<h3>Purpose/Objective(s)</h3> Brain metastases (BM) are the most common intracranial tumors in adults. Benefiting from efficient local control, stereotactic ablative radiotherapy (SABR) is becoming popular in the treatment of BM. Detection and manual delineation of BM are labor-intense processes, and normal blood vessels, which demonstrate high signal intensity on contrast enhanced magnetic resonance imaging (CE-MRI), are occasionally mistaken for metastatic lesions. Recently, several efforts have been made to develop automatic detection and segmentation for BM using advanced deep learning (DL) algorithms. In this study, we investigated the efficacy and accuracy of a DL model for the detection and segmentation of BM using black-blood (BB) MRI. <h3>Materials/Methods</h3> The BB MRI data of 48 patients with 806 BMs were collected to train and validate the DL model. BMs was contoured by a radiation oncologist. Since MRI data have an inconsistent intensity scale across the patients, we applied piecewise linear histogram matching algorithm, also called the Nyul normalization. To deal with bias corruption in the patient, N4 bias field correction was applied. The modified U-Net was implemented to automatically detect and segment BMs. One of the main strengths of modified U-Net is preserving the edge that occurs during the down-sampling process. The evaluation was conducted in both detection and segmentation. The detection performance was measured with detection sensitivity and average false positives and the segmentation performance was measured with the dice score (DSC). <h3>Results</h3> Twelve patients with 132 BMs were randomly selected as the test-set for evaluating our trained model. In the test-set, 19.2% BMs had a volume of <0.02 cc, max volume of 16.642 cc, min volume of 0.009 cc, median volume of 0.071 cc, and mean volume of 1.158 cc. The detection sensitivity was 96.87% by finding 128 among 132 BMs and average false positives were 0.2. When the results were analyzed, we consider <0.02 cc volume as the small volume. As the results, 100% sensitivity for BMs with volumes ≥0.02 cc, and 84.6% sensitivity for BMs with volumes <0.02 cc volume. The DSC of modified U-Net was 86.27 (range, 77-91.2), which is a significant improvement over DSC of U-Net of 81 (range, 64.71-89.2). Due to the edge preservation characteristics of the modified U-Net, the contour is well segmented along the boundary in the image even for a BM of a very small volume. <h3>Conclusion</h3> In this study, our model can detect and segment BMs on BB MRI data with good detection and segmentation performance, suggesting its considerable benefit for SABR.