Pathological Evidence Exploration in Deep Retinal Image Diagnosis


  • Yuhao Niu Beihang University
  • Lin Gu National Institute of Informatics, Japan
  • Feng Lu Beihang University
  • Feifan Lv Beihang University
  • Zongji Wang Beihang University
  • Imari Sato National Institute of Informatics
  • Zijian Zhang Xiangya Hospital Central South University
  • Yangyan Xiao Xiangya Hospital Central South University
  • Xunzhang Dai Xiangya Hospital Central South University
  • Tingting Cheng Xiangya Hospital Central South University



Though deep learning has shown successful performance in classifying the label and severity stage of certain disease, most of them give few evidence on how to make prediction. Here, we propose to exploit the interpretability of deep learning application in medical diagnosis. Inspired by Koch’s Postulates, a well-known strategy in medical research to identify the property of pathogen, we define a pathological descriptor that can be extracted from the activated neurons of a diabetic retinopathy detector. To visualize the symptom and feature encoded in this descriptor, we propose a GAN based method to synthesize pathological retinal image given the descriptor and a binary vessel segmentation. Besides, with this descriptor, we can arbitrarily manipulate the position and quantity of lesions. As verified by a panel of 5 licensed ophthalmologists, our synthesized images carry the symptoms that are directly related to diabetic retinopathy diagnosis. The panel survey also shows that our generated images is both qualitatively and quantitatively superior to existing methods.




How to Cite

Niu, Y., Gu, L., Lu, F., Lv, F., Wang, Z., Sato, I., Zhang, Z., Xiao, Y., Dai, X., & Cheng, T. (2019). Pathological Evidence Exploration in Deep Retinal Image Diagnosis. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 1093-1101.



AAAI Technical Track: Applications