Multi-scale convolutional neural network for accurate corneal segmentation in early detection of fungal keratitis
Article
Mayya, Veena, Kamath S, Sowmya, Kulkarni, Uma, Hazarika, Manali, Barua, Prabal Datta and Acharya, U. Rajendra. 2021. "Multi-scale convolutional neural network for accurate corneal segmentation in early detection of fungal keratitis." Journal of Fungi. 7 (10). https://doi.org/10.3390/jof7100850
| Article Title | Multi-scale convolutional neural network for accurate corneal segmentation in early detection of fungal keratitis |
|---|---|
| ERA Journal ID | 213247 |
| Article Category | Article |
| Authors | Mayya, Veena, Kamath S, Sowmya, Kulkarni, Uma, Hazarika, Manali, Barua, Prabal Datta and Acharya, U. Rajendra |
| Journal Title | Journal of Fungi |
| Journal Citation | 7 (10) |
| Article Number | 850 |
| Number of Pages | 11 |
| Year | 2021 |
| Publisher | MDPI AG |
| Place of Publication | Switzerland |
| ISSN | 2309-608X |
| Digital Object Identifier (DOI) | https://doi.org/10.3390/jof7100850 |
| Web Address (URL) | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85117468546&doi=10.3390%2fjof7100850&partnerID=40&md5=6b2395110c060050d03d3c37a8821ca4 |
| Abstract | Microbial keratitis is an infection of the cornea of the eye that is commonly caused by prolonged contact lens wear, corneal trauma, pre-existing systemic disorders and other ocular surface disorders. It can result in severe visual impairment if improperly managed. According to the latest World Vision Report, at least 4.2 million people worldwide suffer from corneal opacities caused by infectious agents such as fungi, bacteria, protozoa and viruses. In patients with fungal keratitis (FK), often overt symptoms are not evident, until an advanced stage. Furthermore, it has been reported that clear discrimination between bacterial keratitis and FK is a challenging process even for trained corneal experts and is often misdiagnosed in more than 30% of the cases. However, if diagnosed early, vision impairment can be prevented through early cost-effective interventions. In this work, we propose a multi-scale convolutional neural network (MS-CNN) for accurate segmentation of the corneal region to enable early FK diagnosis. The proposed approach consists of a deep neural pipeline for corneal region segmentation followed by a ResNeXt model to differentiate between FK and non-FK classes. The model trained on the segmented images in the region of interest, achieved a diagnostic accuracy of 88.96%. The features learnt by the model emphasize that it can correctly identify dominant corneal lesions for detecting FK. |
| Keywords | Clinical decision support systems; fungal keratitis; microbial keratitis; cornea segmentation; convolution neural networks; slit-lamp images |
| ANZSRC Field of Research 2020 | 400306. Computational physiology |
| Byline Affiliations | National Institute of Technology Karnataka, India |
| Manipal Academy of Higher Education, India | |
| Yenepoya University, India | |
| University of Technology Sydney | |
| School of Management and Enterprise | |
| Ngee Ann Polytechnic, Singapore | |
| Singapore University of Social Sciences (SUSS), Singapore | |
| Asia University, Taiwan |
Permalink -
https://research.usq.edu.au/item/z1vxz/multi-scale-convolutional-neural-network-for-accurate-corneal-segmentation-in-early-detection-of-fungal-keratitis
Download files
35
total views16
total downloads1
views this month1
downloads this month