In English

Presentationsinformation     2012-05-30 (15:15)   •  The seminar room at Vi2

Talare Jing Liu
Kommentar DVM
Typ Master thesis presentation
Titel Implementation of a semi-automatic tool for analysis of TEM images of kidney samples
Sammanfattning Glomerular disease is a cause of chronic kidney disease and it damages the function of kidney. One symptom of glomerular disease is proteinuria, which means that large amounts of protein are emerged in the urine. To detect proteinuria, one way is to detect foot process effacement( FPE). FPE is defined as less than 1 slits/um at the glomerular basement membrane(GBM) from the expert. Measuring it in TEM images is a time-consuming task which used to be measured manually by an expert. This master’s thesis project aims at developing a semi-automatic way to distinct the FPE patients as well as a GUI to make the methods and results accessible for the user. To compute the slits/mm for each image, the GBM needs to be segmented from the background. The proposed work flow combines various filters and mathematical morphology to obtain the outer contour of the GBM. The outer contour is then smoothed and unwanted parts are removed based on distance information and angle differences between points on the contour. The length is then computed by weighted chain code counts. At last, an iterative algorithm is used to locate the position of the ”slits” using local information. For each iteration, both binary image information and gradient information are used to compute candidate ”slits” locations. The result from length measurement and ”slits” counting can be manually corrected by the user. A tool for manual measurement is also provided as an option. In this case, the user can add anchor points on the outer contour of the GBM and then the length is automatically measured and ”slits” locations are detected. For very difficult images, the user can also mark all ”slits” location by hand. To evaluate the performance and the accuracy, data from five patients are tested, and for each patient six images are available. The images are 2048 2048 gray-scale indexed 8 bit images and the scale was 0.008 um/ pixel. The FPE patient is successfully distinguished.