Radiotherapy in brain metastases from EGFR-mutated non-small cell lung cancer

Optimal sequence of LT for symptomatic BM in EGFR-mutant NSCLC: a comparative study of first-line EGFR-TKIs with/without upfront LT

BACKGROUND

The third-generation epidermal growth factor receptor tyrosine kinase inhibitors (EGFR-TKIs) can penetrate blood-brain barrier and are effective for brain metastases (BMs). There is no consensus on the optimal sequence of local therapy (LT) and EGFR-TKIs for symptomatic BM patients because patients suffering neurological symptoms were not enrolled in most clinical trials.

METHODS

Non-small cell lung cancer (NSCLC) patients with EGFR mutation (EGFRm) and symptomatic BM receiving first-line osimertinib and aumolertinib from two medical centers were collected. All participants were allocated into the third-generation EGFR-TKIs (TKIs) group and the upfront LT (uLT) plus third-generation EGFR-TKIs (TKIs + uLT) group. Demographic data, survival outcomes, treatment failure patterns, and adverse events were evaluated between the two groups. We also conducted subgroup analyses to explore the impact of BM number on survival outcomes.

RESULTS

86 patients were enrolled, 44 in the TKIs group and 42 in the TKIs + uLT group. There were no significant differences in the short-term response between the groups. TKIs + uLT was associated with significantly longer overall survival (OS) (43 vs. 28 months; hazard ratio [HR], 0.36, 95% confidence interval [CI], 0.17-0.77; p = .011). No differences in progression-free survival (PFS), intracranial PFS (iPFS), failure patterns, or safety were observed. In subgroup analyses of oligo-BM patients, TKIs + uLT could prolong OS (43 vs. 31 months; HR 0.22; 95% CI 0.05-0.92; p = .015).

CONCLUSIONS

EGFRm NSCLC patients with symptomatic BM might benefit from uLT, particularly oligo-BM patients. However, larger prospective cohort studies should be carried out to confirm the responses of the TKIs + uLT scheme.

A multi-task deep learning model for EGFR genotyping prediction and GTV segmentation of brain metastasis

BACKGROUND

The precise prediction of epidermal growth factor receptor (EGFR) mutation status and gross tumor volume (GTV) segmentation are crucial goals in computer-aided lung adenocarcinoma brain metastasis diagnosis. However, these two tasks present continuous difficulties due to the nonuniform intensity distributions, ambiguous boundaries, and variable shapes of brain metastasis (BM) in MR images.The existing approaches for tackling these challenges mainly rely on single-task algorithms, which overlook the interdependence between these two tasks.

METHODS

To comprehensively address these challenges, we propose a multi-task deep learning model that simultaneously enables GTV segmentation and EGFR subtype classification. Specifically, a multi-scale self-attention encoder that consists of a convolutional self-attention module is designed to extract the shared spatial and global information for a GTV segmentation decoder and an EGFR genotype classifier. Then, a hybrid CNN-Transformer classifier consisting of a convolutional block and a Transformer block is designed to combine the global and local information. Furthermore, the task correlation and heterogeneity issues are solved with a multi-task loss function, aiming to balance the above two tasks by incorporating segmentation and classification loss functions with learnable weights.

RESULTS

The experimental results demonstrate that our proposed model achieves excellent performance, surpassing that of single-task learning approaches. Our proposed model achieves a mean Dice score of 0.89 for GTV segmentation and an EGFR genotyping accuracy of 0.88 on an internal testing set, and attains an accuracy of 0.81 in the EGFR genotype prediction task and an average Dice score of 0.85 in the GTV segmentation task on the external testing set. This shows that our proposed method has outstanding performance and generalization.

CONCLUSION

With the introduction of an efficient feature extraction module, a hybrid CNN-Transformer classifier, and a multi-task loss function, the proposed multi-task deep learning network significantly enhances the performance achieved in both GTV segmentation and EGFR genotyping tasks. Thus, the model can serve as a noninvasive tool for facilitating clinical treatment.

Intracranial complete remissions in an aumolertinib-treated EGFR mutation-positive non-small cell lung cancer (NSCLC) patient with symptomatic brain metastases and Eastern Cooperative Oncology Group performance status (ECOG PS) up to 4: a case report

Background

Brain metastases happen in approximately 70% of epidermal growth factor receptor (EGFR)-mutant non-small cell lung cancer (NSCLC) patients. It negatively impacts the survival and quality of life, with the median survival time for untreated patients is just 2.9 months. Nevertheless, no extensive research data is available for symptomatic brain metastases because asymptomatic brain metastases patients are usually included in the clinical trials then.

Case Description

Here, we report a 74-year-old male lung cancer patient with symptomatic brain metastases and performance status (PS) score of ~4. The patient was presented to our clinic on July 19 2020 with dizziness for one day, convulsions in the right lower limb for 2 hours, nausea, and severe vomiting. Further tissue and imaging analysis revealed EGFR-mutant stage IV (cT2N3M1) NSCLC with multiple brain metastases and cerebral edema. Initially, he was treated with bevacizumab on July 24^th for one cycle, then with novel third-generation EGFR-tyrosine kinase inhibitor (TKI) aumolertinib at 110 mg daily from July 31^st until disease control. Systemic partial remission (PR) and complete intracranial remission had been achieved in the lung and intracranial lesions. Notably, the PS score has detected as a level 4 at the time of diagnosis. After 2 weeks of aumolertinib administration, the patient showed significant improvement, and the PS score returned to 0. Interestingly, the patient significantly recovered from brain metastases and living a healthy daily life; nevertheless, he is currently receiving aumolertinib monotherapy for NSCLC and being follow-up for clinical updates.

Conclusions

Our case presented a patient with EGFR-mutant NSCLC with symptomatic brain metastases. Aumolertinib proved to be a highly effective and well-tolerated treatment option for sustained disease control and comprehensive future studies are needed to confirm its efficacy in a larger population.

Answering the Big Clinical Questions in Brain Metastasis Management

Management of brain metastases is challenging, both because of the historically guarded prognosis and evolving, more efficacious treatment paradigms for metastatic cancer. This perspective addresses several of the important difficult questions that practitioners treating patients with brain tumors face in the clinic. Successfully answering these questions requires knowledge of the clinical evidence, thoughtful discussion of the patient’s goals of care and collaboration in a multi-disciplinary setting.