Back to Search
Start Over
U-Net Segmented Adjacent Angle Detection (USAAD) for Automatic Analysis of Corneal Nerve Structures
- Source :
- Data, Volume 5, Issue 2, Data, Vol 5, Iss 37, p 37 (2020)
- Publication Year :
- 2020
- Publisher :
- Multidisciplinary Digital Publishing Institute, 2020.
-
Abstract
- Measurement of corneal nerve tortuosity is associated with dry eye disease, diabetic retinopathy, and a range of other conditions. However, clinicians measure tortuosity on very different grading scales that are inherently subjective. Using in vivo confocal microscopy, 253 images of corneal nerves were captured and manually labelled by two researchers with tortuosity measurements ranging on a scale from 0.1 to 1.0. Tortuosity was estimated computationally by extracting a binarised nerve structure utilising a previously published method. A novel U-Net segmented adjacent angle detection (USAAD) method was developed by training a U-Net with a series of back feeding processed images and nerve structure vectorizations. Angles between all vectors and segments were measured and used for training and predicting tortuosity measured by human labelling. Despite the disagreement among clinicians on tortuosity labelling measures, the optimised grading measurement was significantly correlated with our USAAD angle measurements. We identified the nerve interval lengths that optimised the correlation of tortuosity estimates with human grading. We also show the merit of our proposed method with respect to other baseline methods that provide a single estimate of tortuosity. The real benefit of USAAD in future will be to provide comprehensive structural information about variations in nerve orientation for potential use as a clinical measure of the presence of disease and its progression.
- Subjects :
- Information Systems and Management
Corneal nerve
Computer science
In vivo confocal microscopy
deep learning
corneal nerve
Tortuosity
U-Net
lcsh:Z
lcsh:Bibliography. Library science. Information resources
030218 nuclear medicine & medical imaging
Computer Science Applications
03 medical and health sciences
0302 clinical medicine
030221 ophthalmology & optometry
Nerve structure
tortuosity
Grading (tumors)
automatic analysis
Information Systems
Biomedical engineering
Subjects
Details
- Language :
- English
- ISSN :
- 23065729
- Database :
- OpenAIRE
- Journal :
- Data
- Accession number :
- edsair.doi.dedup.....d4035038d47addea67cdbac18604e20f
- Full Text :
- https://doi.org/10.3390/data5020037