论文标题
针对医学成像的特定领域，半监督的转移学习
Domain Specific, Semi-Supervised Transfer Learning for Medical Imaging
论文作者
论文摘要
带注释的医学成像数据的有限可用性对深度学习算法构成了挑战。尽管转移学习通常可以最大程度地减少这一障碍，但跨不同领域的知识转移被证明效果较差。另一方面，发现较小的架构在学习更好的功能方面更具吸引力。因此，我们提出了一种轻巧的体系结构，该体系结构使用混合的不对称内核（MAKNET）大大减少参数的数量。此外，我们使用半监督的学习训练拟议的体系结构，为大型医疗数据集提供伪标记，以协助转移学习。拟议的Maknet提供的分类性能更好，$ 60-70 \％$ $ $ $比流行的架构少。实验结果还强调了特定于域知识对有效传输学习的重要性。
Limited availability of annotated medical imaging data poses a challenge for deep learning algorithms. Although transfer learning minimizes this hurdle in general, knowledge transfer across disparate domains is shown to be less effective. On the other hand, smaller architectures were found to be more compelling in learning better features. Consequently, we propose a lightweight architecture that uses mixed asymmetric kernels (MAKNet) to reduce the number of parameters significantly. Additionally, we train the proposed architecture using semi-supervised learning to provide pseudo-labels for a large medical dataset to assist with transfer learning. The proposed MAKNet provides better classification performance with $60 - 70\%$ less parameters than popular architectures. Experimental results also highlight the importance of domain-specific knowledge for effective transfer learning.
