Automated Detection of Diabetic Retinopathy From Smartphone Fundus Videos

Simon Mueller, Snezhana Karpova, Maximilian Wintergerst, Kaushik Murali, Mahesh Shanmugam, Robert Finger, and Thomas Schultz
In proceedings of MICCAI Workshop on Ophthalmic Medical Image Analysis, 2020
 

Abstract

Even though it is important to screen patients with diabetes for signs of diabetic retinopathy (DR), doing so comprehensively remains a practical challenge in low- and middle-income countries due to limited resources and financial constraints. Supervised machine learning has shown a strong potential for automated DR detection, but has so far relied on photographs that show all relevant parts of the fundus, which require relatively costly imaging systems. We present the first approach that automatically detects DR from fundus videos that show different parts of the fundus at different times, and that can be acquired with a low-cost smartphone-based fundus imaging system. Our novel image analysis pipeline consists of three main steps: Detecting the lens with a circle Hough Transform, detecting informative frames using a Support Vector Machine, and detecting the disease itself with an attention-based multiple instance learning (MIL) CNN architecture. Our results support the feasibility of a smartphone video based approach.

Images

Download Paper

Download Paper

Bibtex

@INPROCEEDINGS{Mueller:OMIA2020,
     author = {Mueller, Simon and Karpova, Snezhana and Wintergerst, Maximilian and Murali, Kaushik and Shanmugam,
               Mahesh and Finger, Robert and Schultz, Thomas},
      title = {Automated Detection of Diabetic Retinopathy From Smartphone Fundus Videos},
  booktitle = {MICCAI Workshop on Ophthalmic Medical Image Analysis},
       year = {2020},
   abstract = {Even though it is important to screen patients with diabetes for signs of diabetic retinopathy (DR),
               doing so comprehensively remains a practical challenge in low- and middle-income countries due to
               limited resources and financial constraints. Supervised machine learning has shown a strong
               potential for automated DR detection, but has so far relied on photographs that show all relevant
               parts of the fundus, which require relatively costly imaging systems. We present the first approach
               that automatically detects DR from fundus videos that show different parts of the fundus at
               different times, and that can be acquired with a low-cost smartphone-based fundus imaging system.
               Our novel image analysis pipeline consists of three main steps: Detecting the lens with a circle
               Hough Transform, detecting informative frames using a Support Vector Machine, and detecting the
               disease itself with an attention-based multiple instance learning (MIL) CNN architecture. Our
               results support the feasibility of a smartphone video based approach.}
}