Szu-Yeu, HuHuSzu-YeuWeng, Wei-HungWei-HungWengLu, Shao-LunShao-LunLuCheng, Yueh-HungYueh-HungChengFU-REN XIAOHsu, Feng-MingFeng-MingHsuLu, Jen-TangJen-TangLu2023-03-212023-03-212019-08-1523318422https://scholars.lib.ntu.edu.tw/handle/123456789/629517Stereotactic radiosurgery (SRS), which delivers high doses of irradiation in a single or few shots to small targets, has been a standard of care for brain metastases. While very effective, SRS currently requires manually intensive delineation of tumors. In this work, we present a deep learning approach for automated detection and segmentation of brain metastases using multimodal imaging and ensemble neural networks. In order to address small and multiple brain metastases, we further propose a volume-aware Dice loss which optimizes model performance using the information of lesion size. This work surpasses current benchmark levels and demonstrates a reliable AI-assisted system for SRS treatment planning for multiple brain metastases. Copyright © 2019, The Authors. All rights reserved.enBrain MetastasesDeep learningRadiosurgeryother2-s2.0-85093395848http://www.scopus.com/inward/record.url?eid=2-s2.0-85093395848&partnerID=MN8TOARS