Checklist for responsible deep learning modeling of medical images based on COVID-19 detection studies

作者：

Highlights：

• Deeplearning models for medical image analysis offers high performance

• Responsible medical modelling requires that model predictions are explained

• Explanations needs to be aligned with medical domain knowledge.

• Proposed checklist protects against common errors in CT image predictive modelling.

• Lung CT data modeling needs different solutions than non-medical images.

摘要

•Deeplearning models for medical image analysis offers high performance•Responsible medical modelling requires that model predictions are explained•Explanations needs to be aligned with medical domain knowledge.•Proposed checklist protects against common errors in CT image predictive modelling.•Lung CT data modeling needs different solutions than non-medical images.

论文关键词：COVID-19,Lungs,Computed tomography,X-ray,Explainable AI,Deep learning

论文评审过程：Received 10 January 2021, Revised 23 April 2021, Accepted 11 May 2021, Available online 21 May 2021, Version of Record 2 June 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108035