Skip to content

Code for TMI 2018 "Joint Optic Disc and Cup Segmentation Based on Multi-label Deep Network and Polar Transformation"

Notifications You must be signed in to change notification settings

SamuelMarks/MNet_DeepCDR

 
 

Repository files navigation

MNet_CDR_Seg

Code for TMI 2018 "Joint Optic Disc and Cup Segmentation Based on Multi-label Deep Network and Polar Transformation"

Project homepage:https://hzfu.github.io/proj_glaucoma_fundus.html

  1. The code is based on: TensorFlow 1.14 (with Keras) + Matlab
  2. The deep output is raw segmentation result without ellipse fitting. The Matlab code is the ellipse fitting and CDR calculation (by using PDollar toolbox: https://pdollar.github.io/toolbox/).
  3. You can run the 'Step_3_MNet_test.py' for testing any new image directly.
  4. We also provided the validation and test results on REFUGE dataset in 'REFUGE_result' fold.

Main files:

  1. 'Step_1_Disc_Crop.py': The disc detection code for whole funuds image.
  2. 'Step_2_MNet_train.py': The M-Net training code.
  3. 'Step_3_MNet_test.py': The M-Net testing code.
  4. 'Step_4_CDR_output.m': The ellipse fitting for disc and cup, and CDR calculation.

If you use this code, please cite the following papers:

[1] Huazhu Fu, Jun Cheng, Yanwu Xu, Damon Wing Kee Wong, Jiang Liu, and Xiaochun Cao, "Joint Optic Disc and Cup Segmentation Based on Multi-label Deep Network and Polar Transformation", IEEE Transactions on Medical Imaging (TMI), vol. 37, no. 7, pp. 1597–1605, 2018. (ArXiv version)

[2] Huazhu Fu, Jun Cheng, Yanwu Xu, Changqing Zhang, Damon Wing Kee Wong, Jiang Liu, and Xiaochun Cao, "Disc-aware Ensemble Network for Glaucoma Screening from Fundus Image", IEEE Transactions on Medical Imaging (TMI), vol. 37, no. 11, pp. 2493–2501, 2018. (ArXiv version)


Note: for ORIGA and SCES datasets

Unfortunately, the ORIGA and SCES datasets cannot be released due to the clinical policy. But, here is an other glaucoma challenge, Retinal Fundus Glaucoma Challenge (REFUGE), including disc/cup segmentation, glaucoma screening, and localization of Fovea.


Update log:

  • 19.01.22: Added training code, and uploaded the results on REFUGE dataset.
  • 18.06.30: Added ellipse fitting code (based on Matlab), and Fixed the bug for macular center fundus.
  • 18.06.29: Added disc detection code (based on U-Net).
  • 18.02.26: Added CDR calculation code (based on Matlab).
  • 18.02.24: Released the code.

Install

pip install -r requirements.txt

OpenCV will need to be installed separately.

About

Code for TMI 2018 "Joint Optic Disc and Cup Segmentation Based on Multi-label Deep Network and Polar Transformation"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • MATLAB 33.0%
  • HTML 33.0%
  • Jupyter Notebook 26.5%
  • C++ 4.9%
  • C 1.6%
  • Python 1.0%