Ying Zhuge

Medical Image Segmentation by Combining Graph Cuts and Oriented Active Appearance Models

In this paper, we propose a novel method based on a strategic combination of the active appearance model (AAM), live wire (LW), and graph cuts (GCs) for abdominal 3-D organ segmentation. The proposed method consists of three main parts: model building, object recognition, and delineation. In the model building part, we construct the AAM and train the LW cost function and GC parameters. In the recognition part, a novel algorithm is proposed for improving the conventional AAM matching method, which effectively combines the AAM and LW methods, resulting in the oriented AAM (OAAM). A multiobject strategy is utilized to help in object initialization. We employ a pseudo-3-D initialization strategy and segment the organs slice by slice via a multiobject OAAM method. For the object delineation part, a 3-D shape-constrained GC method is proposed. The object shape generated from the initialization step is integrated into the GC cost computation, and an iterative GC-OAAM method is used for object delineation. The proposed method was tested in segmenting the liver, kidneys, and spleen on a clinical CT data set and also on the MICCAI 2007 Grand Challenge liver data set. The results show the following: 1) The overall segmentation accuracy of true positive volume fraction TPVF >; 94.3% and false positive volume fraction FPVF <; 0.2% can be achieved; 2) the initializa- tion performance can be improved by combining the AAM and LW; 3) the multiobject strategy greatly facilitates initialization; 4) compared with the traditional 3-D AAM method, the pseudo-3-D OAAM method achieves comparable performance while running 12 times faster; and 5) the performance of the proposed method is comparable to state-of-the-art liver segmentation algorithm. The executable version of the 3-D shape-constrained GC method with a user interface can be downloaded from http://xinjianchen.word- press.com/research/.

Iterative relative fuzzy connectedness for multiple objects with multiple seeds

In this paper we present a new theory and an algorithm for image segmentation based on a strength of connectedness between every pair of image elements. The object definition used in the segmentation algorithm utilizes the notion of iterative relative fuzzy connectedness, IRFC. In previously published research, the IRFC theory was developed only for the case when the segmentation was involved with just two segments, an object and a background, and each of the segments was indicated by a single seed. (See Udupa, Saha, Lotufo [15] and Saha, Udupa [14].) Our theory, which solves a problem of Udupa and Saha from [13], allows simultaneous segmentation involving an arbitrary number of objects. Moreover, each segment can be indicated by more than one seed, which is often more natural and easier than a single seed object identification.The first iteration step of the IRFC algorithm gives a segmentation known as relative fuzzy connectedness, RFC, segmentation. Thus, the IRFC technique is an extension of the RFC method. Although the RFC theory, due to Saha and Udupa [19], is developed in the multi object/multi seed framework, the theoretical results presented here are considerably more delicate in nature and do not use the results from [19]. On the other hand, the theoretical results from [19] are immediate consequences of the results presented here. Moreover, the new framework not only subsumes previous fuzzy connectedness descriptions but also sheds new light on them. Thus, there are fundamental theoretical advances made in this paper.We present examples of segmentations obtained via our IRFC based algorithm in the multi object/multi seed environment, and compare it with the results obtained with the RFC based algorithm. Our results indicate that, in many situations, IRFC outperforms RFC, but there also exist instances where the gain in performance is negligible.

Methodology for evaluating image-segmentation algorithms

The purpose of this paper is to describe a framework for evaluating image segmentation algorithms. Image segmentation consists of object recognition and delineation. For evaluating segmentation methods, three factors - precision (reproducibility), accuracy (agreement with truth, validity), and efficiency (time taken) - need to be considered for both recognition and delineation. To assess precision, we need to choose a figure of merit, repeat segmentation considering all sources of variation, and determine variations in figure of merit via statistical analysis. It is impossible usually to establish true segmentation. Hence, to assess accuracy, we need to choose a surrogate of true segmentation and proceed as for precision. In determining accuracy, it may be important to consider different landmark areas of the structure to be segmented depending on the application. To assess efficiency, both the computational and the user time required for algorithm and operator training and for algorithm execution should be measured and analyzed. Precision, accuracy, and efficiency are interdependent. It is difficult to improve one factor without affecting others. Segmentation methods must be compared based on all three factors. The weight given to each factor depends on application.

Vectorial scale-based fuzzy-connected image segmentation

This paper presents an extension of previously published theory and algorithms for fuzzy-connected image segmentation. In this approach, a strength of connectedness is assigned to every pair of image elements. This is done by finding the strongest among all possible connecting paths between the two elements in each pair. The strength assigned to a particular path is defined as the weakest affinity between successive pairs of elements along the path. Affinity specifies the degree to which elements hang together locally in the image. A scale is determined at every element in the image that indicates the size of the largest homogeneous hyperball region centered at the element. In determining affinity between any two elements, all elements within their scale regions are considered. This method has been effectively utilized in several medical applications. In this paper, we generalize this method from scalar images to vectorial images. In a vectorial image, scale is defined as the radius of the largest hyperball contained in the same homogeneous region under a predefined condition of homogeneity of the image vector field. Two different components of affinity, namely homogeneity-based affinity and object-feature-based affinity, are devised in a fully vectorial manner. The original relative fuzzy connectedness algorithm is utilized to delineate a specified object via a competing strategy among multiple objects. We have presented several studies to evaluate the performance of this method based on simulated MR images, 20 clinical MR images, and 250 mathematical phantom images. These studies indicate that the fully vectorial fuzzy connectedness formulation has generally overall better accuracy than the method using some intermediate ad hoc steps to fit the vectorial image to a scalar fuzzy connectedness formulation, and precision and efficiency are similar for these two methods.

Scale-based method for correcting background intensity variation in acquired images

An automatic, acquisition-protocol-independent, entirely image-based strategy for correcting background intensity variation in medical images has been developed. Local scale - a fundamental image property that is derivable entirely from the image and that does not require any prior knowledge about the imaging protocol or object material property distributions - is used to obtain a set of homogeneous regions, no matter what each region is, and to fit a 2nd degree polynomial to the intensity variation within them. This polynomial is used to correct the intensity variation. The above procedure is repeated for the corrected image until the size of segmented homogeneous regions does not change significantly from that in the previous iteration. Intensity scale standardization is effected to make sure that the corrected images are not biased by the fitting strategy. The method has been tested on 1000 3D mathematical phantoms, which include 5 levels each of blurring and noise and 4 types of background variation - additive and multiplicative Gaussian and ramp. It has also been tested on 10 clinical MRI data sets of the brain. These tests, and a comparison with the method of homomorphic filtering, indicate the effectiveness of the method.

CAVASS: A Computer-Assisted Visualization and Analysis Software System

The Medical Image Processing Group at the University of Pennsylvania has been developing (and distributing with source code) medical image analysis and visualization software systems for a long period of time. Our most recent system, 3DVIEWNIX, was first released in 1993. Since that time, a number of significant advancements have taken place with regard to computer platforms and operating systems, networking capability, the rise of parallel processing standards, and the development of open-source toolkits. The development of CAVASS by our group is the next generation of 3DVIEWNIX. CAVASS will be freely available and open source, and it is integrated with toolkits such as Insight Toolkit and Visualization Toolkit. CAVASS runs on Windows, Unix, Linux, and Mac but shares a single code base. Rather than requiring expensive multiprocessor systems, it seamlessly provides for parallel processing via inexpensive clusters of work stations for more time-consuming algorithms. Most importantly, CAVASS is directed at the visualization, processing, and analysis of 3-dimensional and higher-dimensional medical imagery, so support for digital imaging and communication in medicine data and the efficient implementation of algorithms is given paramount importance.

Image Background Inhomogeneity Correction in MRI via Intensity Standardization

An automatic, simple, and image intensity standardization-based strategy for correcting background inhomogeneity in MR images is presented in this paper. Image intensities are first transformed to a standard intensity gray scale by a standardization process. Different tissue sample regions are then obtained from the standardized image by simply thresholding based on fixed intensity intervals. For each tissue region, a polynomial is fitted to the estimated discrete background intensity variation. Finally, a combined polynomial is determined and used for correcting the intensity inhomogeneity in the whole image. The above procedure is repeated on the corrected image iteratively until the size of the extracted tissue regions does not change significantly in two successive iterations. Intensity scale standardization is effected to make sure that the corrected image is not biased by the fitting strategy. The method has been tested on a number of simulated and clinical MR images. These tests and a comparison with the method of non-parametric non-uniform intensity normalization (N3) indicate that the method is effective in background intensity inhomogeneity correction and may have a slight edge over the N3 method.

Intensity standardization simplifies brain MR image segmentation

Typically, brain MR images present significant intensity variation across patients and scanners. Consequently, training a classifier on a set of images and using it subsequently for brain segmentation may yield poor results. Adaptive iterative methods usually need to be employed to account for the variations of the particular scan. These methods are complicated, difficult to implement and often involve significant computational costs. In this paper, a simple, non-iterative method is proposed for brain MR image segmentation. Two preprocessing techniques, namely intensity inhomogeneity correction, and more importantly MR image intensity standardization, used prior to segmentation, play a vital role in making the MR image intensities have a tissue-specific numeric meaning, which leads us to a very simple brain tissue segmentation strategy.Vectorial scale-based fuzzy connectedness and certain morphological operations are utilized first to generate the brain intracranial mask. The fuzzy membership value of each voxel within the intracranial mask for each brain tissue is then estimated. Finally, a maximum likelihood criterion with spatial constraints taken into account is utilized in classifying all voxels in the intracranial mask into different brain tissue groups. A set of inhomogeneity corrected and intensity standardized images is utilized as a training data set. We introduce two methods to estimate fuzzy membership values. In the first method, called SMG (for simple membership based on a gaussian model), the fuzzy membership value is estimated by fitting a multivariate Gaussian model to the intensity distribution of each brain tissue whose mean intensity vector and covariance matrix are estimated and fixed from the training data sets. The second method, called SMH (for simple membership based on a histogram), estimates fuzzy membership value directly via the intensity distribution of each brain tissue obtained from the training data sets. We present several studies to evaluate the performance of these two methods based on 10 clinical MR images of normal subjects and 10 clinical MR images of Multiple Sclerosis (MS) patients. A quantitative comparison indicates that both methods have overall better accuracy than the k-nearest neighbors (kNN) method, and have much better efficiency than the Finite Mixture (FM) model based Expectation-Maximization (EM) method. Accuracy is similar for our methods and EM method for the normal subject data sets, but much better for our methods for the patient data sets.

Vectoral-scale-based fuzzy-connected image segmentation

This paper presents an extension of previously published theory and algorithms for scale-based fuzzy connected image segmentation. In this approach, a strength of connectedness is assigned to every pair of image elements. This is done by finding the strongest among all possible connecting paths between the two elements in each pair. The strength assigned to a particular path is defined as the weakest affinity between successive pairs of elements along the path. Affinity specifies the degree to which elements hang together locally in the image. A scale is determined at every element in the image that indicates the size of the largest homogeneous region centered at the element. IN determining affinity between any two elements, all elements within their scale regions are considered. This method has been effectively utilized in several medical applications. In this paper, we generalize this scale-based fuzzy connected image segmentation method from scalar images to vectorial images. In a vectorial image, scale is defined as the radius of the largest hyperball contained in the same homogeneous region under a predefined condition of homogeneity of the image vector field. Two different components of affinity, namely homogeneity-based affinity and object-feature-based affinity, are devised in a fully vectorial manner. The original relative fuzzy connectedness algorithm is utilized to delinate a specified object via a competing strategy among multiple objects. We have tested this method in several medical applications, which qualitatively demonstrate the effectiveness of the method. Based on evaluation studies, a precision and accuracy of better than 95% has been achieved in an application involving MR brain image analysis.

GPU accelerated fuzzy connected image segmentation by using CUDA

Image segmentation techniques using fuzzy connectedness principles have shown their effectiveness in segmenting a variety of objects in several large applications in recent years. However, one problem of these algorithms has been their excessive computational requirements when processing large image datasets. Nowadays commodity graphics hardware provides high parallel computing power. In this paper, we present a parallel fuzzy connected image segmentation algorithm on Nvidia’s Compute Unified Device Architecture (CUDA) platform for segmenting large medical image data sets. Our experiments based on three data sets with small, medium, and large data size demonstrate the efficiency of the parallel algorithm, which achieves a speed-up factor of 7.2x, 7.3x, and 14.4x, correspondingly, for the three data sets over the sequential implementation of fuzzy connected image segmentation algorithm on CPU.