Neural collaborative filtering for unsupervised mitral valve segmentation in echocardiography

作者：

Highlights：

• Unsupervised segmentation can perform adequately on echocardiography exploiting the low dimensional structure of the video.

• Non-linear models, i.e. neural collaborative filtering, outperform their linear counterparts by exploiting the high adaptivity of the model.

• Our method outperforms supervised methods on low-quality videos and defines a new state-of-the-art method for unsupervised mitral valve segmentation.

摘要

•Unsupervised segmentation can perform adequately on echocardiography exploiting the low dimensional structure of the video.•Non-linear models, i.e. neural collaborative filtering, outperform their linear counterparts by exploiting the high adaptivity of the model.•Our method outperforms supervised methods on low-quality videos and defines a new state-of-the-art method for unsupervised mitral valve segmentation.

论文关键词：Mitral valve,Segmentation,Collaborative filtering,Neural network

论文评审过程：Received 27 December 2019, Revised 13 August 2020, Accepted 18 October 2020, Available online 21 October 2020, Version of Record 10 November 2020.

论文官网地址：https://doi.org/10.1016/j.artmed.2020.101975