# Pathological Evidence Exploration in Deep Retinal Image Diagnosis

arXiv: https://arxiv.org/abs/1812.02640 · HTML: https://mlsanity.com/paper/1812.02640/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Dec 2018.

## Built on by (most cited first, 6 of 6)

- [Applications of Deep Learning in Fundus Images: A Review](https://mlsanity.com/paper/2101.09864/) (2021)
- [Unsupervised Two-Stage Anomaly Detection](https://mlsanity.com/paper/2103.11671/) (2021)
- [Explainable Diabetic Retinopathy Detection and Retinal Image Generation](https://mlsanity.com/paper/2107.00296/) (2021)
- [k-SALSA: k-anonymous synthetic averaging of retinal images via local style alignment](https://mlsanity.com/paper/2303.10824/) (2023)
- [PatchBackdoor: Backdoor Attack against Deep Neural Networks without Model Modification](https://mlsanity.com/paper/2308.11822/) (2023)
- [Controllable retinal image synthesis using conditional StyleGAN and latent space manipulation for improved diagnosis and grading of diabetic retinopathy](https://mlsanity.com/paper/2409.07422/) (2024)

## Abstract (arXiv)

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.