Published September 6, 2019 | Version v2
Dataset Open

A Self-Adaptive Deep Learning Method for Automated Eye Laterality Detection Based on Color Fundus Photography

  • 1. School of Computer Science, University of Technology, Sydney, Australia
  • 2. State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China
  • 3. Faculty of Medicine, Nursing and Health Sciences, Monash University, Clayton, Australia
  • 4. Guangzhou Healgoo Interactive Medical Technology Co. Ltd., Guangzhou, China

Description

The data for "A Self-Adaptive Deep Learning Method for Automated Eye Laterality Detection Based on Color Fundus Photography", including original image data and labels, DL model files, training logs and validation results.

Content:

- Ex1_Preprocessing # the first experiment: preprocessing methods comparison

    - history # validation results of different metrics of models 

    - log # training record of models. Read by TensorBoard

    - model # model file.  Read by Keras

- Ex2_Self-adaptive model # the second experiment: development of eye laterality detection model

    - data # serialized image data, including data and ground-truth label. Read by Python Pickle package.

        - Xy.h5 # training data

        - test_Xy.h5 # testing data

    - history # validation results of different metrics of models 

    - log # training record of models. Read by TensorBoard

    - model # model file. Read by Keras

        - with_adaptive # with self-adaptive strategy

        - without_adaptive # without self-adaptive strategy

For code review, please see: https://github.com/keepgallop/Eye-laterality-detection

For more information, please contact liuchi_email@foxmail.com

 

 

 

Files

Published_Data.zip

Files (5.4 GB)

Name Size Download all
md5:6647513378d68018768ee991200fb467
5.4 GB Preview Download

Additional details

Related works

Is documented by
10.1371/journal.pone.0222025 (DOI)