Robust and Efficient Computation of Retinal Fractal Dimension Through Deep Approximation

Justin Engelmann, Ana Villaplana-Velasco, Amos Storkey, Miguel O. Bernabeu

Research output: Chapter in Book/Report/Conference proceedingConference contribution


A retinal trait, or phenotype, summarises a specific aspect of a retinal image in a single number. This can then be used for further analyses, e.g. with statistical methods. However, reducing an aspect of a complex image to a single, meaningful number is challenging. Thus, methods for calculating retinal traits tend to be complex, multi-step pipelines that can only be applied to high quality images. This means that researchers often have to discard substantial portions of the available data. We hypothesise that such pipelines can be approximated with a single, simpler step that can be made robust to common quality issues. We propose Deep Approximation of Retinal Traits (DART) where a deep neural network is used predict the output of an existing pipeline on high quality images from synthetically degraded versions of these images. We demonstrate DART on retinal Fractal Dimension (FD) - a measure of vascular complexity - calculated by VAMPIRE, using retinal images from UK Biobank that previous work identified as high quality. Our method shows very high agreement with FDVAMPIRE on unseen test images (Pearson r=0.9572r=0.9572). Even when those images are severely degraded, DART can still recover an FD estimate that shows good agreement with FDVAMPIRE obtained from the original images (Pearson r=0.8817r=0.8817). This suggests that our method could enable researchers to discard fewer images in the future. Our method can compute FD for over 1,000 img/s using a single GPU. We consider these to be very encouraging initial results and hope to develop this approach into a useful tool for retinal analysis. Code for running DART with the trained model is available on GitHub.
Original languageEnglish
Title of host publicationOphthalmic Medical Image Analysis: 9th International Workshop, OMIA 2022, Held in Conjunction with MICCAI 2022, Singapore, Singapore, September 22, 2022, Proceedings
EditorsBhavna Antony, Huazhu Fu, Cecilia S. Lee, Tom MacGillivray, Yanwu Xu, Yalin Zheng
Place of PublicationCham
PublisherSpringer International Publishing Switzerland
Number of pages10
ISBN (Electronic)978-3-031-16525-2
ISBN (Print)978-3-031-16524-5
Publication statusPublished - 15 Sep 2022
EventThe 9th MICCAI Workshop on Ophthalmic Medical Image Analysis, 2022 - , Singapore
Duration: 22 Sep 202222 Sep 2022
Conference number: 9

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Cham
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


WorkshopThe 9th MICCAI Workshop on Ophthalmic Medical Image Analysis, 2022
Abbreviated titleOMIA 2022
Internet address


  • Retinal fractal dimension
  • Deep approximation of retinal traits
  • Robust retinal image analysis


Dive into the research topics of 'Robust and Efficient Computation of Retinal Fractal Dimension Through Deep Approximation'. Together they form a unique fingerprint.

Cite this