LDA-SVM-based EGFR mutation model for NSCLC brain metastases: an observational study

Peritumoural MRI radiomics signature of brain metastases can predict epidermal growth factor receptor mutation status in lung adenocarcinoma

AIM

To investigate whether magnetic resonance imaging (MRI) radiomics features of brain metastases (BMs) can predict epidermal growth factor receptor (EGFR) mutation status in lung adenocarcinoma.

MATERIALS AND METHODS

Between June 2014 and December 2022, 58 histopathologically confirmed lung adenocarcinoma patients (27 with EGFR wild-type, 31 with EGFR mutation) who underwent gadobenate dimeglumine-enhanced brain MRI were recruited retrospectively. A total of 123 metastatic brain lesions were allocated randomly into the training cohort (n=86) and test cohort (n=37) at a ratio of 7:3. Radiomics models based on multi-sequence MRI images in different regions such as volume of interest (VOI)enhancing tumour, VOIwholetumour, VOIperitumour 1mm, VOIperitumour 3mm, and VOIperitumour 5mm were built. The optimal radiomics model was integrated into the clinical or radiological indicators to construct a fusion model through multivariable logistic regression analysis.

RESULTS

The optimal radiomics model based on the VOIperitumour 1mm, a combination of nine features selected from the fluid-attenuated inversion recovery (FLAIR) sequence, yielded areas under the curves (AUCs) of >0.75 in the training and test cohorts. The prediction of the fusion model with integration of clinical factors (age) and radiomics score (the optimal radiomics model) was not better than that of the optimal radiomics model alone in the test cohort (AUC: 0.808 and 0.785, respectively, p=0.525).

CONCLUSION

The FLAIR radiomics model based on VOIperitumour 1mm as an effective biomarker helps predict EGFR mutation status in lung adenocarcinoma patients with BMs and then assists clinicians in selecting optimal treatment strategies.

Diffusion tensor and postcontrast T1-weighted imaging radiomics to differentiate the epidermal growth factor receptor mutation status of brain metastases from non-small cell lung cancer

PURPOSE

To assess whether the radiomic features of diffusion tensor imaging (DTI) and conventional postcontrast T1-weighted (T1C) images can differentiate the epidermal growth factor receptor (EGFR) mutation status in brain metastases from non-small cell lung cancer (NSCLC).

METHODS

A total of 99 brain metastases in 51 patients who underwent surgery or biopsy with underlying NSCLC and known EGFR mutation statuses (57 from EGFR wild type, 42 from EGFR mutant) were allocated to the training (57 lesions in 31 patients) and test (42 lesions in 20 patients) sets. Radiomic features (n = 526) were extracted from preoperative MR images including T1C and DTI. Radiomics classifiers were constructed by combinations of five feature selectors and four machine learning algorithms. The trained classifiers were validated on the test set, and the classifier performance was assessed by determining the area under the curve (AUC).

RESULTS

EGFR mutation status showed an overall discordance rate of 12% between the primary tumors and corresponding brain metastases. The best performing classifier was a combination of the tree-based feature selection and linear discriminant algorithm and 5 features were selected (1 from ADC, 2 from fractional anisotropy, and 2 from T1C images), resulting in an AUC, accuracy, sensitivity, and specificity of 0.73, 78.6%, 81.3%, and 76.9% in the test set, respectively.

CONCLUSIONS

Radiomics classifiers integrating multiparametric MRI parameters may have potential in differentiating the EGFR mutation status in brain metastases from NSCLC.

Discordance of epidermal growth factor receptor mutation between primary lung tumor and paired distant metastases in non-small cell lung cancer: A systematic review and meta-analysis

Purpose

To evaluate the rate of discordance of epidermal growth factor receptor (EGFR) mutation between primary lung tumor and paired distant metastases in non-small-cell lung cancer (NSCLC).

Methods

We performed a meta-analysis of 17 studies (518 cases) assessing discordance rates of EGFR mutation in primary tumors and paired distant metastases. We performed subgroup analyses based on EGFR mutation status in primary tumor (mutant or wildtype), site of distant metastasis (bone, central nervous system (CNS) or lung/ pleural), methods of testing (direct sequencing or allele-specific testing) and timing of metastasis (synchronous or metachronous).

Results

The overall discordance rate in EGFR mutation was low at 10.36% (95% CI = 4.23% to 18.79%) and varied widely between studies (I² = 83.18%). The EGFR discordance rate was statistically significantly higher in bone metastases (45.49%, 95% CI = 14.13 to 79.02) than CNS (17.26%, 95% CI = 7.64 to 29.74; P = 0.002) and lung/ pleural metastases (8.17%, 95% CI = 3.35 to 14.85; P < 0.001). Subgroup analyses did not demonstrate any significant effect modification on the discordance rates by the EGFR mutation status in primary lung tumor, methods of testing and timing of metastasis.

Conclusion

The overall discordance rate in EGFR mutation between primary lung tumor and paired distant metastases in NSCLC is low, although higher discordance rates were observed in bone metastases compared with CNS and lung/pleural metastases. Future studies assessing the impact of EGFR mutation discordance on treatment outcomes are required.

Detection of Rare Mutations in EGFR-ARMS-PCR-Negative Lung Adenocarcinoma by Sanger Sequencing

PURPOSE

This study aimed to identify potential epidermal growth factor receptor (EGFR) gene mutations in non-small cell lung cancer that went undetected by amplification refractory mutation system-Scorpion real-time PCR (ARMS-PCR).

MATERIALS AND METHODS

A total of 200 specimens were obtained from the First Affiliated Hospital of Guangzhou Medical University from August 2014 to August 2015. In total, 100 ARMS-negative and 100 ARMS-positive specimens were evaluated for EGFR gene mutations by Sanger sequencing. The methodology and sensitivity of each method and the outcomes of EGFR-tyrosine kinase inhibitor (TKI) therapy were analyzed.

RESULTS

Among the 100 ARMS-PCR-positive samples, 90 were positive by Sanger sequencing, while 10 cases were considered negative, because the mutation abundance was less than 10%. Among the 100 negative cases, three were positive for a rare EGFR mutation by Sanger sequencing. In the curative effect analysis of EGFR-TKIs, the progression-free survival (PFS) analysis based on ARMS and Sanger sequencing results showed no difference. However, the PFS of patients with a high abundance of EGFR mutation was 12.4 months [95% confidence interval (CI), 11.6-12.4 months], which was significantly higher than that of patients with a low abundance of mutations detected by Sanger sequencing (95% CI, 10.7-11.3 months) (p<0.001).

CONCLUSION

The ARMS method demonstrated higher sensitivity than Sanger sequencing, but was prone to missing mutations due to primer design. Sanger sequencing was able to detect rare EGFR mutations and deemed applicable for confirming EGFR status. A clinical trial evaluating the efficacy of EGFR-TKIs in patients with rare EGFR mutations is needed.