9th International Conference on Medical Image Computing and Computer--Assisted Intervention (original) (raw)
Related papers
Anisotropic feature extraction from endoluminal images for detection of intestinal contractions
2006
Wireless endoscopy is a very recent and at the same time unique technique allowing to visualize and study the occurrence of contractions and to analyze the intestine motility. Feature extraction is essential for getting efficient patterns to detect contractions in wireless video endoscopy of small intestine. We propose a novel method based on anisotropic image filtering and efficient statistical classification of contraction features. In particular, we apply the image gradient tensor for mining informative skeletons from the original image and a sequence of descriptors for capturing the characteristic pattern of contractions. Features extracted from the endoluminal images were evaluated in terms of their discriminatory ability in correct classifying images as either belonging to contractions or not. Classification was performed by means of a support vector machine classifier with a radial basis function kernel. Our classification rates gave sensitivity of the order of 90.84% and specificity of the order of 94.43% respectively. These preliminary results highlight the high efficiency of the selected descriptors and support the feasibility of the proposed method in assisting the automatic detection and analysis of contractions.
Contraction detection in small bowel from an image sequence of wireless capsule endoscopy
2007
This paper describes a method for automatic detection of contractions in the small bowel through analyzing Wireless Capsule Endoscopic images. Based on the characteristics of contraction images, a coherent procedure that includes analyzes of the temporal and spatial features is proposed. For temporal features, the image sequence is examined to detect candidate contractions through the changing number of edges and an evaluation of similarities between the frames of each possible contraction to eliminate cases of low probability. For spatial features, descriptions of the directions at the edge pixels are used to determine contractions utilizing a classification method. The experimental results show the effectiveness of our method that can detect a total of 83% of cases. Thus, this is a feasible method for developing tools to assist in diagnostic procedures in the small bowel.
Linear radial patterns characterization for automatic detection of tonic intestinal contractions
2006
This work tackles the categorization of general linear radial patterns by means of the valleys and ridges detection and the use of descriptors of directional information, which are provided by steerable filters in different regions of the image. We successfully apply our proposal in the specific case of automatic detection of tonic contractions in video capsule endoscopy, which represent a paradigmatic example of linear radial patterns.
Cascade analysis for intestinal contraction detection
2006
In this work, we address the study of intestinal contractions in a novel approach based on a machine learning framework to process data from Wireless Capsule Video Endoscopy. Wireless endoscopy represents a unique way to visualize the intestine motility by creating long videos to visualize intestine dynamics. In this paper we argue that to analyze huge amount of wireless endoscopy data and define robust methods for contraction detection we should base our approach on sophisticated machine learning techniques. In particular, we propose a cascade of classifiers in order to remove different physiological phenomenon and obtain the motility pattern of small intestines. Our results show obtaining high specificity and sensitivity rates that highlight the high efficiency of the selected approach and support the feasibility of the proposed methodology in the automatic detection and analysis of intestine contractions.
2010
Intestinal motility assessment with video capsule endoscopy arises as a novel and challenging clinical fieldwork. This technique is based on the analysis of the patterns of intestinal contractions shown in a video provided by an ingestible capsule with a wireless micro-camera. The manual labeling of all the motility events requires large amount of time for offline screening in search of findings with low prevalence, which turns this procedure currently unpractical. In this paper, we propose a machine learning system to automatically detect the phasic intestinal contractions in video capsule endoscopy, driving a useful but not feasible clinical routine into a feasible clinical procedure. Our proposal is based on a sequential design which involves the analysis of textural, color and blob features together with support vector machine classifiers (SVM). Our approach tackles the reduction of the imbalance rate of data and allows the inclusion of domain knowledge as new stages in the cascade. We present a detailed analysis, both in a quantitative and a qualitative way, by providing several measures of performance and the assessment study of inter-observer variability. Our system performs at 70% of sensitivity for individual detection, whilst obtaining equivalent patterns to those of the experts for density of contractions.
Feature extraction from images of endoscopic large intestine
In this paper, we propose feature extraction methods from two types of images of endoscopic large intestine taken by a colonoscopy for diagnosis of colon cancer. Today, there are two observation methods. One is staining surface of large intestine. The other is colonoscopy using Narrow Band Imaging (NBI) system, a new feature of endoscope. We describe extraction methods of features for each observation method so that the features may be used to estimate colon cancer staging from an observed image.Pit pattern is a texture that appears on the surface of stained intestine and they are categorized and used for diagnosis. Thus, we extract pits from an endoscope image to analyze patterns. First, color edge of the image is extracted, then watershed segmentation is applied. In the result, pits are roughly extracted. NBI system can observe vascular structure under the surface of large intestine. The vascular structure can be used to estimate cancer staging. A vascular area is roughly extracted by adaptive binarization, then the fine shape of vascular area is extracted by the level set method
Identification of intestinal motility events of capsule endoscopy video analysis
2005
Purpose: To develop a system for assisting the analysis of capsuleendoscopy (CE) video data and identifying sequences of frames related to small intestine motility. Material and Methods: Six videos were analyzed and labelled manually by an expert, indicating the events of contractions. For addressing the imbalanced recognition task of small intestinal contractions we employed an efficient two-level video analysis system. At the first level of the system, each video was processed resulting in a number of possible sequences of contractions. In the second operating part of the system, the final recognition of contractions sequences was carried out by means of a SVM classification algorithm. To encode the patterns of intestinal motility a panel of textural and morphological features of the intestine lumer were extracted. Results: The system exhibited an overall sensitivity of 73.53% in correct detecting events of contractions. The false alarm ratio (false positives over the true positives) was of the order of 59.92%.Conclusion: these results serve as a first step for developing assisting tools for computer based CE video analysis, reducing drastically the physician's time spent in image evaluation and enhancing the diagnostic potential of CE examination.
Self organized maps for intestinal contractions categorization with wireless capsule video endoscopy
2005
Wireless Capsule Video Endoscopy constitutes a recent technology in which a capsule with micro-camera attached to it is swallowed by the patient, emitting a RF signal which is recorded as a video of its trip throughout the gut. We applied this technology to develop a first approach in intestinal contractions categorization, under the perspective of intestinal motility assessment. In order to automatically cluster the different types of contractions, we designed a computer vision system which describes video sequences in terms of classical image descriptors. We used Self Organized Maps (SOM) to build a two-dimensional representation of the different types of contractions, which were clustered by the SOM in a non-supervised way. In this work, we describe the methodology used, as well as the qualitative results of the visual assessment of this technique using a database of intestinal contractions previously labelled by the specialist in a selected pool of test studios.
2009
Recognizing intestinal contractions from wireless capsule endoscopy (WCE) image sequences provides a non-invasive method of measurement, and suggests a solution to the problems of traditional techniques for assessing intestinal motility. Based on the characteristics of contractile patterns and information on their frequencies, the contractions can be investigated using essential image features extracted from WCE videos. In this study, we proposed a coherent three-stage procedure using temporal and spatial features. The possible contractions are recognized by changes in the edge structure of the intestinal folds in Stage 1 and evaluating similarity features in consecutive frames in Stage 2. In order to take account of the properties of contraction frequency, we consider that the possible contractions are located within windows including consecutive frames. The size of these contraction windows is adjusted according to the passage of the WCE. These procedures aim to exclude as many non-contractions as possible. True contractions are determined through spatial analysis of directional information in Stage 3. Using the proposed method, 81% of true contractions are detected with a 37% false alarm rate for evaluations in the experiments. The overall performance of this method is better than that of previous methods, in terms of both the quality and quantity indices. The results suggest feasible data for further clinical applications.
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.