摘要：Artificial intelligence (AI) shows great promise in many domains, and diagnostic imaging is an area wherethe potential is particularly articulated. The main bottleneck for achieving high-quality AI results is accessto massive amounts of representative training data. Sharing of painstakingly gathered data collections is,therefore, an essential part of making substantial advances in the field 1 . Moreover, sharing is necessary for thepurpose of research reproducibility 2 .
