Li Hui-Qi

Supervised Segmentation of Un-annotated Retinal Fundus Images by Synthesis

Published date : 24 Jul 2018

We focus on the practical challenge of segmenting new retinal fundus images that are dissimilar to existing well-annotated datasets. It is addressed in this paper by a supervised learning pipeline, with its core being the construction of a synthetic fundus image dataset using the proposed R-sGAN technique. The resulting synthetic images are realistic-looking in terms of the query images, while maintaining the annotated vessel structures from the existing dataset. This helps to bridge the mismatch between the query images and the existing well-annotated dataset.

type
Journal Paper
journal
IEEE Transactions on Medical Imaging, 2018 Jul 24. doi: 10.1109/TMI.2018.2854886
Impact Factor
6.131

Synthesizing retinal and neuronal images with generative adversarial nets

Published date : 04 Jul 2018

This paper aims at synthesizing multiple realistic-looking retinal (or neuronal) images from an unseen tubular structured annotation that contains the binary vessel (or neuronal) morphology. The generated phantoms are expected to preserve the same tubular structure, and resemble the visual appearance of the training images. Inspired by the recent progresses in generative adversarial nets (GANs) as well as image style transfer, our approach enjoys several advantages.

type
Journal Paper
journal
Medical Image Analysis, 2018 Jul 4;49:14-26. doi: 10.1016/j.media.2018.07.001
Impact Factor
5.356

Segment 2D and 3D Filaments by Learning Sructured and Contextual Features

Published date : 31 Oct 2016

We focus on the challenging problem of filamentary structure segmentation in both 2D and 3D images, including retinal vessels and neurons, among others. Despite the increasing amount of efforts in learning based methods to tackle this

type
Journal Paper
journal
IEEE Transactions on Medical Imaging, Issue 99, 2016, doi: 10.1109/TMI.2016.2623357
Impact Factor
2.536

Tracing retinal vessel trees by transductive inference

Published date : 18 Jan 2014

Background:
Structural study of retinal blood vessels provides an early indication of diseases such as diabetic
retinopathy, glaucoma, and hypertensive retinopathy. These studies require accurate tracing of retinal vessel tree structure from fundus images in an automated manner. However, the existing work encounters great difficulties when dealing with the crossover issue commonly-seen in vessel networks.

Results:
In this paper, we consider a novel graph-based approach to address this tracing with crossover problem:

type
Journal Paper
journal
BMC Bioinformatics, 15(20):1-20, 2014
Impact Factor
2.67