A data-driven approach to referable diabetic retinopathy detection

作者：

Highlights：

• Our model yields relevant results for referable DR even with different datasets.

• It has a good trade-off between efficiency and effectiveness for mobile deployment.

• We boost the performance of the initial baseline model by a set of directives.

• Time and memory footprint is improved by 5x compared to prior art.

• For DR2, we clearly outperform recent works with error reductions by 44%, 65% and 70%.

摘要

•Our model yields relevant results for referable DR even with different datasets.•It has a good trade-off between efficiency and effectiveness for mobile deployment.•We boost the performance of the initial baseline model by a set of directives.•Time and memory footprint is improved by 5x compared to prior art.•For DR2, we clearly outperform recent works with error reductions by 44%, 65% and 70%.

论文关键词：Diabetic retinopathy,Referral,Screening,Multi-resolution training,Robust feature-extraction augmentation,Integrated patient-basis analysis

论文评审过程：Received 17 October 2018, Revised 23 March 2019, Accepted 26 March 2019, Available online 27 March 2019, Version of Record 6 April 2019.

论文官网地址：https://doi.org/10.1016/j.artmed.2019.03.009