Deep learning with attention supervision for automated motion artefact detection in quality control of cardiac T1-mapping

作者：

Highlights：

• A multi-stream CNN ResNet classifier customised for CMR T1-mapping motion artefact detection.

• An attention supervision module to guide the training of CNN classifier.

• A multiple human observer analysis of the scoring results to adjudicate human and machine performance.

摘要

•A multi-stream CNN ResNet classifier customised for CMR T1-mapping motion artefact detection.•An attention supervision module to guide the training of CNN classifier.•A multiple human observer analysis of the scoring results to adjudicate human and machine performance.

论文关键词：Cardiac Magnetic Resonance,T1-mapping,Quality Control,Convolutional Neural Network,Attention Mapping,Attention Supervision

论文评审过程：Received 10 December 2019, Revised 3 August 2020, Accepted 3 September 2020, Available online 7 September 2020, Version of Record 7 November 2020.

论文官网地址：https://doi.org/10.1016/j.artmed.2020.101955