Chuin-Mu Wang

Generalized constrained energy minimization approach to subpixel target detection for multispectral imagery

Subpixel detection in multispectral imagery presents a chal- lenging problem due to relatively low spatial and spectral resolution. We present a generalized constrained energy minimization (GCEM) ap- proach to detecting targets in multispectral imagery at subpixel level. GCEM is a hybrid technique that combines a constrained energy mini- mization (CEM) method developed for hyperspectral image classification with a dimensionality expansion (DE) approach resulting from a gener- alized orthogonal subspace projection (GOSP) developed for multispec- tral image classification. DE enables us to generate additional bands from original multispectral images nonlinearly so that CEM can be used for subpixel detection to extract targets embedded in multispectral im- ages. CEM has been successfully applied to hyperspectral target detec- tion and image classification. Its applicability to multispectral imagery is yet to be investigated. A potential limitation of CEM on multispectral imagery is the effectiveness of interference elimination due to the lack of sufficient dimensionality. DE is introduced to mitigate this problem by expanding the original data dimensionality. Experiments show that the proposed GCEM detects targets more effectively than GOSP and CEM without dimensionality expansion.

Detection of spectral signatures in multispectral MR images for classification

Presents a new spectral signature detection approach to magnetic resonance (MR) image classification. It is called constrained energy minimization (CEM) method, which is derived from the minimum variance distortionless response in passive sensor array processing. It considers a bank of spectral channels as an array of sensors where each spectral channel represents a sensor and object spectral signature in multispectral MR images are viewed as signals impinging upon the array. The strength of the CEM lies on its ability in detection of spectral signatures of interest without knowing image background. The detected spectral signatures are then used for classification. The CEM makes use of a finite impulse response (FIR) filter to linearly constrain a desired object while minimizing interfering effects caused by other unknown signal sources. Unlike most spatial-based classification techniques, the proposed CEM takes advantage of spectral characteristics to achieve object detection and classification. A series of experiments is conducted and compared with the commonly used c-means method for performance evaluation. The results show that the CEM method is a promising and effective spectral technique for MR image classification.

Unsupervised orthogonal subspace projection approach to magnetic resonance image classification

MR images and remotely sensed images share similar image structures and characteristics because they are acquired remotely as image sequences by spectral channels at different wavelengths. As a result, techniques developed for one may be also applicable to the other. In the past, we have witnessed that some techniques that were developed for magnetic resonance imaging (MRI) found great success in remote sensing image applications. Unfortunately, the opposite direction is yet to be investigated. In this paper, we present an application of one successful remote sensing image classification technique, called orthogonal subspace projection (OSP), to magnetic resonance image classification. Unlike classical image classification techniques, which are designed on a pure pixel basis, OSP is a mixed pixel classification technique that models an image pixel as a linear mixture of different material substances assumed to be present in the image data, then estimates the abundance fraction of each individual material substance within a pixel for classification. Technically, such mixed pixel classification is performed by estimating the abundance fractions of material substances resident in a pixel, rather than assigning a class label to it as usually done in pure-pixel-based classification techniques such as a minimum-distance or nearest-neighbor rule. The advantage of mixed pixel classification has been demonstrated in many applications in remote sensing image processing. The MRI experiments reported in this paper further show that mixed pixel classification may have advantages over the pure pixel classification.

Computer-aided diagnostic detection system of venous beading in retinal images

The detection of venous beading in retinal images provides an early sign of diabetic retinopathy and plays an important role as a preprocessing step in diagnosing ocular diseases. We present a computer-aided diagnostic system to automatically detect venous bead- ing of blood vessels. It comprises of two modules, referred to as the blood vessel extraction module (BVEM) and the venus beading detection module (VBDM). The former uses a bell-shaped Gaussian kernel with 12 azimuths to extract blood vessels while the latter applies a neural network-based shape cognitron to detect venous beading among the extracted blood vessels for diagnosis. Both modules are fully computer- automated. To evaluate the proposed system, 61 retinal images (32 beaded and 29 normal images) are used for performance evaluation.

Contrast enhancement and tissues classification of breast MRI using Kalman filter-based linear mixing method

Much attention is currently focused on one of the newest breast examination techniques, breast MRI. Contrast-enhanced breast MRIs acquired by contrast injection have been shown to be very sensitive in the detection of breast cancer, but are also time-consuming and cause waste of medical resources. This paper therefore proposes the use of spectral signature detection technology, the Kalman filter-based linear mixing method (KFLM), which can successfully present the results as high-contrast images and classify breast MRIs into major tissues from four bands of breast MRIs. A series of experiments using phantom and real MRIs was conducted and the results compared with those of the commonly used c-means (CM) method and dynamic contrast-enhanced (DCE) breast MRIs for performance evaluation. After comparison with the CM algorithm and DCE breast MRIs, the experimental results showed that the high-contrast images generated by the spectral signature detection technology, the KFLM, were of superior quality.

Extension Neural Network Approach to Classification of Brain MRI

Magnetic Resonance Image (MRI) has been widely used for clinical applications in recent years. With the ability of scanning the same section by multiple frequencies, MRI makes it possible to generate several images on the same section. Despite of accessible abundant information, MRI also makes it more difficult to judge the location of every tissue. MRI will complicate the judgment due to strong noise. In order to resolve this problem, this paper endeavors to classify them via the help of Extension Neural Network (ENN), This paper has to demonstrate the advantages of Extension Theory, Statistical theory is considered as a judgment method, whereby obtaining experimental data of Extension Neural Network and perceptron for subsequent comparison. It has proved that Extension is superior to the other algorithms in terms of classification.

Adaptive inverse hyperbolic tangent algorithm for dynamic contrast adjustment in displaying scenes

Contrast has a great influence on the quality of an image in human visual perception. A poorly illuminated environment can significantly affect the contrast ratio, producing an unexpected image. This paper proposes an Adaptive Inverse Hyperbolic Tangent (AIHT) algorithm to improve the display quality and contrast of a scene. Because digital cameras must maintain the shadow in a middle range of luminance that includes a main object such as a face, a gamma function is generally used for this purpose. However, this function has a severe weakness in that it decreases highlight contrast. To mitigate this problem, contrast enhancement algorithms have been designed to adjust contrast to tune human visual perception. The proposed AIHT determines the contrast levels of an original image as well as parameter space for different contrast types so that not only the original histogram shape features can be preserved, but also the contrast can be enhanced effectively. Experimental results show that the proposed algorithm is capable of enhancing the global contrast of the original image adaptively while extruding the details of objects simultaneously.

Application of Artificial Immune System Approach in MRI Classification

Numerous scholars have submitted the theory and research of artificial immune systems (AISs) in recent years. Although AIS has been used in various fields, applying the AIS to medical images is very rare. The purpose of this study is using the clonal selection algorithm (CSA) of artificial immune systems for classifying the brain MRI, and displaying a single organism image which can finally offer faster organism reference information to a doctor; hence reducing the time to ascertain large number of images, so that the doctor can diagnose the nidus more efficiently and accurately. In order to verify the feasibility and efficiency of this method, we adopt statistical theory for manifold assessment and compare with the perceptron network of double layers, FCM method. The result proves that the method of this study is both feasible and useful.

An Extenics Approach to MRI Classification

Magnetic resonance imaging (MRI) has become a useful modality since it provides unparallel capability of revealing soft tissue contrast as well as 3D visualization. One potential application of MRI in clinical practice is the parenchyma classification and segmentation of normal and pathological tissue. It is the first step to address a wide range of clinical problems. This paper presents a new spectral signature detection approach to magnetic resonance (MR) image classification. It is called the extension (extenics, extension theory), which can separate the blocks efficiently so as to reduce the noise effect upon tissues. This paper has demonstrated satisfactory noise-proof features of extension. A series of experiments is conducted and compared with the commonly used c-means method for performance evaluation. The results show that the Extensions method is a promising and effective technique for MR image classification.

Comparative Evaluation of classifiers and Feature Selection Methods for Mass Screening in Digitized Mammograms

In this paper, three groups of characteristics related to mass texture are adopted, namely, SGLD (spatial gray level dependence), TS (texture spectrum) and TFCM (texture feature coding method) to describe the characteristics of masses and normal textures on digitized mammograms. Next, under the testing by classifiers, three feature selection methods - SBS (sequential backward selection), SFS (sequential forward selection) and SFSM (sequential floating search method) are used to find out suboptimal subset from 19 features in order to improve the performance of mass detection. Finally, two classifiers PNN (probabilistic neural network) and SVM (support vector machine) are applied and their performances are compared