PFEMed: Few-shot medical image classification using prior guided feature enhancement

作者：

Highlights：

• A novel dual-encoder architecture is introduced to extract feature representation.

• To our knowledge, we are the first to investigate the proposed VAE model.

• We present a novel method to initialize the priors estimated in the VAE module.

• Proposed approach will help medical industry utilize knowledge from public datasets.

摘要

•A novel dual-encoder architecture is introduced to extract feature representation.•To our knowledge, we are the first to investigate the proposed VAE model.•We present a novel method to initialize the priors estimated in the VAE module.•Proposed approach will help medical industry utilize knowledge from public datasets.

论文关键词：Deep learning,Domain adaption,Few-shot learning,Medical image classification,Variational autoencoder

论文评审过程：Received 22 December 2021, Revised 23 July 2022, Accepted 9 October 2022, Available online 13 October 2022, Version of Record 18 October 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.109108