Application of artificial neural networks for the classification of liver lesions by image texture parameters
TL;DR: In this article, a multilayered back-propagation neural network was used for liver lesion classification using B-scan ultrasound images for normal, hemangioma and malignant livers.
Abstract: Ultrasound imaging is a powerful tool for characterizing the state of soft tissues; however, in some cases, where only subtle differences in images are seen as in certain liver lesions such as hemangioma and malignancy, existing B-scan methods are inadequate. More detailed analyses of image texture parameters along with artificial neural networks can be utilized to enhance differentiation. From B-scan ultrasound images, 11 texture parameters comprising of first, second and run length statistics have been obtained for normal, hemangioma and malignant livers. Tissue characterization was then performed using a multilayered backpropagation neural network. The results for 113 cases have been compared with a classification based on discriminant analysis. For linear discriminant analysis, classification accuracy is 79.6% and with neural networks the accuracy is 100%. The present results show that neural networks classify better than discriminant analysis, demonstrating a much potential for clinical application.
Citations
More filters
•
TL;DR: This work provides a concise but all encompassing review of methods that have been adopted in the recent time for development of an EEG classification in BCI.
Abstract: Brain computer interface (BCI) is one of the technologies growing at an exponential rate with its applications extended to medical and non-medical fields. EEG is widely used in BCI for detection and analysis of abnormalities of the brain. EEG is characterized by inherently high temporal resolution and precision, low spatial resolution and specificity plus contains artifacts and redundant or noise information both from the subject and equipment interferences. Thus, feature extraction is a critical issue in translation algorithm development for BCI. Above all, BCI still faces a lot challenges that results in performance variation across and even within subjects. Thus, this work provides a concise but all encompassing review of methods that have been adopted in the recent time for development of an EEG classification in BCI.
8 citations
••
26 Sep 2012
TL;DR: The role that some multiresolution textural features have in improving the liver tumors' diagnosis accuracy is analyzed, and features derived from the second and superior order GLCM and edge-based statistics, all computed after applying the Wavelet transform are added.
Abstract: The malignant tumors are complex structures, which evolve chaotically, invading the entire human body. The gold standard for cancer diagnosis is the biopsy, but this is invasive, dangerous. We elaborated non-invasive, computerized methods, for tumor characterization, based on ultrasound images. We defined the textural model of the malignant tumors, consisting of the relevant textural features, able to distinguish these structures from similar tissues, and of the specific values associated to the relevant features [1]. In this paper, we analyzed the role that some multiresolution textural features have in improving the liver tumors' diagnosis accuracy. In the new attribute set we added features derived from the second and superior order GLCM and edge-based statistics, all computed after applying the Wavelet transform. The experiments were performed on ultrasound images of patients suffering from hepatocellular carcinoma and from benign liver tumors, considering also the aspect of the cirrhotic parenchyma where the tumors evolve.
7 citations
••
25 Oct 2001
TL;DR: The Fuzzy C-Means algorithm is applied and it is revealed that the k-th nearest neighbour method outperforms the other methods; thus discriminating up to 93% of the normal parenchyma and up to 82%" of the hepatocellular carcinoma, correctly.
Abstract: A quantitative study for the discrimination of different hepatic lesions is presented in this paper. The study is based on the fractal analysis of CT liver images in order to estimate their fractal dimension and to differentiate normal liver parenchyma from hepatocellular carcinoma. Four fractal dimension estimators have been implemented throughout this work; three well-established methods and a novel implementation of a method. Analytically, these methods correspond to the power spectrum method, the box counting method, the morphological fractal estimator and the novel modification of the kth-nearest neighbour method. The Fuzzy C-Means algorithm is finally applied revealing that the k-th nearest neighbour method outperforms the other methods; thus discriminating up to 93% of the normal parenchyma and up to 82% of the hepatocellular carcinoma, correctly.
7 citations
••
TL;DR: The classification of ultrasonic liver images is studied by using texture features extracted from Laws' method, Autocorrelation method, Edge frequency methods, Gabor Wavelet method and Co-occurrence probability method to improve the classification.
Abstract: Image analysis techniques have played an important role in several medical applications. In this paper, the classification of ultrasonic liver images is studied by using texture features extracted from Laws' method, Autocorrelation method, Edge frequency methods, Gabor Wavelet method and Co-occurrence probability method. Then the best features from different methods are combined to improve the classification. The features from these methods are used to classify four sets of ultrasonic liver images – Normal, Cyst, Benign and Malignant, and how well they suit in classifying the abnormalities is reported. A Neural Network classifier is employed to evaluate the performance of these features based on their recognition ability.
7 citations
•
16 Oct 2006TL;DR: Specific methods for texture analysis and recognition, for automatic and semi-automatic detection of some liver diseases from ultrasound images, are developed in order to assist the medical personal in establishing a diagnostic in non-invasive way.
Abstract: Non-invasive, image based detection of diseases is one of the most important issues in the nowadays research of biomedical images, because it prevents from some serious problems, that could be generated by the invasive techniques and could be dangerous for the patients. Texture is a fundamental visual property of the tissue providing a lot of information concerning its pathological state. Thus, we developed specific methods for texture analysis and recognition, for automatic and semi-automatic detection of some liver diseases from ultrasound images, in order to assist the medical personal in establishing a diagnostic in non-invasive way. We also performed some studies concerning the relevance of these parameters in the case of various liver diseases.
7 citations
References
More filters
••
01 Nov 1973TL;DR: These results indicate that the easily computable textural features based on gray-tone spatial dependancies probably have a general applicability for a wide variety of image-classification applications.
Abstract: Texture is one of the important characteristics used in identifying objects or regions of interest in an image, whether the image be a photomicrograph, an aerial photograph, or a satellite image. This paper describes some easily computable textural features based on gray-tone spatial dependancies, and illustrates their application in category-identification tasks of three different kinds of image data: photomicrographs of five kinds of sandstones, 1:20 000 panchromatic aerial photographs of eight land-use categories, and Earth Resources Technology Satellite (ERTS) multispecial imagery containing seven land-use categories. We use two kinds of decision rules: one for which the decision regions are convex polyhedra (a piecewise linear decision rule), and one for which the decision regions are rectangular parallelpipeds (a min-max decision rule). In each experiment the data set was divided into two parts, a training set and a test set. Test set identification accuracy is 89 percent for the photomicrographs, 82 percent for the aerial photographic imagery, and 83 percent for the satellite imagery. These results indicate that the easily computable textural features probably have a general applicability for a wide variety of image-classification applications.
20,442 citations
••
TL;DR: This paper provides an introduction to the field of artificial neural nets by reviewing six important neural net models that can be used for pattern classification and exploring how some existing classification and clustering algorithms can be performed using simple neuron-like components.
Abstract: Artificial neural net models have been studied for many years in the hope of achieving human-like performance in the fields of speech and image recognition. These models are composed of many nonlinear computational elements operating in parallel and arranged in patterns reminiscent of biological neural nets. Computational elements or nodes are connected via weights that are typically adapted during use to improve performance. There has been a recent resurgence in the field of artificial neural nets caused by new net topologies and algorithms, analog VLSI implementation techniques, and the belief that massive parallelism is essential for high performance speech and image recognition. This paper provides an introduction to the field of artificial neural nets by reviewing six important neural net models that can be used for pattern classification. These nets are highly parallel building blocks that illustrate neural net components and design principles and can be used to construct more complex systems. In addition to describing these nets, a major emphasis is placed on exploring how some existing classification and clustering algorithms can be performed using simple neuron-like components. Single-layer nets can implement algorithms required by Gaussian maximum-likelihood classifiers and optimum minimum-error classifiers for binary patterns corrupted by noise. More generally, the decision regions required by any classification algorithm can be generated in a straightforward manner by three-layer feed-forward nets.
7,798 citations
•
01 Jan 1974
TL;DR: The objective is to establish an experimental procedure and show direct AFM progression from EMT to EMT using a simple, straightforward, and reproducible procedure.
Abstract: Pathologic basis of disease , Pathologic basis of disease , کتابخانه دیجیتالی دانشگاه علوم پزشکی و خدمات درمانی شهید بهشتی
5,162 citations
••
01 Apr 1976TL;DR: In this paper, three standard approaches to automatic texture classification make use of features based on the Fourier power spectrum, on second-order gray level statistics, and on first-order statistics of gray level differences, respectively.
Abstract: Three standard approaches to automatic texture classification make use of features based on the Fourier power spectrum, on second-order gray level statistics, and on first-order statistics of gray level differences, respectively. Feature sets of these types, all designed analogously, were used to classify two sets of terrain samples. It was found that the Fourier features generally performed more poorly, while the other feature sets all performned comparably.
1,379 citations
••
TL;DR: The gray value distribution of the runs is proposed to be used to define two new features, viz., low gray level run emphasis ( LGRE) and high gray levelrun emphasis ( HGRE).
443 citations