The researchers are doing this study is to find out whether treating brain metastasis with SRS after 3 months of therapy with osimertinib is better than treating with osimertinib alone in people with NSCLC. The researchers will also look at how the study intervention impacts participants' quality of life. The researchers will measure quality of life by having participants complete questionnaires.

Patients in both arms of this study will receive standard of care (SOC) systemic therapy which includes a backbone of an FDA-approved CNS-active TKI targeting mutant EGFR, specifically osimertinib.

Participant Inclusion Criteria: Screening

• Age ≥ 18 years
• Non-small cell lung cancer (NSCLC) with somatic activating mutation in EGFR diagnosis, confirmed at enrolling institution
• At least one intact brain metastasis at baseline prior to TKI therapy initiation, visible on MRI brain with contrast (but without a minimum diameter requirement)
• Either TKI-naïve or started TKI ≤ 3-months prior (with documented start date and available imaging prior to TKI start)

Participant Exclusion Criteria: Screening

• Unable to undergo contrast-enhanced MRI brain
• Prior brain-directed radiotherapy
• Evidence of leptomeningeal disease on MRI total spine and/or lumbar puncture cytology. The latter are not mandated by protocol but are rather at the discretion of the treating medical team as clinically indicated.
• Neurologic symptoms or presence of a lesion in the brainstem, motor strip, or other eloquent brain area that is felt to warrant immediate intervention with SRS
• Active hematologic malignancy or a second solid tumor histology with known CNS tropism
• Patients who have undergone a therapeutic craniotomy for resection of one or more symptomatic brain metastasis are ineligible unless one or more additional intact BM remain unresected, and meets size criteria (e.g., a patient with removal of a 3cm symptomatic brain metastasis, but has an additional visible lesion remaining post-operatively, remains eligible for the study).
• Judgment by the investigator that the patient should not participate in the study if the patient is unlikely to comply with study procedures, restrictions and requirements.
• Pregnant women or women who are breastfeeding or of childbearing potential. If the risk of contraception exists, male and female subjects must use highly effective contraception throughout the study and for at least 3 months after last treatment. Highly effective contraception includes either 2 barrier methods (diaphragm, condom by the partner, copper intrauterine device, sponge, or spermicide), or 1 barrier method and 1 hormonal method (any oral, subcutaneous, intrauterine, or intramuscular registered and marketed contraceptive agent that contains an estrogen and/or a progesterone agent)

Participant Inclusion Criteria: Randomization

- Presence of detectable and non-progressing BM lesions on imaging consistent with viable residual disease

Participant Exclusion Criteria: Randomization

• Progressive Disease (PD) with multiple lesions and/or other features that would warrant a change in systemic therapy, as determined by the primary treating provider
• Presence of BM not deemed safely treatable with SRS, as determined by a radiation oncologist
• Intracranial Complete Response (CR)
• More than 20 visible residual brain metastases at the time of enrollment (i.e. after initial treatment with TKI). However, no upper limit on the number of visible brain metastases is set at the time of initial diagnosis prior to treatment with TKI. For example, a patient who had 35 visible brain metastases at the time of diagnosis, but after three months of treatment with TKI had 10 visible brain metastases remaining will be eligible for enrollment and randomization

Memorial Sloan Kettering Cancer Center supports the international committee of medical journal editors (ICMJE) and the ethical obligation of responsible sharing of data from clinical trials. The protocol summary, a statistical summary, and informed consent form will be made available on clinicaltrials.gov when required as a condition of Federal awards, other agreements supporting the research and/or as otherwise required. Requests for deidentified individual participant data can be made beginning 12 months after publication and for up to 36 months post publication. Deidentified individual participant data reported in the manuscript will be shared under the terms of a Data Use Agreement and may only be used for approved proposals. Requests may be made to: crdatashare@mskcc.org.