Automatic liver parenchyma segmentation from abdominal CT images using support vector machines
read more
Citations
Automatic liver segmentation in MRI images using an iterative watershed algorithm and artificial neural network
Review on the methods of automatic liver segmentation from abdominal images
New approach to detect and classify stroke in skull CT images via analysis of brain tissue densities.
Computer-aided diagnosis of cirrhosis and hepatocellular carcinoma using multi-phase abdomen CT
An Approach of Household Power Appliance Monitoring Based on Machine Learning
References
An Introduction to Support Vector Machines and Other Kernel-based Learning Methods
Image Analysis and Mathematical Morphology
Statistical and structural approaches to texture
Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters.
Multifrequency channel decompositions of images and wavelet models
Related Papers (5)
Frequently Asked Questions (15)
Q2. What future works have the authors mentioned in the paper "Automatic liver parenchyma segmentation from abdominal ct images using support vector machines" ?
Future work and further improvements needed for the method include: theoretical and implemental study on the support vector machine classifier to make the pixel based classifier more robust on test data ; calculation speed improvement to SVM on both training and testing ; and testing on more data.
Q3. What is the wavelet transform used in image processing?
The family of vectors is obtained by translations and dilatations of the base atom:)(1)(, s ut s tsu −= ψψ (EQ 2)In image processing applications, the wavelet transform is usually computed with dyadic wavelet transform which is implemented by filter banks.
Q4. What are the main categories of texture analysis?
There mainly exist four categories of texture analysis, namely, structural, statistical, model-based, and transform-based approaches [9].
Q5. What was the purpose of the study?
In designing the support vector machine classifier, an open source software LIBSVM [18] was used as a platform to derive proper parameters.
Q6. What are the limitations of the SVM?
Since the SVM is a pixel-wised classifier, i.e., it classifies the CT slices pixel by pixel, and the classification will not be perfect on test data, there will be both false negative error (FNE) inside the liver parenchyma and false positive error (FPE) outside the liver parenchyma.
Q7. What are the main aspects of the automatic segmentation of liver?
both texture features and distribution or resolution features are important in isolating the liver from other surrounding areas.
Q8. What is the definition of a ffv?
False negative volume fraction (FNVF)FPVF is defined as the amount of the pixels that are falsely classified by SVM as the liver, as a fraction of the total amount of pixels that are manually identified as the liver by radiologist.
Q9. What is the last aspect of the proposed approach?
The last aspect is that the combination of a pixel-wised classifier with a shape-wised refiner will deliver a robust yet accurate segmentation of the liver.
Q10. What is the morphological operation used to classify the liver?
When a “dilate” or “erode” operator is used, the size of the structural element has to be chosen carefully: if the structural element is too small, there will form multiple regions inside the liver; if the structural element is too large, other organs and tissues will be wrongly combined into liver.
Q11. What is the morphological operation of the SVM?
Then the SVM as a classifier can classify any input data x with the following classify function:)},({)( 1xxKysignxf ii li i∑ == α (EQ 7)D. Integrated Morphological Operations A SVM is a pixel-wised classifier.
Q12. What is the way to solve the wavelet transform?
Applying Lagrange multipliers, the optimal quadratic programming problem with the above linear conditions can be solved as the following dual optimal problem:)},(max{ 1 1 2 1 1 jijilijj jili i xxKyy∑∑∑ = == − ααα , subject toCi ≤≤ α0 , and 0 1 =∑ = ili i yα (EQ 5)Where iα is support value, the xi corresponding to Ci ≤≤ α0 is called support vector (SV), and the xicorresponding to Ci << α0 is called normal support vector (noted as NSV).)],([1 j NSVx SVx ijjiN xxKyyb i j NSV ∑ ∑ ∈ ∈−= α (EQ 6)Authorized licensed use limited to: University of Newcastle.
Q13. What is the definition of a hyperplane?
Then an optimal hyperplane in canonical form must satisfy the following constraints:0)( =+ bxωφ (EQ 3) Where b∈R, ω is a normal vector, )(xφ is an innerproduct that maps the input space into a high dimension linear space.
Q14. What is the definition of a wavelet transform?
The wavelet transform is defined bydt suttffsuWf ssu )()(,),( *1, −== ∫ +∞ ∞− ψψ (EQ 1)Where the base atom ψ is a zero average function, centered around zero with a finite energy.
Q15. What is the definition of the liver?
Support vector machines are used to classify each pixel into either liver (with value of 1 assigned) or non-liver (with value of 0 assigned).