Abdominal multi-organ segmentation with cascaded convolutional and adversarial deep networks
作者：
Highlights：
• Abdominal multi-organ segmentation with deep learning is successfully investigated.
• Standard adversarial networks are extended with cascaded pre-trained encoder-decoders.
• Cascaded convolutional and adversarial networks strengthens generalization abilities.
• our pipeline outperforms existing methods for liver, kidneys and spleen segmentation.
• Our contributions gave us the first rank for three CHAOS competition categories.
摘要
•Abdominal multi-organ segmentation with deep learning is successfully investigated.•Standard adversarial networks are extended with cascaded pre-trained encoder-decoders.•Cascaded convolutional and adversarial networks strengthens generalization abilities.•our pipeline outperforms existing methods for liver, kidneys and spleen segmentation.•Our contributions gave us the first rank for three CHAOS competition categories.
论文关键词：Multi-organ segmentation,Convolutional encoder-decoders,Adversarial learning,Cascaded networks,Abdominal images
论文评审过程：Received 16 June 2020, Revised 24 January 2021, Accepted 6 May 2021, Available online 14 May 2021, Version of Record 26 May 2021.
论文官网地址：https://doi.org/10.1016/j.artmed.2021.102109
