Fernando Vilariño

Towards automatic polyp detection with a polyp appearance model

This work aims at automatic polyp detection by using a model of polyp appearance in the context of the analysis of colonoscopy videos. Our method consists of three stages: region segmentation, region description and region classification. The performance of our region segmentation method guarantees that if a polyp is present in the image, it will be exclusively and totally contained in a single region. The output of the algorithm also defines which regions can be considered as non-informative. We define as our region descriptor the novel Sector Accumulation-Depth of Valleys Accumulation (SA-DOVA), which provides a necessary but not sufficient condition for the polyp presence. Finally, we classify our segmented regions according to the maximal values of the SA-DOVA descriptor. Our preliminary classification results are promising, especially when classifying those parts of the image that do not contain a polyp inside.

Automatic Detection of Intestinal Juices in Wireless Capsule Video Endoscopy

Wireless capsule video endoscopy is a novel and challenging clinical technique, whose major reported drawback relates to the high amount of time needed for video visualization. In this paper, we propose a method for the rejection of the parts of the video resulting not valid for analysis by means of automatic detection of intestinal juices. We applied Gabor filters for the characterization of the bubble-like shape of intestinal juices in fasting patients. Our method achieves a significant reduction in visualization time, with no relevant loss of valid frames. The proposed approach is easily extensible to other image analysis scenarios where the described pattern of bubbles can be found

Predictive (un)distortion model and 3-D reconstruction by biplane snakes

This paper is concerned with the three-dimensional (3-D) reconstruction of coronary vessel centerlines and with how distortion of X-ray angiographic images affects it. Angiographies suffer from pincushion and other geometrical distortions, caused by the peripheral concavity of the image intensifier (II) and the nonlinearity of electronic acquisition devices. In routine clinical practice, where a field-of-view (FOV) of 17-23 cm is commonly used for the acquisition of coronary vessels, this distortion introduces a positional error of up to 7 pixels for an image matrix size of 512/spl times/512 and an FOV of 17 cm. This error increases with the size of the FOV. Geometrical distortions have a significant effect on the validity of the 3-D reconstruction of vessels from these images. We show how this effect can be reduced by integrating a predictive model of (un)distortion into the biplane snakes formulation for 3-D reconstruction. First, we prove that the distortion can be accurately modeled using a polynomial for each view. Also, we show that the estimated polynomial is independent of focal length, but not of changes in anatomical angles, as the II is influenced by the Earths magnetic field. Thus, we decompose the polynomial into two components: the steady and the orientation-dependent component. We determine the optimal polynomial degree for each component, which is empirically determined to be five for the steady component and three for the orientation-dependent component. This fact simplifies the prediction of the orientation-dependent polynomial, since the number of polynomial coefficients to be predicted is lower. The integration of this model into the biplane snakes formulation enables us to avoid image unwarping, which deteriorates image quality and therefore complicates vessel centerline feature extraction. Moreover, we improve the biplane snake behavior when dealing with wavy vessels, by means of using generalized gradient vector flow. Our experiments show that the proposed methods in this paper decrease up to 88% the reconstruction error obtained when geometrical distortion effects are ignored. Tests on imaged phantoms and real cardiac images are presented as well.

ROC curves and video analysis optimization in intestinal capsule endoscopy

Wireless capsule endoscopy involves inspection of hours of video material by a highly qualified professional. Time episodes corresponding to intestinal contractions, which are of interest to the physician constitute about 1% of the video. The problem is to label automatically time episodes containing contractions so that only a fraction of the video needs inspection. As the classes of contraction and non-contraction images in the video are largely imbalanced, ROC curves are used to optimize the trade-off between false positive and false negative rates. Classifier ensemble methods and simple classifiers were examined. Our results reinforce the claims from recent literature that classifier ensemble methods specifically designed for imbalanced problems have substantial advantages over simple classifiers and standard classifier ensembles. By using ROC curves with the bagging ensemble method the inspection time can be drastically reduced at the expense of a small fraction of missed contractions.

Intestinal Motility Assessment With Video Capsule Endoscopy: Automatic Annotation of Phasic Intestinal Contractions

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 SVM classifiers. 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 interobserver variability. Our system performs at 70% of sensitivity for individual detection, whilst obtaining equivalent patterns to those of the experts for density of contractions.

Texture-Based Polyp Detection in Colonoscopy

Colonoscopy is one of the best methods for screening colon cancer. A variety of research groups have proposed methods for automatic detection of polyps in colonoscopic images to support the doctors during examination. However, the problem can still not be assumed as solved. The major drawback of many approaches is the amount and quality of images used for classifier training and evaluation. Our database consists of more than four hours of high resolution video from colonoscopies which were examined and labeled by medical experts. We applied four methods of texture feature extraction based on Grey-Level-Co-occurence and Local-Binary-Patterns. Using this data, we achieved classification results with an area under the ROC-curve of up to 0.96.

Experiments with SVM and stratified sampling with an imbalanced problem: detection of intestinal contractions

In this paper we show some preliminary results of our research in the fieldwork of classification of imbalanced datasets with SVM and stratified sampling. Our main goal is to deal with the clinical problem of automatic intestinal contractions detection in endoscopic video images. The prevalence of contractions is very low, and this yields to highly skewed training sets. Stratified sampling together with SVM have been reported in the literature to behave well in this kind of problems. We applied both the SMOTE algorithm developed by Chawla et al. and under-sampling, in a cascade system implementation to deal with the skewed training sets in the final SVM classifier. We show comparative results for both sampling techniques using precision-recall curves, which appear to be useful tools for performance testing.

Anisotropic feature extraction from endoluminal images for detection of intestinal contractions

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.

Categorization and Segmentation of Intestinal Content Frames for Wireless Capsule Endoscopy

Wireless capsule endoscopy (WCE) is a device that allows the direct visualization of gastrointestinal tract with minimal discomfort for the patient, but at the price of a large amount of time for screening. In order to reduce this time, several works have proposed to automatically remove all the frames showing intestinal content. These methods label frames as {intestinal content - clear} without discriminating between types of content (with different physiological meaning) or the portion of image covered. In addition, since the presence of intestinal content has been identified as an indicator of intestinal motility, its accurate quantification can show a potential clinical relevance. In this paper, we present a method for the robust detection and segmentation of intestinal content in WCE images, together with its further discrimination between turbid liquid and bubbles. Our proposal is based on a twofold system. First, frames presenting intestinal content are detected by a support vector machine classifier using color and textural information. Second, intestinal content frames are segmented into {turbid, bubbles, and clear} regions. We show a detailed validation using a large dataset. Our system outperforms previous methods and, for the first time, discriminates between turbid from bubbles media.

Identification of intestinal motility events of capsule endoscopy video analysis

In this paper we introduce a system for assisting the analysis of capsule-endoscopy (CE) data, and identifying sequences of frames related to small intestine motility. The imbalanced recognition task of intestinal contractions was addressed by employing an efficient two-level video analysis system. At the first level, each video was processed resulting in a number of possible sequences of contractions. In the second level, the recognition of contractions was carried out by means of a SVM classifier. To encode patterns of intestinal motility a panel of textural and morphological features of the intestine lumen were extracted. The system exhibited an overall sensitivity of 73.53% in detecting contractions. The false alarm ratio was of the order of 59.92%. 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.