1 code implementation • 9 Dec 2021 • Joeran S. Bosma, Anindo Saha, Matin Hosseinzadeh, Ilse Slootweg, Maarten de Rooij, Henkjan Huisman
Semi-supervised training was 14$\times$ more annotation-efficient for case-based performance and 6$\times$ more annotation-efficient for lesion-based performance.