Detection of diseases in an early stage is very important since it can make the treatment of patients easier, safer and more ecient. For the detection of rheumatic diseases, and even prediction of tendencies towards such diseases, capillaroscopy is becoming an increasingly recognized method. Nail-fold capillaroscopy is a non-invasive imaging technique that is used for analysis of microcirculation abnormalities that may lead todisease like systematic sclerosis, Reynauds phenomenon and others. The main goal of this master thesis project is to provide new tools and techniques for the analysis of capillaroscopy images from the nail-fold area. Image processing and machine learning techniques are applied to images obtained by digital microscopes, like Mediscope as produced by Optilia Instruments AB, Sollentuna. This thesis oers a novel way for segmentation of capillaries from images as well as (semi)automatic capillary width calculation and automatic annotation of capillaries. These tools provide new insights into the structure of capillaries and also reduce the time required for measurement/annotation of capillaries.
| Identifer | oai:union.ndltd.org:UPSALLA1/oai:DiVA.org:kth-174868 |
| Date | January 2015 |
| Creators | Vucic, Vladimir |
| Publisher | KTH, Skolan för elektro- och systemteknik (EES) |
| Source Sets | DiVA Archive at Upsalla University |
| Language | English |
| Detected Language | English |
| Type | Student thesis, info:eu-repo/semantics/bachelorThesis, text |
| Format | application/pdf |
| Rights | info:eu-repo/semantics/openAccess |
| Relation | TRITA-EE, 1653-5146 ; 2015:58 |
Page generated in 0.0016 seconds