Carlos S. Lima

Detection of small bowel tumors in capsule endoscopy frames using texture analysis based on the discrete wavelet transform

Capsule endoscopy is an important tool to diagnose tumor lesions in the small bowel. The capsule endoscopic images possess vital information expressed by color and texture. This paper presents an approach based in the textural analysis of the different color channels, using the wavelet transform to select the bands with the most significant texture information. A new image is then synthesized from the selected wavelet bands, trough the inverse wavelet transform. The features of each image are based on second-order textural information, and they are used in a classification scheme using a multilayer perceptron neural network. The proposed methodology has been applied in real data taken from capsule endoscopic exams and reached 98.7% sensibility and 96.6% specificity. These results support the feasibility of the proposed algorithm.

Automatic small bowel tumor diagnosis by using multi-scale wavelet-based analysis in wireless capsule endoscopy images

BackgroundWireless capsule endoscopy has been introduced as an innovative, non-invasive diagnostic technique for evaluation of the gastrointestinal tract, reaching places where conventional endoscopy is unable to. However, the output of this technique is an 8 hours video, whose analysis by the expert physician is very time consuming. Thus, a computer assisted diagnosis tool to help the physicians to evaluate CE exams faster and more accurately is an important technical challenge and an excellent economical opportunity.MethodThe set of features proposed in this paper to code textural information is based on statistical modeling of second order textural measures extracted from co-occurrence matrices. To cope with both joint and marginal non-Gaussianity of second order textural measures, higher order moments are used. These statistical moments are taken from the two-dimensional color-scale feature space, where two different scales are considered. Second and higher order moments of textural measures are computed from the co-occurrence matrices computed from images synthesized by the inverse wavelet transform of the wavelet transform containing only the selected scales for the three color channels. The dimensionality of the data is reduced by using Principal Component Analysis.ResultsThe proposed textural features are then used as the input of a classifier based on artificial neural networks. Classification performances of 93.1% specificity and 93.9% sensitivity are achieved on real data. These promising results open the path towards a deeper study regarding the applicability of this algorithm in computer aided diagnosis systems to assist physicians in their clinical practice.

Classification of endoscopic capsule images by using color wavelet features, higher order statistics and radial basis functions

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.

Cardiac Arrhythmia Detection by Parameters Sharing and MMIE Training of Hidden Markov Models

This paper is concerned to the cardiac arrhythmia classification by using hidden Markov models and maximum mutual information estimation (MMIE) theory. The types of beat being selected are normal (N), premature ventricular contraction (V), and the most common class of supra-ventricular arrhythmia (S), named atrial fibrillation (AF). The approach followed in this paper is based on the supposition that atrial fibrillation and normal beats are morphologically similar except that the former does not exhibit the P wave. In fact there are more differences as the irregularity of the RR interval, but ventricular conduction in AF is normal in morphology. Regarding to the Hidden Markov Models (HMM) modelling this can mean that these two classes can be modelled by HMMs of similar topology and sharing some parameters excepting the part of the HMM structure that models the P wave. This paper shows, under that underlying assumption, how this information can be compacted in only one HMM, increasing the classification accuracy by using MMIE training, and saving computational resources at run-time decoding. The algorithm performance was tested by using the MIT-BIH database. Better performance was obtained comparatively to the case where Maximum Likelihood Estimation training is used alone.

Segmentation of small bowel tumor tissue in capsule endoscopy images by using the MAP algorithm

State of the art algorithms for diagnosis of the small bowel by using capsule endoscopic images usually rely on the processing of the whole frame, hence no segmentation is usually required. However, some specific applications such as three-dimensional reconstruction of the digestive wall, detection of small substructures such as polyps and ulcers or training of young medical staff require robust segmentation. Current state of the art algorithms for robust segmentation are mainly based on Markov Random Fields (MRF) requiring prohibitive computational resources not compatible with applications that generate a great amount of data as is the case of capsule endoscopy. However context information given by MRF is not the only way to improve robustness. Alternatives could come from a more effective use of the color information. This paper proposes a Maximum A Posteriori (MAP) based approach for lesion segmentation based on pixel intensities read simultaneously in the three color channels. Usually tumor regions are characterized by higher intensity than normal regions, where the intensity can be measured as the vectorial sum of the 3 color channels. The exception occurs when the capsule is positioned perpendicularly and too close to the small bowel wall. In this case a hipper intense tissue region appears at the middle of the image, which in case of being normal tissue, will be segmented as tumor tissue. This paper also proposes a Maximum Likelihood (ML) based approach to deal with this situation. Experimental results show that tumor segmentation becomes more effective in the HSV than in the RGB color space where diagonal covariance matrices have similar effectiveness than full covariance matrices.

ECG Data-Acquisition and classification system by using wavelet-domain Hidden Markov Models

This article is concerned with the classification of ECG pulses by using state of the art Continuous Density Hidden Markov Models (CDHMMs). The ECG signal is simultaneously observed at three different level of focus by means of the Wavelet Transform (WT). The types of beat being selected are normal (N), premature ventricular contraction (V) which is often precursor of ventricular arrhythmia, two of the most common class of supra-ventricular arrhythmia (S), named atrial fibrillation (AF), atrial flutter (AFL), and normal rhythm (N). Both MLII and V1 derivations are used. Run time classification errors can be detected at the decoding stage if the classification of each derivation is different. These pulses are selected for a posterior physician analysis. Experimental results were obtained in real data from MIT-BIH Arrhythmia Database and also in data acquired from a developed low-cost Data-Acquisition System.

Small bowel tumors detection in capsule endoscopy by Gaussian modeling of Color Curvelet Covariance coefficients

This paper is concerned with the classification of tumoral tissue in the small bowel by using capsule endoscopic images. The followed approach is based on texture classification. Texture descriptors are derived from selected scales of the Discrete Curvelet Transform (DCT). The goal is to take advantage of the high directional sensitivity of the DCT (16 directions) when compared with the Discrete Wavelet Transform (DWT) (3 directions). Second order statistics are then computed in the HSV color space and named Color Curvelet Covariance (3C) coefficients. Finally, these coefficients are modeled by a Gaussian Mixture Model (GMM). Sensitivity of 99% and specificity of 95.19% are obtained in the testing set.

Automatic segmentation of the second cardiac sound by using wavelets and hidden Markov models

This paper is concerned with the segmentation of the second heart sound (S2) of the phonocardiogram (PCG), in its two acoustic events, aortic (A2) and pulmonary (P2) components. The aortic valve (A2) usually closes before the pulmonary valve (P2) and the delay between these two events is known as “split” and is typically less than 30 miliseconds. S2 splitting, reverse splitting or reverse occurrence of components A2 and P2 are the most important aspects regarding cardiac diagnosis carried out by the analysis of S2 cardiac sound. An automatic technique, based on discrete wavelet transform and hidden Markov models, is proposed in this paper to segment S2, to estimate de order of occurrence of A2 and P2 and finally to estimate the delay between these two components (split). A discrete density hidden Markov model (DDHMM) is used for phonocardiogram segmentation while embedded continuous density hidden Markov models are used for acoustic models, which allows segmenting S2. Experimental results were evaluated on data collected from five different subjects, using CardioLab system and a Dash family patient monitor. The ECG leads I, II and III and an electronic stethoscope signal were sampled at 977 samples per second.

Multiscale Texture Descriptors for Automatic Small Bowel Tumors Detection in Capsule Endoscopy

Conventional endoscopic exams do not allow the entire visualization of the gastrointestinal (GI) tract. Push enteroscopy (PE) is an effective diagnostic and therapeutic procedure, although it only allows exploration of the proximal small bowel (Pennazio et al., 1995). Simultaneously, convetional colonoscopy is limited at the terminal ileum. Therefore, prior to the wireless capsule endoscopy era, the small intestine was the conventional endoscopy’s last frontier, because it could not be internally visualized directly or in it’s entirely by any method (Herrerias & Mascarenhas-Saraiva, 2007). The small intestine accounts for 75% of the total length and 90% of the surface area of the gastrointestinal tract. In adults it measures about 570 cm at post mortem, which is substantially longer than conventional video endoscopes (100-180 cm) (Swain & Fritscher-Ravens, 2004). Intraoperative enteroscopy is the most complete but also the most invasive means of examining the small bowel (Gay et al., 1998). Given the technical and medical improvements introduced on the assessment of the gastrointestinal (GI) tract, Capsule Endoscopy (CE) is considered as the first major technological innovation in GI diagnostic medicine since the flexible endoscope (Kaffes, 2009). More recently, a new technique, the double-balloon enteroscopy (DBE), has been introduced into clinical practice (Yamamoto & Kita, 2006). DBE has the potential to examine the entire length of the small bowel with biopsy and therapeutic capability. Nevertheless, it is a time consuming procedure that requires specialist training for the operating physician. We should note that DBE and CE are complementary tools and not competitive (Chen et al., 2007). Hence, the diagnostic ease of CE can be complemented with a targeted and often therapeutic DBE (Kaffes, 2009). Therefore, CE can be used as a first line diagnosis method, while DBE can be used as a confirmatory or therapeutic modality for lesions first visualized by CE (Pennazio, 2006). The endoscopic capsule is a pill-like device, with only 11mm x 26 mm, and includes a miniaturized camera, a light source and circuits for the acquisition and wireless transmission of signals (Iddan et al., 2000). As the capsule moves through GI tract, propelled exclusively by peristalsis, it acquires images at a rate of two per second and sends them to a hard disk receiver that is worn in the belt of the patient, in a wireless communication scheme. The acquisition Multiscale Texture Descriptors for Automatic Small Bowel Tumors Detection in Capsule Endoscopy

Segmentation of angiodysplasia lesions in WCE images using a MAP approach with Markov Random Fields

This paper deals with the segmentation of angiodysplasias in wireless capsule endoscopy images. These lesions are the cause of almost 10% of all gastrointestinal bleeding episodes, and its detection using the available software presents low sensitivity. This work proposes an automatic selection of a ROI using an image segmentation module based on the MAP approach where an accelerated version of the EM algorithm is used to iteratively estimate the model parameters. Spatial context is modeled in the prior probability density function using Markov Random Fields. The color space used was CIELab, specially the a component, which highlighted most these type of lesions. The proposed method is the first regarding this specific type of lesions, but when compared to other state-of-the-art segmentation methods, it almost doubles the results.