scholarly journals Integrating Gene Mutation Mutual Exclusion Information Into Radiomics Algorithms to Improve Gene Mutation Prediction in Non-small Cell Lung Cancer

2021 ◽  
Author(s):  
Jingyi Wang ◽  
Xing Lv ◽  
Xin Cao ◽  
Weicheng Huang ◽  
Zhiyong Quan ◽  
...  
Keyword(s):  
Gene Mutation ◽  
Egfr Mutation ◽  
Mutual Exclusion ◽  
Gene Mutations ◽  
Composite Model ◽  
Kras Gene ◽  
Kras Mutations ◽  
Mutation Status ◽  
Pet Ct ◽  
Mutation Information

Abstract Purpose Gene mutations are mutually exclusive in non-small cell lung cancer (NSCLC). Using EGFR and KRAS as examples, this study aims to assess the significance of mutation mutual exclusion information in the optimization of radiomics algorithms for predicting gene mutation.Methods We retrospectively analyzed 161 NSCLC patients with 18F-FDG PET/CT scans and EGFR and KRAS gene mutation data. Patients were randomly divided into training and testing cohorts. The Pyradiomics toolkit was used for radiomics feature extraction. Based on these features, radiomics score (RS) models were developed for predicting KRAS mutations using the gradient boosting decision tree (GBDT) algorithm. Furthermore, to investigate the value of adding mutation mutual exclusion information, a composite model combining PET/CT RS and EGFR mutation status was developed using logistic regression. The area under the curve (AUC), specificity, sensitivity, and accuracy were calculated for model performance evaluation in the training and test cohorts. To test the generalizability of this optimization method, models for predicting EGFR mutation were established in parallel, with or without adding KRAS gene mutation information.Results Compared with CT, the PET/CT based RS model exhibited higher AUC (KRAS: 0.792 vs 0.426; EGFR: 0.786 vs 0.644). By integrating EGFR mutation information into the PET/CT RS model, the AUC, accuracy, and specificity for predicting KRAS mutations were all elevated in the test cohort (0.928, 0.857, 0.897 vs 0.792, 0.755, 0.769). Conversely, the composite model for predicting EGFR mutations could also be optimized by adding KRAS gene mutation information (AUC, accuracy, and specificity: 0.877, 0.776, 0.700 vs 0.786, 0.694, 0.567). By adding EGFR and KRAS exclusive mutation information, respectively, the composite model corrected 55.4% and 30.7% false positive cases produced by the PET/CT RS model in the test cohort, without sacrificing sensitivity.Conclusion Integrating the mutation status of a known gene is a potential method to optimize radiomics models for predicting another gene mutation. This method may help predict unconventional gene mutations when the second biopsy is clinically difficult to carry out.

scholarly journals The value of haematological parameters and serum tumour markers for predicting KRAS mutations in 784 Chinese colorectal cancer patients: a retrospective analysis

BMC Cancer ◽  
2020 ◽  
Vol 20 (1) ◽  
Author(s):  
Yinghao Cao ◽  
Junnan Gu ◽  
Lizhao Yan ◽  
Shenghe Deng ◽  
Fuwei Mao ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Logistic Regression ◽  
Predictive Value ◽  
Gene Mutations ◽  
Haematological Parameters ◽  
Multivariate Logistic Regression ◽  
Kras Gene ◽  
Kras Mutations ◽  
Mutation Status ◽  
Serum Tumour

Abstract Background Identifying the mutation status of KRAS is important for optimizing treatment in patients with colorectal cancer (CRC). The aim of this study was to investigate the predictive value of haematological parameters and serum tumour markers (STMs) for KRAS gene mutations. Methods The clinical data of patients with colorectal cancer from January 2014 to December 2018 were retrospectively collected, and the associations between KRAS mutations and other indicators were analysed. Receiver operating characteristic (ROC) curve analysis was performed to quantify the predictive value of these factors. Univariate and multivariate logistic regression models were applied to identify predictors of KRAS mutations by calculating the odds ratios (ORs) and their corresponding 95% confidence intervals (CIs). Results KRAS mutations were identified in 276 patients (35.2%). ROC analysis revealed that age, CA12–5, AFP, SCC, CA72–4, CA15–3, FERR, CYFRA21-1, MCHC, and tumor location could not predict KRAS mutations (P = 0.154, 0.177, 0.277, 0.350, 0.864, 0.941, 0.066, 0.279, 0.293, and 0.053 respectively), although CEA, CA19–9, NSE and haematological parameter values showed significant predictive value (P = 0.001, < 0.001, 0.043 and P = 0.003, < 0.001, 0.001, 0.031, 0.030, 0.016, 0.015, 0.019, and 0.006, respectively) but without large areas under the curve. Multivariate logistic regression analysis showed that CA19–9 was significantly associated with KRAS mutations and was the only independent predictor of KRAS positivity (P = 0.016). Conclusions Haematological parameters and STMs were related to KRAS mutation status, and CA19–9 was an independent predictive factor for KRAS gene mutations. The combination of these clinical factors can improve the ability to identify KRAS mutations in CRC patients.

scholarly journals Performance of 18F-FDG PET/CT Radiomics for Predicting EGFR Mutation Status in Patients With Non-Small Cell Lung Cancer

2020 ◽  
Vol 10 ◽  
Author(s):  
Min Zhang ◽  
Yiming Bao ◽  
Weiwei Rui ◽  
Chengfang Shangguan ◽  
Jiajun Liu ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Small Cell Lung Cancer ◽  
Fdg Pet ◽  
Egfr Mutation ◽  
Small Cell ◽  
Small Cell Lung ◽  
Mutation Status ◽  
Pet Ct ◽  
18F Fdg ◽  
Fdg Pet Ct

Assessing EGFR gene mutation status in non-small cell lung cancer with imaging features from PET/CT

2019 ◽  
Vol 40 (8) ◽  
pp. 842-849 ◽  
Author(s):  
Mengmeng Jiang ◽  
Yiqian Zhang ◽  
Junshen Xu ◽  
Min Ji ◽  
Yinglong Guo ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Small Cell Lung Cancer ◽  
Gene Mutation ◽  
Small Cell ◽  
Imaging Features ◽  
Small Cell Lung ◽  
Mutation Status ◽  
Egfr Gene ◽  
Pet Ct ◽  
Egfr Gene Mutation

Expression level of NRP1 and SMAD2 in correlation to mutational status of RAS (BRAF) in pancreatic cancer.

2019 ◽  
Vol 37 (15_suppl) ◽  
pp. e15784-e15784
Author(s):  
Libor Stanek ◽  
Petra Tesarova ◽  
Robert Gurlich
Keyword(s):  
Pancreatic Cancer ◽  
Tumor Growth ◽  
Gene Mutation ◽  
Expression Level ◽  
Wild Type ◽  
Braf Gene ◽  
Kras Gene ◽  
Mutation Status ◽  
Mutational Status ◽  
Neuropilin 1

e15784 Background: Pancreatic cancer is the second leading cause of death in tumor diseases worldwide. Neuropilin-1 (NRP1) is overexpressed in many tumors including the pancreatic cancer. The main goal is to reveal the role of NRP1 in the process of tumorigenesis. The expression of NRP1 and the presence of KRAS point mutation lead to the cell survival by lowering the SMAD2 phosphorylation. On the other hand, the NRP1 inactivation and the wild-type KRAS in tumor cells lead to the tumor growth inhibition. Our aim is to prove correlation between NRP1 level, SMAD2 and the mutational status of KRAS, NRAS in prognosis of patients with pancreatic cancer. Methods: Retrospective study is based on analysis of 50 FFPE bioptical samples (40 resections, 8 punctures, 2 thin-needle biopsies); histology verified all as adenocarcinomas. The expression level of NRP1 and SMAD2 is measured by Imunohistochemistry by mice monoclonal antibodies Anti-Neuropilin 1 and Anti-SMAD2 (Abcan) on the device BenchMark ULTRA (Ventana Medical Systems), Roche. DNA isolation is executed by QIAamp DNA Mini Kit. We used Codon Specific Mutation Detection Kit (Diatech pharmacogenetics) for detection of somatic point mutations in codons 12, 13, 61 and 146 of KRAS and NRAS genes. BRAF mutational status was revealed by direct sequencing on ABI Prism 3130. We monitor the level of expression of NRP1 and SMAD2 and correlate it to the mutational status of RAS and BRAF, and disease prognosis. Results: NRP1 expression was detected in 24 out of 50 cases, SMAD2 expression was detected in 13 of 50 cases, other cases without expression. KRAS gene mutation was detected in 8 cases out of 60, other cases of WT. Mutation in the NRAS gene was detected in 3 of 50 cases. BRAF gene mutation was detected in 1 case out of 50, other WT. NRP1 expression correlated with KRAS gene mutation status in 9 cases and a strong correlation (p = < 0.001) was recorded. One case of mutation in the BRAF gene correlated with KRAS mutation status and NRP1 expression. Due to the small number of samples tested, without statistical significance. Inactivation of NRP1 was detected in 15 cases and was confirmed by the WT status of the KRAS gene. Conclusions: Was demonstrated that causal relationship exists between inactive NRP1 and wild-type KRAS, and that these should cause decrease of the rate of tumor growth. These characteristics, which are achievable simultaneously during the histological verification, may serve as a potential prognostic marker for subsequent decision of how radical surgical resection should be.

scholarly journals Prediction of EGFR Mutation Status Based on 18F-FDG PET/CT Imaging Using Deep Learning-Based Model in Lung Adenocarcinoma

2021 ◽  
Vol 11 ◽  
Author(s):  
Guotao Yin ◽  
Ziyang Wang ◽  
Yingchao Song ◽  
Xiaofeng Li ◽  
Yiwen Chen ◽  
...  
Keyword(s):  
Deep Learning ◽  
Lung Adenocarcinoma ◽  
Fdg Pet ◽  
Egfr Mutation ◽  
Learning Models ◽  
Data Set ◽  
Mutation Status ◽  
Pet Ct ◽  
Testing Data ◽  
Fdg Pet Ct

ObjectiveThe purpose of this study was to develop a deep learning-based system to automatically predict epidermal growth factor receptor (EGFR) mutant lung adenocarcinoma in 18F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT).MethodsThree hundred and one lung adenocarcinoma patients with EGFR mutation status were enrolled in this study. Two deep learning models (SECT and SEPET) were developed with Squeeze-and-Excitation Residual Network (SE-ResNet) module for the prediction of EGFR mutation with CT and PET images, respectively. The deep learning models were trained with a training data set of 198 patients and tested with a testing data set of 103 patients. Stacked generalization was used to integrate the results of SECT and SEPET.ResultsThe AUCs of the SECT and SEPET were 0.72 (95% CI, 0.62–0.80) and 0.74 (95% CI, 0.65–0.82) in the testing data set, respectively. After integrating SECT and SEPET with stacked generalization, the AUC was further improved to 0.84 (95% CI, 0.75–0.90), significantly higher than SECT (p&lt;0.05).ConclusionThe stacking model based on 18F-FDG PET/CT images is capable to predict EGFR mutation status of patients with lung adenocarcinoma automatically and non-invasively. The proposed model in this study showed the potential to help clinicians identify suitable advanced patients with lung adenocarcinoma for EGFR‐targeted therapy.

scholarly journals A Predictive Model of EGFR Mutation Status in Patients with Lung Adenocarcinoma Based on PET/CT Metabolic Indexes and Clinicopathological Variables

2020 ◽  
Author(s):  
Yanlong Yang ◽  
Shuchen Shi ◽  
Qianzhun Huang ◽  
Wenzhao Zhong ◽  
Juntao Lin ◽  
...  
Keyword(s):  
Lung Adenocarcinoma ◽  
Growth Pattern ◽  
Egfr Mutation ◽  
Clinicopathological Characteristics ◽  
Metabolic Parameters ◽  
Smoking History ◽  
Egfr Mutations ◽  
Wild Type ◽  
Mutation Status ◽  
Pet Ct

Abstract PurposeThe purpose of this study was to create a mathematical model based on the metabolic parameters of PET/CT with clinicopathological characteristics to predict the EGFR mutation status of patients with lung adenocarcinoma.MethodsThis study retrospectively enrolled patients with lung adenocarcinoma who underwent surgical treatment at two centres in China between January 2012 and December 2015. PET/CT metabolic parameters and Classical EGFR mutation status detection by molecular pathology were performed before and after surgery, and we analysed the associations of EGFR mutation status with patient sex, age, smoking history, maximum primary lesion diameter, carcinoembryonic antigen (CEA), neuron-specific enolase (NSE), cytokeratin 19 fragment (CYFRA21-1), TNM stage and histopathological subtype of lung adenocarcinoma.ResultsA total of 310 patients were included, comprising 161 with EGFR mutations (51.9%) and 149 with wild-type EGFR (48.1%). EGFR mutations were more common in females, non-smokers, and those with stage IV disease, a low SUVmax, and ≤35 mm nodules, whereas wild-type EGFR was more common in males, smokers, and those with a solid growth pattern. Multivariate analysis suggested that liver SUVratio, smoking history, tumour size, TNM stage, and solid growth pattern can predict EGFR mutation status, and these factors were used to construct a mathematical model.ConclusionThe prediction model constructed in this study based on clinicopathological characteristics and PET/CT parameters might offer a basis by which to predict Classical EGFR status and provide a certain reference value for guiding the use of EGFR-tyrosine kinase inhibitor (EGFR-TKI) treatment in patients with lung adenocarcinoma.

scholarly journals In CLL with Normal Karyotype By Conventional and Genomic Array Karyotyping the Prognostic Impact of an Unmutated IGHV Status Is Stronger Than the Impact of Gene Mutations

Blood ◽  
2016 ◽  
Vol 128 (22) ◽  
pp. 4357-4357 ◽  
Author(s):  
Calogero Vetro ◽  
Torsten Haferlach ◽  
Manja Meggendorfer ◽  
Sabine Jeromin ◽  
Constance Regina Baer ◽  
...  
Keyword(s):  
Gene Mutation ◽  
Mutation Rate ◽  
Gene Mutations ◽  
Normal Karyotype ◽  
Prognostic Impact ◽  
Employment Equity ◽  
Mutation Status ◽  
Genomic Array ◽  
Equity Ownership ◽  
The Impact

Abstract Background: In 15-20% of CLL cases no aberrations are detected by chromosome banding analysis (CBA) and FISH due to limited resolution, lack of evaluable metaphases or presence of aberrations in loci not covered by standard-panel FISH probes. As reported in our previous study (Haferlach C. et al., ASH 2015, abs ID#79545), genomic arrays (GA) detected abnormalities in almost 20% of cases classified as normal by CBA and FISH and these showed an impact on time to first treatment (TTT) (Vetro C. et al., EHA 2016, abs ID# E1069). The CLL subgroup without abnormalities in CBA, FISH, and GA has not been characterised in detail, so far. Aims: 1) to describe CLL without abnormalities by CBA/FISH/GA by evaluating an extended gene panel, the IGHV mutation status and the B-cell receptor (BCR) stereotypy; 2) to determine prognostic impact of these factors. Patients and Methods: CLL diagnosis was based on cytomorphology and immunophenotyping according to standard guidelines. From a cohort of 1190 patients at diagnosis, 133 (11%) were selected based on normal karyotype by CBA, no abnormalities by interphase FISH with probes for 17p13 (TP53), 13q14 (D13S25, D13S319, DLEU), 11q22 (ATM), centromeric region of chromosome 12 and t(11;14)(q13;q32) (IGH-CCND1) and no abnormalities by GA (SurePrint G3 ISCA CGH+SNP Microarray, Agilent, Waldbronn, Germany). IGHV mutation status and BCR stereotypy were determined according to Agathangelidis et al., Blood 2012, and DNA sequencing was performed for the following genes: ATM; SF3B1; TP53; KLHL6; KRAS; MYD88; NOTCH1; NRAS; POT1; FBXW7; HIST1H1E; XPO1; ITPKB; MAPK1; BIRC3; BRAF; DDX3X; EGR2; RIPK1; RPS15; CND2. Results: Median age was 66 years (range: 33-83). Median follow-up was 5.6 years, 33 patients (25%) received treatment since genetic analyses. 10-year overall survival (OS) was 76% and median TTT was 9.2 years. Mutations were observed in 53 patients (40%): SF3B1 (n=17; 13%); NOTCH1 (n=10; 8%); KLHL6 (n=6; 5%); TP53 (n=6; 5%); ATM (n=5; 4%); XPO1 (n=4; 3%); FBXW7 (n=3; 2%); MYD88 (n=3; 2%); DDX3X (n=2; 2%); POT1 (n=2; 1.5%); ITPKB (n=1; 1%); KRAS (n=1; 1%); NRAS (n=1; 1%); and no mutation in RPS15, CCND2, MAPK1, EGR2, BRAF, HIST1H1E, RIPK1, BIRC3. 6 patients had 2 simultaneous gene mutations and 1 patient had 3 (i.e. NOTCH1, ATM and TP53). A mutated IGHV status (IGHV-M) was present in 100 patients (75%) and an unmutated IGHV status (IGHV-U) in 33 patients (25%). IGHV-U was related to both the occurrence of any gene mutation (p<0.001) and the number of gene mutations (p=0.001). NOTCH1 was mutated in 7 out of the 33 IGHV-U patients (21%), but only in 3 out of 99 IGHV-M patients (3%) (p=0.001). XPO1 mutation occurred in 4 IGHV-U patients (12%) and none out of IGHV-M (p<0.001). Two IGHV-U patients showed POT1 mutation (6%), but no IGHV-M case (p=0.014). 9 patients out of 133 (7%) showed BCR-stereotypy. 2 were in cluster CLL#1 (both showing NOTCH1 mutation), 2 in cluster CLL#2 (both of them with SF3B1 mutation), 2 in CLL#4, 1 in CLL#8 (showing NOTCH1 and XPO1 mutations), 1 in CLL#201 (with KLHL6 mutation) and 1 in CLL#202 (with mutations in ATM, TP53 and NOTCH1 genes). In Kaplan-Meier analysis, IGHV-M patients did not reach a median TTT, while IGHV-U had a median of 5.1 years (p<0.001). Stereotypy rate was too low for reliable statistics. At univariate analysis, TTT was only influenced by: IGHV-U (relative risk (RR): 3.9, p<0.001), TP53 mutation (RR: 3.7, p=0.03), % CLL cells (RR: 1.2 per 10% increase, p=0.013), and number of mutations (RR: 1.8 per each mutation, p=0.031). Multivariate Cox regression analysis showed an independent role for IGHV-U status (RR: 3.3, p=0.002) and % CLL cells (RR: 1.2 per 10% increase, p=0.038) Only age showed an impact on OS (RR: 1.2 per decade, p<0.001). Conclusions: 1. The CLL subset without any genomic event by CBA/FISH/genomic array is characterized by very low frequency of IGHV-U status; 2. IGHV-U subgroup showed higher gene mutation rate compared to IGHV-M subgroup, in particular higher NOTCH1, XPO1 and POT1 mutation rate; 3. BCR stereotypy is less frequent than in CLL in general. 4. IGHV-U, as well as the higher disease burden (i.e. % CLL cells), has an independent negative impact on TTT. 5. Requirement for treatment is low and prognosis very favorable in CLL without any genomic event by CBA/FISH/genomic array and a mutated IGHV status. Disclosures Vetro: MLL Munich Leukemia Laboratory: Employment. Haferlach:MLL Munich Leukemia Laboratory: Employment, Equity Ownership. Meggendorfer:MLL Munich Leukemia Laboratory: Employment. Jeromin:MLL Munich Leukemia Laboratory: Employment. Baer:MLL Munich Leukemia Laboratory: Employment. Nadarajah:MLL Munich Leukemia Laboratory: Employment. Kern:MLL Munich Leukemia Laboratory: Employment, Equity Ownership. Haferlach:MLL Munich Leukemia Laboratory: Employment, Equity Ownership.

Genetic and proteomic features associated with survival after treatment with erlotinib in first-line therapy of non-small cell lung cancer

2009 ◽  
Vol 27 (15_suppl) ◽  
pp. 8089-8089
Author(s):  
J. M. Amann ◽  
J. Lee ◽  
H. Roder ◽  
J. Brahmer ◽  
J. Schiller ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Targeted Therapies ◽  
Egf Receptor ◽  
Egfr Mutation ◽  
Egfr Mutations ◽  
First Line ◽  
Serum Samples ◽  
Kras Mutations ◽  
Mutation Status ◽  
Molecular Features

8089 Background: An improved understanding of molecular features of cancers and cancer patients associated with benefit from targeted therapies could allow the rational personalization of therapies to increase the probability of efficacy and decrease toxicity and cost. Multiple biomarkers have been proposed for predicting benefit after therapy with EGF receptor targeted therapies in first line colon and second line lung cancer therapy. Methods: In this study, we analyzed available tumor and serum samples from ECOG 3503, a single arm phase II study of erlotinib in first line lung cancer, for mutations in Kras and EGFR, as well as the previously described serum MALDI proteomic classifier (Veristrat). Out of 137 enrolled patients, there were 93 serum samples and 43 tumor samples available. Results: Molecular analysis of a subset of tumors from patients enrolled in ECOG 3503 shows that 10/43 (23%) contained Kras mutations and 3/43 (7%) harbored EGFR mutations. Classification of the 93 available sera for the pattern of proteins previously published as associated with survival after treatment with gefitinib identified 68/93 (73%) as predicted to be “good” and 25/93 (27%) predicted to have poor survival. Of the 6 responders with available serum, 5 were classified as MALDI good. Correlation with survival demonstrated a highly statistically significant correlation with MALDI status (p < 0.001), and a marginally significant association of EGFR mutation with survival (p = 0.05), but no correlation with ras mutation status. Median survival was 10.8 months in MALDI good patients and 3.9 in MALDI poor patients. MALDI status was independent of both ras and EGFR mutation status. Conclusions: Thus, in distinct contrast to colon cancer, ras gene mutations do not appear to be associated with survival after first line EGFR-targeted therapy in lung cancer. The previously defined MALDI predictor is potent and highly clinically significantly associated with survival after first line treatment with erlotinib, and is independent of mutations in ras and EGFR in this dataset. [Table: see text]

Sign in / Sign up

Export Citation Format

Share Document