Study on Ultrasound Kidney Images Using Principal Component Analysis: A Preliminary Result

نویسندگان

  • C. Karthikeyini
  • K. Bommanna Raja
  • M. Madheswaran
چکیده

An effort has been made to test the potential of principal component analysis (PCA) method for quantifying and classifying the ultrasound kidney images. For our analysis two different classes of kidney images namely normal (NR) and medical renal diseases (MRD) are considered. The eigen values and vectors are derived for a set of 40 images. The weight vectors (WV) are estimated from the obtained eigen vectors. The result indicates that the mean value of WV for NR is 0.4205 and for MRD is -0.9983. The sum value of WV for NR and MRD is 8.4103 and -19.9657 respectively. The regression analysis shows that WV’s of two classes are negative correlated and are in weak moderate association (-0.4271). The student t-test specifies that the eigen value and WV are much significant (p<0.005) in separating the classes of kidney image under study. These analysis shows that there exists an appreciable measure of relevance for this parameter weight vector in classifying the kidney images. .

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Automatic classification of Non-alcoholic fatty liver using texture features from ultrasound images

Background: Accurate and early detection of non-alcoholic fatty liver, which is a major cause of chronic diseases is very important and is vital to prevent the complications associated with this disease. Ultrasound of the liver is the most common and widely performed method of diagnosing fatty liver. However, due to the low quality of ultrasound images, the need for an automatic and intelligent...

متن کامل

Feature reduction of hyperspectral images: Discriminant analysis and the first principal component

When the number of training samples is limited, feature reduction plays an important role in classification of hyperspectral images. In this paper, we propose a supervised feature extraction method based on discriminant analysis (DA) which uses the first principal component (PC1) to weight the scatter matrices. The proposed method, called DA-PC1, copes with the small sample size problem and has...

متن کامل

Faults and fractures detection in 2D seismic data based on principal component analysis

Various approached have been introduced to extract as much as information form seismic image for any specific reservoir or geological study. Modeling of faults and fractures are among the most attracted objects for interpretation in geological study on seismic images that several strategies have been presented for this specific purpose. In this study, we have presented a modified approach of ap...

متن کامل

Detection of zinc-lead mineralization and associated alteration in the Mehdiabad deposit, Yazd province, using ASTER and Landsat 8-OLI satellite images

The Mehdiabad zinc-lead deposit, which is located at the East of Mehriz city, is a carbonate-hosted ore deposit lying in the dolomitic rocks of Taft Formation. This deposit is composed of oxide-carbonate and sulfide ores. Different spectral processing techniques were applied to ASTER and Landsat 8-OLI multispectral images to detect different mineralization zones and associated alterations. In O...

متن کامل

Face Recognition using Eigenfaces , PCA and Supprot Vector Machines

This paper is based on a combination of the principal component analysis (PCA), eigenface and support vector machines. Using N-fold method and with respect to the value of N, any person’s face images are divided into two sections. As a result, vectors of training features and test features are obtain ed. Classification precision and accuracy was examined with three different types of kernel and...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2004