Journal article
A data-driven approach to referable diabetic retinopathy detection
Artificial intelligence in medicine, Vol.96, pp.93-106
05/2019
DOI: 10.1016/j.artmed.2019.03.009
PMID: 31164214
Abstract
•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%.
Prior art on automated screening of diabetic retinopathy and direct referral decision shows promising performance; yet most methods build upon complex hand-crafted features whose performance often fails to generalize.
We investigate data-driven approaches that extract powerful abstract representations directly from retinal images to provide a reliable referable diabetic retinopathy detector.
We gradually build the solution based on convolutional neural networks, adding data augmentation, multi-resolution training, robust feature-extraction augmentation, and a patient-basis analysis, testing the effectiveness of each improvement.
The proposed method achieved an area under the ROC curve of 98.2% (95% CI: 97.4–98.9%) under a strict cross-dataset protocol designed to test the ability to generalize — training on the Kaggle competition dataset and testing using the Messidor-2 dataset. With a 5 × 2-fold cross-validation protocol, similar results are achieved for Messidor-2 and DR2 datasets, reducing the classification error by over 44% when compared to most published studies in existing literature.
Additional boost strategies can improve performance substantially, but it is important to evaluate whether the additional (computation- and implementation-) complexity of each improvement is worth its benefits. We also corroborate that novel families of data-driven methods are the state of the art for diabetic retinopathy screening. Significance: By learning powerful discriminative patterns directly from available training retinal images, it is possible to perform referral diagnostics without detecting individual lesions.
Details
- Title: Subtitle
- A data-driven approach to referable diabetic retinopathy detection
- Creators
- Ramon Pires - Institute of Computing, University of Campinas (Unicamp), Campinas 13083-852, BrazilSandra Avila - Institute of Computing, University of Campinas (Unicamp), Campinas 13083-852, BrazilJacques Wainer - Institute of Computing, University of Campinas (Unicamp), Campinas 13083-852, BrazilEduardo Valle - School of Electrical and Computing Engineering, University of Campinas (Unicamp), Campinas 13083-852, BrazilMichael D Abramoff - Stephen R. Wynn Institute for Vision Research, the Department of Electrical and Computer Engineering, the Department of Biomedical Engineering, the University of Iowa, Iowa City, IA 52242, USAAnderson Rocha - Institute of Computing, University of Campinas (Unicamp), Campinas 13083-852, Brazil
- Resource Type
- Journal article
- Publication Details
- Artificial intelligence in medicine, Vol.96, pp.93-106
- Publisher
- Elsevier B.V
- DOI
- 10.1016/j.artmed.2019.03.009
- PMID
- 31164214
- ISSN
- 0933-3657
- eISSN
- 1873-2860
- Grant note
- name: Microsoft Research, São Paulo Research Foundation, award: 2017/12646-3; DOI: 10.13039/501100005993, name: National Council for Scientific Research, award: 311486/2014-2, 304472/2015-8
- Language
- English
- Date published
- 05/2019
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Electrical and Computer Engineering; Fraternal Order of Eagles Diabetes Research Center; Ophthalmology and Visual Sciences
- Record Identifier
- 9984060634802771
Metrics
41 Record Views