional cohort. This imaging-based biomarker offers a non-invasive approach to select patients with NSCLC who are sensitive to targeted therapies or immunotherapy, which is promising for developing personalized treatment strategies during therapy.

A deep learning model integrating multisequence MRI to predict EGFR mutation subtype in brain metastases from non-small cell lung cancer.

To establish a predictive model based on multisequence magnetic resonance imaging (MRI) using deep learning to identify wild-type (WT) epidermal growth factor receptor (EGFR), EGFR exon 19 deletion (19Del), and EGFR exon 21-point mutation (21L858R) simultaneously. A total of 399 patients with proven brain metastases of non-small cell lung cancer (NSCLC) were retrospectively enrolled and divided into training (n = 306) and testing (n = 93) cohorts separately based on two timepoints. All patients underwent 3.0-T brain MRI including T2-weighted, T2-weighted fluid-attenuated inversion recovery, diffusion-weighted imaging, and contrast-enhanced T1-weighted sequences. Radiomics features were extracted from each lesion based on four sequences. An algorithm combining radiomics approach with graph convolutional networks architecture (Radio-GCN) was designed for the prediction of EGFR mutation status and subtype. The area under the curve (AUC) at receiver operating characteristic analysis was used to evaluate the predication capabilities of each model. We extracted 1,290 radiomics features from each MRI sequence. The AUCs of the Radio-GCN model for identifying EGFR 19Del, 21L858R, and WT for the lesion-wise analysis were 0.996 ± 0.004, 0.971 ± 0.013, and 1.000 ± 0.000 on the independent testing cohort separately. It also yielded AUCs of 1.000 ± 0.000, 0.991 ± 0.009, and 1.000 ± 0.000for predicting EGFR mutations respectively for the patient-wise analysis. The κ coefficients were 0.735 and 0.812, respectively. The constructed Radio-GCN model is a new potential tool to predict the EGFR mutation status and subtype in NSCLC patients with brain metastases. The study demonstrated that a deep learning approach based on multisequence MRI can help to predict the EGFR mutation status in NSCLC patients with brain metastases, which is beneficial to guide a personalized treatment. • This is the first study to predict the EGFR mutation subtype simultaneously. • The Radio-GCN model holds the potential to be used as a diagnostic tool. • This study provides an imaging surrogate for identifying the EGFR mutation subtype.