Multi-Discriminator Adversarial Convolutional Network for Nerve Fiber Segmentation in Confocal Corneal Microscopy Images
- 9 July 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 26 (2) , 648-659
Abstract
Quantitative measurements of corneal sub-basal nerves are biomarkers for many ocular surface disorders and are also important for early diagnosis and assessment of progression of neurodegenerative diseases. This paper aims to develop an automatic method for nerve fiber segmentation from in vivo corneal confocal microscopy (CCM) images, which is fundamental for nerve morphology quantification. A novel multi-discriminator adversarial convolutional network (MDACN) is proposed, where both the generator and the two discriminators emphasize multi-scale feature representations. The generator is a U-shaped fully convolutional network with multi-scale split and concatenate blocks, and the two discriminators have different effective receptive fields, sensitive to features of different scales. A novel loss function is also proposed which enables the network to pay more attention to thin fibers. The MDACN framework was evaluated on four datasets. Experiment results show that our method has excellent segmentation performance for corneal nerve fibers and outperforms some state-of-the-art methods.Keywords
Funding Information
- National Key R&D Program of China (2018YFA0701700)
- National Natural Science Foundation of China (61971298, 61771326)
This publication has 40 references indexed in Scilit:
- Corneal nerves in health and diseaseSurvey of Ophthalmology, 2014
- A method for corneal nerves automatic segmentation and morphometric analysisComputer Methods and Programs in Biomedicine, 2012
- Automatic analysis of diabetic peripheral neuropathy using multi-scale quantitative morphology of nerve fibres in corneal confocal microscopy imagingMedical Image Analysis, 2011
- Automatic Evaluation of Corneal Nerve Tortuosity in Images from In Vivo Confocal MicroscopyInvestigative Ophthalmology & Visual Science, 2011
- Automated Software Analysis of Corneal Micrographs for Peripheral NeuropathyInvestigative Ophthalmology & Visual Science, 2010
- Corneal Confocal MicroscopyDiabetes Care, 2010
- Automatic Recognition of Corneal Nerve Structures in Images from Confocal MicroscopyInvestigative Ophthalmology & Visual Science, 2008
- Linear Structures in Mammographic Images: Detection and ClassificationIEEE Transactions on Medical Imaging, 2004
- Ridge-Based Vessel Segmentation in Color Images of the RetinaIEEE Transactions on Medical Imaging, 2004
- Multiscale vessel enhancement filtering1998