{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T05:36:49Z","timestamp":1778823409004,"version":"3.51.4"},"reference-count":31,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2020,4,14]],"date-time":"2020-04-14T00:00:00Z","timestamp":1586822400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Data"],"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.3390\/data5020037","type":"journal-article","created":{"date-parts":[[2020,4,15]],"date-time":"2020-04-15T04:01:46Z","timestamp":1586923306000},"page":"37","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["U-Net Segmented Adjacent Angle Detection (USAAD) for Automatic Analysis of Corneal Nerve Structures"],"prefix":"10.3390","volume":"5","author":[{"given":"Philip","family":"Mehrgardt","sequence":"first","affiliation":[{"name":"School of Computer Science, The University of Sydney, NSW 2006, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seid Miad","family":"Zandavi","sequence":"additional","affiliation":[{"name":"School of Computer Science, The University of Sydney, NSW 2006, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2726-9109","authenticated-orcid":false,"given":"Simon K.","family":"Poon","sequence":"additional","affiliation":[{"name":"School of Computer Science, The University of Sydney, NSW 2006, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juno","family":"Kim","sequence":"additional","affiliation":[{"name":"School of Optometry and Vision Science, University of New South Wales, Sydney, NSW 2052, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maria","family":"Markoulli","sequence":"additional","affiliation":[{"name":"School of Optometry and Vision Science, University of New South Wales, Sydney, NSW 2052, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7792-2327","authenticated-orcid":false,"given":"Matloob","family":"Khushi","sequence":"additional","affiliation":[{"name":"School of Computer Science, The University of Sydney, NSW 2006, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2020,4,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1205","DOI":"10.1111\/dme.12466","article-title":"Standardizing corneal nerve fibre length for nerve tortuosity increases its association with measures of diabetic neuropathy","volume":"31","author":"Edwards","year":"2014","journal-title":"Diabet. Med."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1111\/j.1442-9071.2010.02363.x","article-title":"Anatomy and physiology of the human eye: Effects of mucopolysaccharidoses disease on structure and function\u2014A review","volume":"38","author":"Willoughby","year":"2010","journal-title":"Clin. Exp. Ophthalmol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1016\/j.cmpb.2016.07.032","article-title":"A fully automatic nerve segmentation and morphometric parameter quantification system for early diagnosis of diabetic neuropathy in corneal images","volume":"135","author":"Ipson","year":"2016","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_4","unstructured":"Arnold, F. (1832). Anatomische und Physiologische Untersuchungen \u00fcber das Auge des Menschen, Heidelberg, Germany."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"556","DOI":"10.2337\/dc11-1909","article-title":"Global prevalence and major risk factors of diabetic retinopathy","volume":"35","author":"Yau","year":"2012","journal-title":"Diabetes Care"},{"key":"ref_6","first-page":"909","article-title":"Diabetic neuropathy","volume":"82","author":"Rayaz","year":"1998","journal-title":"Ann. Der Phys."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"374","DOI":"10.1097\/00003226-200105000-00008","article-title":"Morphology of corneal nerves using confocal microscopy","volume":"20","year":"2001","journal-title":"Cornea"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1167\/iovs.03-0637","article-title":"Corneal nerve tortuosity in diabetic patients with neuropathy","volume":"45","author":"Kallinikos","year":"2004","journal-title":"Investig. Ophthalmol. Vis. Sci."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2017","DOI":"10.1167\/iovs.06-1129","article-title":"The cornea in sjogren\u2019s syndrome: An in vivo confocal study","volume":"48","author":"Viola","year":"2007","journal-title":"Investig. Ophthalmol. Vis. Sci."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"6404","DOI":"10.1167\/iovs.11-7529","article-title":"Automatic evaluation of corneal nerve tortuosity in images from in vivo confocal microscopy","volume":"52","author":"Ohashi","year":"2011","journal-title":"Investig. Ophthalmol. Vis. Sci."},{"key":"ref_11","unstructured":"Jesse, M., Vislisel Mark, A., Greiner Miles, F., and Greenwald Brittni, A. (2019, October 15). Corneal Imaging: An Introduction. Available online: http:\/\/webeye.ophth.uiowa.edu\/eyeforum\/tutorials\/Corneal-Imaging\/Index.htm."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1016\/j.survophthal.2013.09.002","article-title":"Corneal nerves in health and disease","volume":"59","author":"Shaheen","year":"2013","journal-title":"Surv. Opthalmol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"338","DOI":"10.1111\/j.1444-0938.2012.00743.x","article-title":"Assessing corneal nerve structure and function indiabetic neuropathy","volume":"95","author":"Tavakoli","year":"2012","journal-title":"Clin. Exp. Optom."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Stachs, O., Sperlich, K., Bohn, S., Stolz, H., and Guthoff, R. (2017, January 7). Rostock cornea module 2.0\u2013A versatile extension for anterior segment imaging. Proceedings of the 2017 European Association for Vision and Eye Research Conference, Toronto, ON, Canada.","DOI":"10.1111\/j.1755-3768.2017.02381"},{"key":"ref_15","first-page":"147","article-title":"Automatic analysis of corneal nerves imaged using in vivo confocal microscopy","volume":"101","author":"Kim","year":"2018","journal-title":"Optom. Aust."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"5102","DOI":"10.1167\/iovs.15-17284","article-title":"Focused tortuosity definitions based on expert clinical assessment of corneal subbasal nerves","volume":"56","author":"Lagali","year":"2015","journal-title":"Investig. Opthalmol. Vis. Sci."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1016\/S1386-5056(98)00163-4","article-title":"Measurement and classification of retinal vascular","volume":"53","author":"Hart","year":"1999","journal-title":"Int. J. Med. Inform."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1016\/j.media.2016.04.006","article-title":"A fully automated tortuosity quantification system with application to corneal nerve fibres in confocal microscopy images","volume":"32","author":"Aggarwal","year":"2016","journal-title":"Med Image Anal."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Ruggeri, A., Guimaraes, P., and Wigdahl, J. (2016, January 16\u201320). Automatic estimation of corneal nerves focused tortuosities. Proceedings of the 2016 38th IEEE Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Orlando, FL, USA.","DOI":"10.1109\/EMBC.2016.7590953"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Colonna, A., Scarpa, F., and Ruggeri, A. (2018). Segmentation of Corneal Nerves Using a U-Net-Based Convolutional Neural Network, Springer.","DOI":"10.1007\/978-3-030-00949-6_22"},{"key":"ref_21","first-page":"1085823","article-title":"Fully automated corneal nerve segmentation algorithm for corneal nerves analysis from in-vivo uhr-oct images","volume":"10858","author":"Hosseinaee","year":"2019","journal-title":"Ophthalmic Technol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"921","DOI":"10.1097\/ICO.0000000000001949","article-title":"Implementation of a quality index for improvement of quantification of corneal nerves in corneal confocal microcopy images: A multicenter study","volume":"38","author":"Sturm","year":"2019","journal-title":"Cornea"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"691","DOI":"10.1097\/IJG.0000000000001270","article-title":"Optic nerve tortuosity and globe proptosis in normal and glaucoma subjects","volume":"28","author":"Wang","year":"2019","journal-title":"J. Glaucoma"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Barlow, H., Mao, S., and Khushi, M. (2019). Predicting High-Risk Prostate Cancer Using Machine Learning Methods. Data, 4.","DOI":"10.3390\/data4030129"},{"key":"ref_25","unstructured":"Brox, T., Ronneberger, O., and Fischer, P. (2019, October 17). U-net: Convolutional Networks for Biomedical Image Segmentation. Available online: https:\/\/arxiv.org\/abs\/1505.04597."},{"key":"ref_26","unstructured":"(2019, October 17). Zhixuhao 2018, Implementation of Deep Learning Framework-Unet, Using Keras, GitHub Repository. Available online: https:\/\/github.com\/zhixuhao\/unet."},{"key":"ref_27","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume":"Volume 1","author":"Krizhevsky","year":"2012","journal-title":"Proceedings of the 25th International Conference on Neural Information Processing Systems"},{"key":"ref_28","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Khushi, M., Dean, I.M., Teber, E.T., Chircop, M., Arthur, J.W., and Flores-Rodriguez, N. (2017). Automated classification and characterization of the mitotic spindle following knockdown of a mitosis-related protein. BMC Bioinform., 18.","DOI":"10.1186\/s12859-017-1966-4"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1186\/1746-1596-8-22","article-title":"Open source tools for management and archiving of digital microscopy data to allow integration with patient pathology and treatment information","volume":"8","author":"Khushi","year":"2013","journal-title":"Diagn Pathol."},{"key":"ref_31","unstructured":"Cho, J., Lee, K., Shin, E., Choy, G., and Do, S. (2015). How much data is needed to train a medical image deep learning system to achieve necessary high accuracy. arXiv."}],"container-title":["Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5729\/5\/2\/37\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T13:44:56Z","timestamp":1760363096000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5729\/5\/2\/37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4,14]]},"references-count":31,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2020,6]]}},"alternative-id":["data5020037"],"URL":"https:\/\/doi.org\/10.3390\/data5020037","relation":{},"ISSN":["2306-5729"],"issn-type":[{"value":"2306-5729","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,4,14]]}}}