Semi-supervised learning and graph cuts for consensus based medical image segmentation

作者：

Highlights：

• Semisupervised learning (SSL) is used for predicting missing annotations.

• A self consistency score quantifies reliability of expert's annotations.

• Graph cuts obtain the consensus segmentation through a globally accurate solution.

摘要

Highlights•Semisupervised learning (SSL) is used for predicting missing annotations.•A self consistency score quantifies reliability of expert's annotations.•Graph cuts obtain the consensus segmentation through a globally accurate solution.

论文关键词：Multiple experts,Segmentation,Crohn's disease,Retina,Self-consistency,Semi supervised learning,Graph cuts

论文评审过程：Received 1 February 2016, Revised 2 September 2016, Accepted 21 September 2016, Available online 28 September 2016, Version of Record 27 November 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.09.030