Reproduction study using public data of: Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs (2018-03-12T00:00:00.000000Z)

TL;DR

The challenges of reproducing deep learning method results are shown, and the need for more replication and reproduction studies to validate deep learning methods, especially for medical image analysis is shown.

Abstract

We have attempted to reproduce the results in Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs, published in JAMA 2016; 316(22), using publicly available data sets. We re-implemented the main method in the original study since the source code is not available. The original study used non-public fundus images from EyePACS and three hospitals in India for training. We used a different EyePACS data set from Kaggle. The original study used the benchmark data set Messidor-2 to evaluate the algorithm’s performance. We used another distribution of the Messidor-2 data set, since the original data set is no longer available. In the original study, ophthalmologists re-graded all images for diabetic retinopathy, macular edema, and image gradability. We have one diabetic retinopathy grade per image for our data sets, and we assessed image gradability ourselves. We were not able to reproduce the original study’s results with publicly available data. Our algorithm’s area under the receiver operating characteristic curve (AUC) of 0.951 (95% CI, 0.947-0.956) on the Kaggle EyePACS test set and 0.853 (95% CI, 0.835-0.871) on Messidor-2 did not come close to the reported AUC of 0.99 on both test sets in the original study. This may be caused by the use of a single grade per image, or different data. This study shows the challenges of reproducing deep learning method results, and the need for more replication and reproduction studies to validate deep learning methods, especially for medical image analysis. Our source code and instructions are available at: https://github.com/mikevoets/jama16-retina-replication.

References31 items

Diabetic Retinopathy Detection

Fundus photograph-based deep learning algorithms in detecting diabetic retinopathy

Missing data hinder replication of artificial intelligence studies

Development and Validation of a Deep Learning System for Diabetic Retinopathy and Related Eye Diseases Using Retinal Images From Multiethnic Populations With Diabetes

Diabetic Retinopathy detection through integration of Deep Learning classification framework

Grader variability and the importance of reference standards for evaluating machine learning models for diabetic retinopathy

Automated Identification of Diabetic Retinopathy Using Deep Learning.

Opportunities and obstacles for deep learning in biology and medicine

A survey on deep learning in medical image analysis

The challenges of replication

Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs.

Improved Automated Detection of Diabetic Retinopathy on a Publicly Available Dataset Through Integration of Deep Learning.

Rethinking the Inception Architecture for Computer Vision

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

ImageNet Large Scale Visual Recognition Challenge

FEEDBACK ON A PUBLICLY DISTRIBUTED IMAGE DATABASE: THE MESSIDOR DATABASE

Announcement: Reducing our irreproducibility

Large Scale Distributed Deep Networks

ImageNet classification with deep convolutional neural networks

Optimal Wavelet Transform for the Detection of Microaneurysms in Retina Photographs

Proposed international clinical diabetic retinopathy and diabetic macular edema disease severity scales.

Overfitting and neural networks: conjugate gradient and backpropagation

Reality check on reproducibility

Large-Scale Machine Learning with Stochastic Gradient Descent

Koutroumbas, Pattern Recognition

1 Image Processing

Methods to evaluate segmentation and indexing techniques in the field of retinal ophthalmology

Overfitting in Neural Nets: Backpropagation, Conjugate Gradient, and Early Stopping

Bulletin of mathematical biology

Abramoff Messidor-2 reference standard rDR 20

Press Announcements-FDA permits marketing of artificial intelligence-based device to detect certain diabetes-related eye problems Available from