Jünger ST, Hoyer UCI, Schaufler D, et al. - A retrospective study was conducted to investigate a deep learning model (DLM) for fully automated detection and 3D segmentation of brain metastases (BMs) in non-small cell lung cancer (NSCLC) on a clinical routine MRI. Researchers included a total of 98 NSCLC patients with 315 BMs on pretreatment MRI, divided them into training (66 patients, 248 BMs) and independent test (17 patients, 67 BMs) and control (15 patients, 0 BMs) cohorts. They performed sensitivity (recall) and false positive (FP) findings per scan, dice similarity coefficient (DSC) to correlate the spatial overlap between manual and automated segmentation, Pearson's correlation coefficient (r) to assess the association between quantitative volumetric measurements of segmentation, and the volumes of BMs were compared by using Wilcoxon rank-sum test. This study’s findings demonstrate that deep learning provided a high detection sensitivity and good segmentation performance for BMs in NSCLC on heterogeneous scanner data while yielding a low number of FP findings.