An Automated Brain Metastasis Detection and Segmentation System from MRI with a Large Multi Institutional Dataset

We achieved excellent detection sensitivity and segmentation accuracy for BMs > 0.1 cm, and promising performance for small BMs (<0.1cm) with a controlled FP rate using a large multi-institutional dataset. Clinical utility for assisting early detection and SRS planning will be investigated. Table 1: Per-lesion detection and segmentation performance stratified by individual BM size. N is the number of BMs in each category.