Kaid, Rakeeb Saeed (2007) Estimation Of Gestational Age From Ultrasound Images Using Direct Least Squares Fitting Of Ellipses. Masters thesis, Universiti Putra Malaysia.
Ultrasound imaging or echography is a very important and competitive medical diagnostic tool, due to its low cost, short acquisition time, and non-invasive nature. However, ultrasound images are inherently difficult to analyze due to their echo texture, speckle noise, low contrast and weak edges. Measurement of the fetal head biparietal diameter (BPD) and head circumference (HC) is crucial for estimation of fetal age. Due to the noisy nature of ultrasound images and variation in image acquisition and measurement techniques, manual measurements of these parameters are subject to inter and intra-observer variability. The aim of this work is to develop a fully automated technique for efficient and accurate detection and estimation of the gestational age of a fetus by measuring the biparietal diameter of the head. The head was assumed to have an elliptical shape. No user input or size range of the head was required. The proposed technique based on a method called direct least squares fitting of an ellipse. This method combines several advantages: It is ellipse-specific so that even bad data will always return an ellipse, it can be solved naturally by a generalized eigensystem, and it is extremely robust, efficient and easy to implement. The process goes through three steps: image preprocessing (contrast enhancement, smoothing, and intensity enhancement), object extraction (sharpening, morphological reconstruction and skeletoning) and fitting an ellipse to the resultant shape and measuring its parameters. The proposed fully automatic technique was tested and evaluated on about 20 images of fetal heads. The images had a combination of noise and low contrast. Excellent linear correlation r = 0.997 between manual and automatic measurement was obtained, which verifies the reliability of the proposed automatic approach.
|Item Type:||Thesis (Masters)|
|Chairman Supervisor:||Mohammad Hamiruce Marhaban, PhD|
|Call Number:||FK 2007 90|
|Faculty or Institute:||Faculty of Engineering|
|Deposited By:||Nurul Hayatie Hashim|
|Deposited On:||08 Apr 2010 14:35|
|Last Modified:||02 Jun 2011 16:32|
Repository Staff Only: item control page