11th Iberoamerican Congress on Pattern Recognition

Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine, EMBC 2009, 2009

Traditional endoscopic methods do not allow the visualization of the entire Gastrointestinal (GI) tract. Wireless Capsule Endoscopy (CE) is a diagnostic procedure that overcomes this limitation of the traditional endoscopic methods. The CE video frames possess rich information about the condition of the stomach and intestine mucosa, encoded as color and texture patterns. It is known for a long time that human perception of texture is based in a multi-scale analysis of patterns, which can be modeled by multi-resolution approaches. Furthermore, modeling the covariance of textural descriptors has been successfully used in classification of colonoscopy videos. Therefore, in the present paper it is proposed a frame classification scheme based in statistical textural descriptors taken from the Discrete Curvelet Transform domain, a recent multi-resolution mathematical tool, which is based in an anisotropic notion of scale and high directional sensitivity in multiple directions, being therefore suited to characterization of complex patterns as texture.The covariance of texture descriptors taken at a given detail level, at different scales, is used as classification feature, in a scheme designated as Color Curvelet Covariance. The classification step is performed by a multilayer perceptron neural network. The proposed method has been applied in real data taken from several capsule endoscopic exams and reaches 97.2% of sensitivity and 97.4% specificity. These promising results support the feasibility of the proposed method.

2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Vols 1-8, 2008

This paper presents a system to support medical diagnosis and detection of abnormal lesions by processing capsule endoscopic images. Endoscopic images possess rich information expressed by texture. Texture information can be efficiently extracted from medium scales of the wavelet transform. The set of features proposed in this paper to code textural information is named color wavelet covariance (CWC). CWC coefficients are based on the covariances of second order textural measures, an optimum subset of them is proposed. Third and forth order moments are added to cope with distributions that tend to become non-Gaussian, especially in some pathological cases. The proposed approach is supported by a classifier based on radial basis functions procedure for the characterization of the image regions along the video frames. The whole methodology has been applied on real data containing 6 full endoscopic exams and reached 95% specificity and 93% sensitivity.

2010 20th International Conference on Pattern Recognition, 2010

We present a system for an automated colon cancer detection based on the pit pattern classification. In contrast to previous work we exploit the visual nature of the underlying classification scheme by extracting features based on detected edges. To focus on the most discriminative subset of features we use a greedy forward feature subset selection. The classification is then carried out using the k-nearest neighbors (k-NN) classifier.

SPIE Proceedings, 1999

In this paper, we present a review of the research conducted by our group to design an automatic endoscope navigation and advisory system. The whole system can be viewed as a two-layer system. The first layer is at the signal level, which consists of the processing that will be performed on a series of images to extract all the identifiable features. The information is purely dependent on what can be extracted from the 'raw' images. At the signal level, the first task is performed by detecting a single dominant feature, lumen. Few methods of identifying the lumen are proposed. The first method used contour extraction. Contours are extracted by edge detection, thresholding and linking. This method required images to be divided into overlapping squares (8 by 8 or 4 by 4) where line segments are extracted by using a Hough transform. Perceptual criteria such as proximity, connectivity, similarity in orientation, contrast and edge pixel intensity, are used to group edges both strong and weak. This approach is called perceptual grouping. The second method is based on a region extraction using split and merge approach using spatial domain data. An n-level (for a 2 n by 2 n image) quadtree based pyramid structure is constructed to find the most homogenous large dark region, which in most cases corresponds to the lumen. The algorithm constructs the quadtree from the bottom (pixel) level upward, recursively and computes the mean and variance of image regions corresponding to quadtree nodes. On reaching the root, the largest uniform seed region, whose mean corresponds to a lumen is selected that is grown by merging with its neighboring regions.

Neurocomputing, 2014

Finding mucosal abnormalities (e.g., erythema, blood, ulcer, erosion, and polyp) is one of the most essential tasks during endoscopy video review. Since these abnormalities typically appear in a small number of frames (around 5% of the total frame number), automated detection of frames with an abnormality can save physician's time significantly. In this paper, we propose a new multi-texture analysis method that effectively discerns images showing mucosal abnormalities from the ones without any abnormality since most abnormalities in endoscopy images have textures that are clearly distinguishable from normal textures using an advanced image texture analysis method. The method uses a "texton histogram" of an image block as features. The histogram captures the distribution of different "textons" representing various textures in an endoscopy image. The textons are representative response vectors of an application of a combination of Leung and Malik (LM) filter bank (i.e., a set of image filters) and a set of Local Binary Patterns on the image. Our experimental results indicate that the proposed method achieves 92% recall and 91.8% specificity on wireless capsule endoscopy (WCE) images and 91% recall and 90.8% specificity on colonoscopy images.

2001

Video processing for classification purposes in medical imaging is an area with great importance. In this paper a framework for classification of suspicious lesions using the video produced during an endoscopic session is presented. The proposed approach is based on a feature extraction scheme that uses second order statistical information of the wavelet transformation. These features are used as input to a Multilayer Feedforward Neural Network (MFNN) architecture, which has been trained using features of normal and tumor regions. The system uses a limited number of frames with a rather small population of training vectors. The classification results are promising, since the system has been proven capable to classify and locate regions, that correspond to lesions with a success of 94 up to 99%, in a sequence of the video-frames. The proposed methodology can be used as a valuable diagnostic tool that may assist physicians to identify possible tumor regions or malignant formations.

Lecture Notes in Computer Science, 2010

In this work we present a method for an automated classification of endoscopic images according to the pit pattern classification scheme. Images taken during colonoscopy are transformed using an extended and rotation invariant version of the Local Binary Patterns operator (LBP). The result of the transforms is then used to extract polygons from the images. Based on these polygons we compute the regularity of the polygon positions by using the Delaunay triangulation and constructing histograms from the edge lengths of the Delaunay triangles. Using these histograms, the classification is carried out by employing the k-nearest-neighbors (k-NN) classifier in conjunction with the histogram intersection distance metric. While, compared to previously published results, the performance of the proposed approach is lower, the results achieved are yet promising and show that a pit pattern classification is feasible by using the proposed system.

International Journal of Computer Science & …

Endoscopic images do not contain sharp edges to segment using the traditional segmentation methods for obtaining edges. Therefore, the active contours or ‘snakes’ using level set method with the energy minimization algorithm is adopted here to segment these images. The results obtained from the above segmentation process will be number of segmented regions. The boundary of each region is considered as a curve for further processing. The curvature for each point of this curve is computed considering the support region of each point. The possible presence of abnormality is identified, when curvature of the contour segment between two zero crossings has the opposite curvature signs to those of such neighboring contour segments on the same edge contours. The Knearest neighbor classifier is used to classify the images as normal or abnormal. The experiment based on the proposed method is carried out on 50 normal and 50 abnormal endoscopic images and the results are encouraging.

Computers in Biology and Medicine, 2006

Today 95% of all gastrointestinal carcinomas are believed to arise from adenomas. The early detection of adenomas could prevent their evolution to cancer. A novel system for the support of the detection of adenomas in gastrointestinal video endoscopy is presented. Unlike other systems, it accepts standard low-resolution video input thus requiring less computational resources and facilitating both portability and the potential to be used in telemedicine applications. It combines intelligent processing techniques of SVMs and color-texture analysis methodologies into a sound pattern recognition framework. Concerning the system's accuracy this was measured using ROC analysis and found to exceed 94%.

2001

Video processing for classification purposes in medical imaging is an area with great importance. In this paper a framework for classification of suspicious lesions using the video produced during an endoscopic session is presented. The proposed approach is based on a feature extraction scheme that uses second order statistical information of the wavelet transformation. These features are used as input to a Multilayer Feedforward Neural Network (MFNN) architecture, which has been trained using features of normal and tumor regions. The system uses a limited number of frames with a rather small population of training vectors. The classification results are promising, since the system has been proven capable to classify and locate regions, that correspond to lesions with a success of 94 up to 99%, in a sequence of the video-frames. The proposed methodology can be used as a valuable diagnostic tool that may assist physicians to identify possible tumor regions or malignant formations.