Please use this identifier to cite or link to this item: https://repository.sustech.edu/handle/123456789/14643
Title: Characterizationof RenalInfection Using Ultrasonography and Texture Analysis
Other Titles: توصيف التهاب الكلى بالتصوير بالموجات فوق الصوتية و التحليل النسيجي
Authors: Ibrahim, Ibtisam Abd Allah Fadull Elmula
Supervisor, - Elsafi Ahmed Abdalla Balla
Co - Supervisor, - Mohamed Elfadil Mohamed Gar Elnabi
Keywords: Medical Radiologic
Ultrasonography
RenalInfection
Issue Date: 21-Aug-2016
Publisher: Sudan University of Science and Technology
Citation: Ibrahim, Ibtisam Abd Allah Fadull Elmula . Characterizationof RenalInfection Using Ultrasonography and Texture Analysis \ Ibtisam Abd Allah Fadull Elmula Ibrahim ; Elsafi Ahmed Abdalla Balla .- Khartoum:Sudan University of Science and Technology,College of Medical Radiologic Sciences,2016.-112p:ill;28cm.- PhD
Abstract: This study was done to determine the ultrasonography characteristics in renal infections (glomerulonephritis and pyelonephritis) versus normal. This study carried out in Khartoum hospital,Madanihospital ,Elmanagil hospital and Elkramit family health center , in those referred to urology department in the period from January 2014 to August 2016. A total of 234 patients were included in this study (106 were normal cases (22.6% male and 77.4% female) 128 patients had renal infections; 68 diagnosed with glomerulonephritis (38.2% males and 61.8% females) 60 with pyelonephritis (33.3% males and 66.7 females). Ultrasound scanning has been carried out, using a curve linear probe with a frequency of 3.5 to 5MHz. texrural features were extracted from kidney medulla and calycle system using a window of 3×3 pixel of first order statistics. The result of this study reveals that female was mostly affected by glomerulonephritis and pyelonephritis rather than male with male to female ratio of 1:1.6 and 1:2 respectively. Flank pain found in 82.4% associated with glomerulonephritis while 75% of pyelonephritis showed ill-defined corticomedullary differentiation. The overall accuracy using textural feature extracted from medulla was 98% while for those extracted from pelvic calycle system was 95.7%. In conclusion linear function was developed to classify other ultrasound images using textural features or ultrasonography characterizes with an error <4%.
Description: Thesis
URI: http://repository.sustech.edu/handle/123456789/14643
Appears in Collections:PhD theses :Medical Radiologic Science

Files in This Item:
File Description SizeFormat 
Characterizationof RenalInfection ...........pdfTitle48.76 kBAdobe PDFView/Open
Abstract .pdfAbstract140.73 kBAdobe PDFView/Open
Research.pdfResearch8.55 MBAdobe PDFView/Open
Supplements.pdfSupplements23.78 kBAdobe PDFView/Open
Supplements1 (1).pdfSupplements290.14 kBAdobe PDFView/Open
Supplements1 (2).pdfSupplements272.46 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.