Dec, 2020
自监督学习放射学图像像素级解剖嵌入
SAM: Self-supervised Learning of Pixel-wise Anatomical Embeddings in Radiological Images
Ke Yan, Jinzheng Cai, Dakai Jin, Shun Miao, Dazhou Guo...
TL;DRSelf-supervised Anatomical eMbedding (SAM) is introduced to extract semantic embeddings for imaging pixels with intrinsic structures, which can be used to locate body parts in other images by nearest neighbor searching, surpassing supervised methods trained on 50 labeled images with only one labeled template image and being effective in improving image registration and initializing CNN weights.