An automated system for detecting and measuring nailfold capillaries
| Autor: | Michael Berks, Tonia Moore, Christopher J. Taylor, Andrea Murray, Ariane L. Herrick, Graham Dinsdale, Philip A. Tresadern |
|---|---|
| Rok vydání: | 2014 |
| Předmět: |
Sensitivity and Specificity
Article Microscopic Angioscopy Pattern Recognition Automated Image Interpretation Computer-Assisted Medicine Humans Computer vision RAYNAUD DISEASE Raynauds Phenomenon Nailfold Capillaroscopy integumentary system business.industry Reproducibility of Results Pattern recognition Raynaud Disease Image enhancement Image Enhancement Capillaries Fully automated Nails Vessel morphology Subtraction Technique Artificial intelligence business Algorithms Regression forest |
| Zdroj: | Medical Image Computing and Computer-Assisted Intervention – MICCAI 2014 ISBN: 9783319104034 MICCAI (1) |
| Popis: | Nailfold capillaroscopy is an established qualitative technique in the assessment of patients displaying Raynaud’s phenomenon. We describe a fully automated system for extracting quantitative biomarkers from capillaroscopy images, using a layered machine learning approach. On an unseen set of 455 images, the system detects and locates individual capillaries as well as human experts, and makes measurements of vessel morphology that reveal statistically significant differences between patients with (relatively benign) primary Raynaud’s phenomenon, and those with potentially life-threatening systemic sclerosis. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|