Fundus Image Quality-Guided Diabetic Retinopathy Grading

With the increasing use of fundus cameras, we can get a large number of retinal images. However there are quite a number of images in poor quality because of uneven illumination, occlusion and so on. The quality of images significantly affects the performance of automated diabetic retinopathy (DR) screening systems. Unlike the previous methods that did not face the unbalanced distribution, we propose weighted softmax with center loss to solve the unbalanced data distribution in medical images. Furthermore, we propose Fundus Image Quality (FIQ)-guided DR grading method based on multi-task deep learning, which is the first work using fundus image quality to help grade DR. Experimental results on the Kaggle dataset show that fundus image quality greatly impact DR grading. By considering the influence of quality, the experimental results validate the effectiveness of our propose method. All codes and fundus image quality label on Kaggle DR dataset are released in https://github.com/ClancyZhou/kaggle_DR_image_quality_miccai2018_workshop.

[1]  Yu Qiao,et al.  A Discriminative Feature Learning Approach for Deep Face Recognition , 2016, ECCV.

[2]  Cheng Wan,et al.  Image quality classification for DR screening using deep learning , 2017, 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[3]  Yiming Wang,et al.  Automatic retinal image quality assessment and enhancement , 1999, Medical Imaging.

[4]  Cheng Wan,et al.  Retinal Image Quality Classification Using Fine-Tuned CNN , 2017, FIFI/OMIA@MICCAI.

[5]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[6]  Xiaochun Cao,et al.  Disc-Aware Ensemble Network for Glaucoma Screening From Fundus Image , 2018, IEEE Transactions on Medical Imaging.

[7]  Xiaochun Cao,et al.  Joint Optic Disc and Cup Segmentation Based on Multi-Label Deep Network and Polar Transformation , 2018, IEEE Transactions on Medical Imaging.