Brain MRI imaging characteristics predict treatment response and outcome in patients with de novo brain metastasis of EGFR-mutated NSCLC

Diagnostic accuracy of MRI-based radiomic features for EGFR mutation status in non-small cell lung cancer patients with brain metastases: a meta-analysis

Objective

This meta-analysis aims to evaluate the diagnostic accuracy of magnetic resonance imaging (MRI) based radiomic features for predicting epidermal growth factor receptor (EGFR) mutation status in non-small cell lung cancer (NSCLC) patients with brain metastases.

Methods

We systematically searched PubMed, Embase, Cochrane Library, Web of Science, Scopus, Wanfang, and China National Knowledge Infrastructure (CNKI) for studies published up to April 30, 2024. We included those studies that utilized MRI-based radiomic features to detect EGFR mutations in NSCLC patients with brain metastases. Sensitivity, specificity, positive and negative likelihood ratios (PLR, NLR), and area under the curve (AUC) were calculated to evaluate the accuracy. Quality assessment was performed using the quality assessment of prognostic accuracy studies 2 (QUADAS-2) tool. Meta-analysis was conducted using random-effects models.

Results

A total of 13 studies involving 2,348 patients were included. The pooled sensitivity and specificity of MRI-based radiomic features for detecting EGFR mutations were 0.86 (95% CI: 0.74-0.93) and 0.83 (95% CI: 0.72-0.91), respectively. The PLR and NLR were calculated as 5.14 (3.09, 8.55) and 0.17 (0.10, 0.31), respectively. Substantial heterogeneity was observed, with I² values exceeding 50% for all parameters. The AUC for the receiver operating characteristic analysis was 0.91 (95% CI: 0.88-0.93). Subgroup analysis indicated that deep learning models and studies conducted in Asian showed higher diagnostic accuracy compared to their respective counterparts.

Conclusions

MRI-based radiomic features demonstrate a high potential for accurately detecting EGFR mutations in NSCLC patients with brain metastases, particularly when advanced deep learning techniques were employed. However, the variability in diagnostic performance across different studies underscores the need for standardized radiomic protocols to enhance reproducibility and clinical utility.

Systematic review registration

https://www.crd.york.ac.uk/prospero/, identifier CRD42024544131.

Enhancing intracranial efficacy prediction of osimertinib in non-small cell lung cancer: a novel approach through brain MRI radiomics

Introduction

Osimertinib, a third-generation EGFR-TKI, is known for its high efficacy against brain metastases (BM) in non-small cell lung cancer (NSCLC) due to its ability to penetrate the blood-brain barrier. This study aims to evaluate the use of brain MRI radiomics in predicting the intracranial efficacy to osimertinib in NSCLC patients with BM.

Materials and methods

This study analyzed 115 brain metastases from NSCLC patients with the EGFR-T790M mutation treated with second-line osimertinib. The primary endpoint was intracranial response, and the secondary endpoint was intracranial progression-free survival (iPFS). We performed tumor delineation, image preprocessing, and radiomics feature extraction. Using a 5-fold cross-validation strategy, we built radiomic models with eight feature selectors and eight machine learning classifiers. The models' performance was evaluated by the area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis.

Results

The dataset of 115 brain metastases was divided into training and validation sets in a 7:3 ratio. The radiomic model utilizing the mRMR feature selector and stepwise logistic regression classifier showed the highest predictive accuracy, with AUCs of 0.879 for the training cohort and 0.786 for the validation cohort. This model outperformed a clinical-MRI morphological model, which included age, ring enhancement, and peritumoral edema (AUC: 0.794 for the training cohort and 0.697 for the validation cohort). The radiomic model also showed strong performance in calibration and decision curve analyses. Using a radiomic-score threshold of 199, patients were classified into two groups with significantly different median iPFS (3.0 months vs. 15.4 months, p < 0.001).

Conclusion

This study demonstrates that MRI radiomics can effectively predict the intracranial efficacy of osimertinib in NSCLC patients with brain metastases. This approach holds promise for assisting clinicians in personalizing treatment strategies.

MRI radiomics predicts the efficacy of EGFR-TKI in EGFR-mutant non-small-cell lung cancer with brain metastasis

AIM

To develop and validate models based on magnetic resonance imaging (MRI) radiomics for predicting the efficacy of epidermal growth factor receptor tyrosine kinase inhibitor (EGFR-TKI) in EGFR-mutant non-small-cell lung cancer (NSCLC) patients with brain metastases.

MATERIALS AND METHODS

117 EGFR-mutant NSCLC patients with brain metastases who received EGFR-TKI treatment were included in this study from January 1, 2014 to December 31, 2021. Patients were randomly divided into training and validation cohorts in a ratio of 2:1. Radiomics features extracted from brain MRI were screened by least absolute shrinkage and selection operator (LASSO) algorithm. Logistic regression analysis and Cox proportional hazard regression analysis were used to screen clinical risk factors. Clinical (C), radiomics (R), and combined (C + R) nomograms were constructed in models predicting short-term efficacy and intracranial progression-free survival (iPFS), respectively. Calibration curves, Harrell's concordance index (C-index), and decision curve analysis (DCA) were used to evaluate the performance of models.

RESULTS

Overall response rate (ORR) was 57.3% and median iPFS was 12.67 months. The C + R nomograms were more effective. In the short-term efficacy model, the C-indexes of C + R nomograms in training cohort and validation cohort were 0.860 (0.820-0.901, 95%CI) and 0.843 (0.783-0.904, 95%CI). In iPFS model, the C-indexes of C + R nomograms in training cohort and validation cohort were 0.837 (0.751-0.923, 95%CI) and 0.850 (0.763-0.937, 95%CI).

CONCLUSION

The C + R nomograms were more effective in predicting EGFR-TKI efficacy of EGFR-mutant NSCLC patients with brain metastases than single clinical or radiomics nomograms.

Clinical Management of Patients with Non-Small Cell Lung Cancer, Brain Metastases, and Actionable Genomic Alterations: A Systematic Literature Review

INTRODUCTION

Nearly 60% of patients with non-small cell lung cancer (NSCLC) present with metastatic disease, and approximately 20% have brain metastases (BrMs) at diagnosis. During the disease course, 25-50% of patients will develop BrMs. Despite available treatments, survival rates for patients with NSCLC and BrMs remain low, and their overall prognosis is poor. Even with newer agents for NSCLC, options for treating BrMs can be limited by their ineffective transport across the blood-brain barrier (BBB) and the unique brain tumor microenvironment. The presence of actionable genomic alterations (AGAs) is a key determinant of optimal treatment selection, which aims to maximize responses and minimize toxicities. The objective of this systematic literature review (SLR) was to understand the current landscape of the clinical management of patients with NSCLC and BrMs, particularly those with AGAs.

METHOD

A Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA)-compliant SLR was conducted to identify studies in patients with BrMs in NSCLC. Searches used the EMBASE and MEDLINE® databases, and articles published between January 1, 2017 and September 26, 2022 were reviewed.

RESULTS

Overall, 179 studies were included in the SLR. This subset review focused on 80 studies that included patients with NSCLC, BrMs, and AGAs (19 randomized controlled trials [RCTs], two single-arm studies, and 59 observational studies). Sixty-four of the 80 studies reported on epidermal growth factor receptor (EGFR) mutations, 14 on anaplastic lymphoma kinase (ALK) alterations, and two on both alterations. Ninety-five percent of studies evaluated targeted therapy. All RCTs allowed patients with previously treated, asymptomatic, or neurologically stable BrMs; the percentage of asymptomatic BrMs varied across observational studies.

CONCLUSIONS

Although targeted therapies demonstrate systemic benefits for patients with NSCLC, BrMs, and AGAs, there remains a continued need for effective therapies to treat and prevent BrMs in this population. Increased BBB permeability of emerging therapies may improve outcomes for this population.

Rationale and value of consolidative cranial local therapy in EGFR-mutant non-small cell lung cancer patients with baseline brain metastasis treated with first-line EGFR-TKIs

Objectives

To explore the rationale and value of consolidative cranial local therapy (CLT) in epidermal growth factor receptor (EGFR)-mutant non-small cell lung cancer (NSCLC) patients with brain metastases (BMs).

Methods

EGFR-mutant NSCLC patients with baseline BMs who received first-line EGFR-tyrosine kinase inhibitors (TKIs) at two academic centers from May 2015 to June 2020 were retrospectively enrolled. Patterns of tumor response and treatment failure were extensively analyzed in order to explore the rationale of CLT. Cranial lesions with number ⩽3 and largest tumor size ⩽3 cm at baseline and best response to EGFR-TKIs were defined as oligo-BMs and oligo-residual cranial disease (ORCD), respectively. To provide preliminary data supporting CLT, survival outcomes were compared in patients with ORCD, stratified by CLT status.

Results

Of the 216 patients enrolled, 57.1% had oligo-BMs and 24.5% received first-line osimertinib. At best response to the first-line EGFR-TKIs, intracranial complete response, partial response, and stable disease occurred in 18.5, 31.9, and 44.4% of the whole population, respectively. For patients without CLT (n = 193), ORCD was observed in 78.1% of the 105 patients with baseline oligo-BMs and 10.2% of the 88 patients with baseline multiple-BMs. With a median follow-up of 22.8 months, 107 patients had cranial first progressive disease (PD); more than 60% developed their first PD solely from the residual tumor sites at best response to EGFR-TKIs. Moreover, among patients with ORCD (n = 108), patients who received CLT (n = 17) achieved significantly longer progression-free survival (13.4 versus 8.5 months, p = 0.001) and overall survival (58.9 versus 28.8 months, p = 0.021) than those without CLT. Meanwhile, CLT remained as an independent prognostic factor associated with improved survival after Cox regression analyses.

Conclusions

Cranial progressive disease developed mostly at the residual cranial lesions in EGFR-mutant NSCLC patients with baseline BMs who received first-line EGFR-TKIs. Consolidative cranial local therapy targeting the oligo-residual cranial tumor lesions may provide survival benefit, which warrants future validation.

The Efficacy and Safety of Afatinib in Non-Small Cell Lung Cancer Patients with Brain Metastasis: A Meta-Analysis

Aim

The aim of this study is to evaluate the efficacy and safety of afatinib in the treatment of non-small cell lung cancer (NSCLC) patients with brain metastasis based on meta-analysis.

Methods

Related literatures were searched in the following databases: EMbase, PubMed, China Knowledge Network (CNKI), Wanfang, Weipu, Google Scholar, the China Biomedical Literature Service System, and other databases. Clinical trials and observational studies that met the requirements were selected for meta-analysis using Revman 5.3. The hazard ratio (HR) was used as an indicator of the impact of afatinib.

Results

A total of 142 related literatures were acquired, but after screening, five literatures were selected for data extraction. The following indices were compared: the progression-free survival (PFS), overall survival (OS), and common adverse reactions (ARs) of grade 3 and above. A total of 448 patients with brain metastases were included and were divided into two groups: the control group (no afatinib treatment, with chemotherapy alone and the first-generation EGFR-TKIs) and the afatinib group. The results showed that afatinib could improve PFS (HR: 0.58, 95% CI: 0.39-0.85, P < 0.05) and ORR (OR = 2.86, 95% CI: 1.45-2.57, P < 0.05), but had no benefit on OS (HR: 1.13, 95% CI: 0.15-8.75, P > 0.05) and DCR (OR = 2.87, 95% CI: 0.97-8.48, P > 0.05). For the safety of afatinib, the incidence of grade-3-and-above ARs was low (HR: 0.01, 95% CI: 0.00-0.02, P < 0.05).

Conclusion

Afatinib improves the survival of NSCLC patients with brain metastases and shows satisfactory safety.

Case Report: Focal leptomeningeal disease, atypical cancer of unknown primary site

Background: Leptomeningeal metastasis is an infrequent form of cancer expression, and it has a poor prognosis due to its torpid evolution and its challenging diagnosis. Case report: We report the case of a 68-year-old woman with rapidly progressing cognitive decline and focal epilepsy. Brain magnetic resonance imaging showed extensive gyriform hypersignal in the right precentral sulcus region, without mass effect, tenuous contrast uptake, and hydrocephalus with transependymal edema. The body tomographic study was negative for solid cancer and the 18F-FDG PET-CT revealed a severe hypermetabolism in the right lung upper lobe. These findings were suggestive of lung cancer with leptomeningeal metastasis. We performed a brain biopsy, finding atypical cells in the leptomeningeal region with positive immunohistochemical staining for CK7 and negative for CK20 corresponding to lung adenocarcinoma. The patient was evaluated in the oncology service and scheduled for radiotherapy and chemotherapy. Conclusions: Focal leptomeningeal disease is an entity that should be considered as a differential diagnosis in all cases of focal leptomeningitis. Timely diagnosis and adequate cancer management can increase patient survival.

Perilesional edema in brain metastases as predictive factor of response to systemic therapy in non-small cell lung cancer patients: a preliminary study

BACKGROUND

The significance of upfront systemic therapies as an alternative to whole brain radiotherapy (WBRT) for multiple brain metastases (BM) is debatable. Our purpose is to investigate if peritumoral edema could predict the intracranial response to systemic chemotherapy (chemo) in patients with advanced non-squamous non-small cell lung cancer (non-SQ-NSCLC) and synchronous multiple BM.

METHODS

In this observational cohort study, we evaluated the outcome of 28 patients with multiple BM (≥3) treated with chemo based on cisplatin/carboplatin plus pemetrexed (chemo, group A, n=17) or WBRT plus subsequent chemo (group B, n=11). The intracranial response, assessed by the response assessment neuro-oncology (RANO) BM criteria, was correlated with the degree of BM-associated edema estimated by the maximum diameter ratio among fluid attenuated inversion recovery (FLAIR) and gadolinium-enhanced T1WI (T1Gd) per each BM at the baseline brain magnetic resonance imaging (MRI).

RESULTS

No differences were observed in baseline characteristics between both groups, except for the number of patients under steroid treatment that was clearly superior in group B (P=0.007). Median OS was similar between groups. Regarding FLAIR/T1Gd ratio (F/Gd), patients treated with chemo alone exhibited significantly higher values (P=0.001) in those who developed intracranial progression disease (PD) (2.80±0.32 mm), compared with those who achieved partial response (PR) (1.30±0.11 mm) or stable disease (SD) (1.35±0.09 mm). In patients treated with WBRT, F/Gd ratio was not predictive of response.

CONCLUSIONS

Peritumoral edema estimated by F/Gd ratio appears a promising predictive tool to identify oligosymptomatic patients with multiple BM in whom WBRT can be postponed.

Focal Leptomeningeal Disease with Perivascular Invasion in EGFR-Mutant Non-Small-Cell Lung Cancer

We report a previously undescribed pattern of brain metastases in patients with epidermal growth factor receptor-mutated non-small-cell lung cancer treated with tyrosine kinase inhibitors and radiation therapy. These highly distinct lesions appear to spread focally within the leptomeninges, with invasion along the perivascular spaces (FLIP). The survival of patients with FLIP was significantly better compared with patients with classic leptomeningeal disease (median survival, 21 versus 3 months; P = .003). It is unclear whether this pattern of growth is unique to epidermal growth factor receptor-mutated non-small-cell lung cancer.

Tyrosine Kinase Inhibitor Therapy for Brain Metastases in Non-Small-Cell Lung Cancer: A Primer for Radiologists

Treatment options for patients who develop brain metastases secondary to non-small-cell lung cancer have rapidly expanded in recent years. As a key adjunct to surgical and radiation therapy options, systemic therapies are now a critical component of the oncologic management of metastatic CNS disease in many patients with non-small-cell lung cancer. The aim of this review article was to provide a guide for radiologists, outlining the role of systemic therapies in metastatic non-small-cell lung cancer, with a focus on tyrosine kinase inhibitors. The critical role of the blood-brain barrier in the development of systemic therapies will be described. The final sections of this review will provide an overview of current imaging-based guidelines for therapy response. The utility of the Response Assessment in Neuro-Oncology criteria will be discussed, with a focus on how to use the response criteria in the assessment of patients treated with systemic and traditional therapies.