Weakly-Supervised Vessel Detection in Ultra-Widefield Fundus Photography Via Iterative Multi-Modal Registration and Learning

Li Ding, Ajay E. Kuriyan, Rajeev S. Ramchandran, Charles C. Wykoff, Gaurav Sharma

Research output: Contribution to journalArticle

1 Scopus citations

Abstract

We propose a deep-learning based annotation-efficient framework for vessel detection in ultra-widefield (UWF) fundus photography (FP) that does not require de novo labeled UWF FP vessel maps. Our approach utilizes concurrently captured UWF fluorescein angiography (FA) images, for which effective deep learning approaches have recently become available, and iterates between a multi-modal registration step and a weakly-supervised learning step. In the registration step, the UWF FA vessel maps detected with a pre-trained deep neural network (DNN) are registered with the UWF FP via parametric chamfer alignment. The warped vessel maps can be used as the tentative training data but inevitably contain incorrect (noisy) labels due to the differences between FA and FP modalities and the errors in the registration. In the learning step, a robust learning method is proposed to train DNNs with noisy labels. The detected FP vessel maps are used for the registration in the following iteration. The registration and the vessel detection benefit from each other and are progressively improved. Once trained, the UWF FP vessel detection DNN from the proposed approach allows FP vessel detection without requiring concurrently captured UWF FA images. We validate the proposed framework on a new UWF FP dataset, PRIME-FP20, and on existing narrow-field FP datasets. Experimental evaluation, using both pixel-wise metrics and the CAL metrics designed to provide better agreement with human assessment, shows that the proposed approach provides accurate vessel detection, without requiring manually labeled UWF FP training data.

Original languageEnglish (US)
JournalIEEE Transactions on Medical Imaging
DOIs
StateAccepted/In press - 2020

Keywords

  • Electronic mail
  • multi-modal registration
  • Noise measurement
  • noisy labels
  • Photography
  • Retinal vessel detection
  • Retinal vessels
  • Training
  • Training data
  • ultra-widefield fundus photography

ASJC Scopus subject areas

  • Software
  • Radiological and Ultrasound Technology
  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Weakly-Supervised Vessel Detection in Ultra-Widefield Fundus Photography Via Iterative Multi-Modal Registration and Learning'. Together they form a unique fingerprint.

Cite this