Active Contours Based Segmentation and Lesion Periphery Analysis For Characterization of Skin Lesions in Dermoscopy Images.

This paper proposes a computer assisted diagnostic (CAD) system for the detection of melanoma in dermoscopy images. Clinical findings have concluded that in case of melanoma, the lesion borders exhibit differential structures such as pigment networks and streaks as opposed to normal skin spots, which have smoother borders. We aim to validate these findings by performing segmentation of the skin lesions followed by an extraction of the peripheral region of the lesion that is subjected to feature extraction and classification for detecting melanoma. For segmentation, we propose a novel active contours based method that takes an initial lesion contour followed by the usage of Kullback-Leibler divergence between the lesion and skin to fit a curve precisely to the lesion boundaries. After segmentation of the lesion, its periphery is extracted to detect melanoma using image features that are based on local binary patterns. For validation of our algorithms, we have used the publicly available PH dermoscopy dataset. An extensive experimental analysis reveals two important findings: 1). The proposed segmentation method mimics the ground truth data accurately, outperforming the other methods that have been used for comparison purposes, and 2). The most significant melanoma characteristics in the lesion actually lie on the lesion periphery.

Virtual M-Mode for Echocardiography: A New Approach for the Segmentation of the Anterior Mitral Leaflet.

Rheumatic heart disease can result from repeated episodes of acute rheumatic fever, which damages the heart valves and reduces their functionality. Early manifestations of heart valve damage are visible in echocardiography in the form of valve thickening, shape changing and mobility reduction. The quantification of these features is important for a precise diagnosis and it is the main motivation for this work. The first step to make this quantification is to accurately identify and track the anterior mitral leaflet throughout the cardiac cycle. An accurate segmentation and tracking with minimum user interaction is still an open problem in literature due to low image quality, speckle noise, signal dropout and nonrigid deformations. In this work, we propose a novel approach for the identification of the anterior mitral valve leaflet in all frames. The method requires a single user-specified point on the posterior wall of the aorta as input, in the first frame. The echocardiography videos are converted into a new image space, the Virtual M-mode, which samples the original echocardiography image over automatically estimated scanning lines. This new image space not only provides the motion pattern of the posterior wall of the aorta, the anterior wall of the aorta and the posterior wall of the left atrium, but also provides the location of the structures in each frame. The location information is then used to initialize the localized active contours, followed by segmenting the anterior mitral leaflet. Results shown that the new image space has robustly identified the anterior mitral valve leaflet, without any failure. The median modified Hausdorff distance error of the proposed method was 2.3 mm, with a recall of 0.94.

A New Method for the Anterior Mitral Leaflet Segmentation in Echocardiography Videos using the Virtual M-mode Space.

Rheumatic heart disease is responsible for the heart valve damage, caused by repeated episodes of rheumatic fever. The disease commonly inflames and scars the mitral valve of the heart, resulting in thicker, less mobile leaflets, with associated decrease in cardiac efficiency. It is important to measure and quantity the early manifestations of this disease, including variations of the thickness, shape and mobility of the leaflets. These manifestations are visible in an echocardiographic screening process. The first step towards the defined objective is to segment the anterior mitral leaflet throughout the cardiac cycle, enabling the future automatic quantification of mentioned clinical parameters. In this work, a new algorithm for the segmentation of the whole region of the anterior mitral leaflet in the virtual M-mode space is proposed. The algorithm requires a single initialization point on the posterior wall of the aorta, in the first frame of the video. A junction point is then computed, showing the location where the two leaflets connect. This junction point helps to automatically redefine the range of virtual M-mode images required to completely segment the region of the anterior mitral leaflet. The segmented anterior mitral leaflet region in the virtual M-mode space is transferred back to regular image space and its shape refined using localized active contours. Results suggest the suitability of the proposed algorithm for the segmentation of anterior mitral leaflet with a median Dice Similarity Coefficient of 0.63, and with median precision and recall of 58% and 73% respectively.

Extracting Thickness Profiles of Anterior Mitral Leaflets in Echocardiography Videos.

Rheumatic heart disease is the serious consequence of repeated episodes of acute rheumatic fever. It is the major cause of heart valve damage resulting in morbidity and mortality. Its early detection is considered vital to control the disease's progression. The key manifestations that are visible in the early stages of this disease are changes in the thickness, shape and mobility of the mitral valve leaflets. Echocardiography based screening is sensitive enough to identify these changes in early stages of the disease. In this work, an automatic approach is proposed to measure, quantify and analyze the thickness of the anterior mitral leaflet, in an echocardiographic video. The shape of the anterior mitral leaflet is simplified via morphological skeletonization and spline modelling to get the central line of the leaflet. To analyze the overall thickness from the tip to its base, the anterior mitral leaflet is divided into four quartiles. In ach quartile the thickness is measured as the length of the line segment resulting from the intersection of the contour with the normal direction of the central point of each quartile. Finally, the thickness is analyzed by measuring the variance per quartile, divided by leaflet position (open, straight and closed). The comparison between the normal and pathological leaflets are also presented, exhibiting statistical significant differences in all quartiles, especially near the tip of the leaflet.

Content-Adaptive Region-Based Color Texture Descriptors for Medical Images.

The design of computer-assisted decision (CAD) systems for different biomedical imaging scenarios is a challenging task in computer vision. Sometimes, this challenge can be attributed to the image acquisition mechanisms since the lack of control on the cameras can create different visualizations of the same imaging site under different rotation, scaling, and illumination parameters, with a requirement to get a consistent diagnosis by the CAD systems. Moreover, the images acquired from different sites have specific colors, making the use of standard color spaces highly redundant. In this paper, we propose to tackle these issues by introducing novel region-based texture, and color descriptors. The proposed texture features are based on the usage of analytic Gabor filters (for compensation of illumination variations) followed by the calculation of first- and second-order statistics of the filter responses and making them invariant using some trivial mathematical operators. The proposed color features are obtained by compensating for the illumination variations in the images using homomorphic filtering followed by a bag-of-words approach to obtain the most typical colors in the images. The proposed features are used for the identification of cancer in images from two distinct imaging modalities, i.e., gastroenterology and dermoscopy . Experiments demonstrate that the proposed descriptors compares favorably to several other state-of-the-art methods, elucidating on the effectiveness of adapted features for image characterization.

An Automatic Subject-Adaptable Heartbeat Classifier Based on Multiview Learning.

In this paper, a novel subject-adaptable heartbeat classification model is presented, in order to address the significant interperson variations in ECG signals. A multiview learning approach is proposed to automate subject adaptation using a small amount of unlabeled personal data, without requiring manual labeling. The designed subject-customized models consist of two models, namely, general classification model and specific classification model. The general model is trained using similar subjects out of a population dataset, where a pattern matching based algorithm is developed to select the subjects that are "similar" to the particular test subject for model training. In contrast, the specific model is trained mainly on a small amount of high-confidence personal dataset, resulting from multiview-based learning. The learned general model represents the population knowledge, providing an interperson perspective for classification, while the specific model corresponds to the specific knowledge of the subject, offering an intraperson perspective for classification. The two models supplement each other and are combined to achieve improved personalized ECG analysis. The proposed methods have been validated on the MIT-BIH Arrhythmia Database, yielding an average classification accuracy of 99.4% for ventricular ectopic beat class and 98.3% for supraventricular ectopic beat class, which corresponds to a significant improvement over other published results.

Integral scale histogram local binary patterns for classification of narrow-band gastroenterology images.

The introduction of various novel imaging technologies such as narrow-band imaging have posed novel image processing challenges to the design of computer assisted decision systems. In this paper, we propose an image descriptor referred to as integrated scale histogram local binary patterns. We propagate an aggregated histogram of local binary patterns of an image at various resolutions. This results in low dimensional feature vectors for the images while incorporating their multiresolution analysis. The descriptor was used to classify gastroenterology images into four distinct groups. Results produced by the proposed descriptor exhibit around 92% accuracy for classification of gastroenteroloy images outperforming other state-of-the-art methods, endorsing the effectiveness of the proposed descriptor.

Impact of visual features on the segmentation of gastroenterology images using normalized cuts.

Gastroenterology imaging is an essential tool to detect gastrointestinal cancer in patients. Computer-assisted diagnosis is desirable to help us improve the reliability of this detection. However, traditional computer vision methodologies, mainly segmentation, do not translate well to the specific visual characteristics of a gastroenterology imaging scenario. In this paper, we propose a novel method for the segmentation of gastroenterology images from two distinct imaging modalities and organs: chromoendoscopy (CH) and narrow-band imaging (NBI) from stomach and esophagus, respectively. We have used various visual features individually and their combinations (edgemaps, creaseness, and color) in normalized cuts image segmentation framework to segment ground truth datasets of 142 CH and 224 NBI images. Experiments show that an integration of edgemaps and creaseness in normalized cuts gives the best segmentation performance resulting in high-quality segmentations of the gastroenterology images.

Invariant Gabor texture descriptors for classification of gastroenterology images.

Automatic classification of lesions for gastroenterology imaging scenarios poses novel challenges to computer-assisted decision systems, which are mostly attributed to the dynamics of the image acquisition conditions. Such challenges demand that automatic systems are able to give robust characterizations of tissues irrespective of camera rotation, zoom, and illumination gradients when viewing the inner surface of the gastrointestinal tract. In this paper, we study the invariance properties of Gabor filters and propose a novel descriptor, the autocorrelation Gabor features (AGF). We show that our proposed AGF is invariant to scale, rotation, and illumination changes in the images. We integrate these new features in a texton framework (Texton-AGF) to classify images from two complementary gastroenterology imaging scenarios (chromoendoscopy and narrow-band imaging) broadly into three different groups: normal, precancerous, and cancerous. Results show that they compare favorably to using state-of-the-art texture descriptors for both imaging modalities.

Heartbeat classification using morphological and dynamic features of ECG signals.

In this paper, we propose a new approach for heartbeat classification based on a combination of morphological and dynamic features. Wavelet transform and independent component analysis (ICA) are applied separately to each heartbeat to extract morphological features. In addition, RR interval information is computed to provide dynamic features. These two different types of features are concatenated and a support vector machine classifier is utilized for the classification of heartbeats into one of 16 classes. The procedure is independently applied to the data from two ECG leads and the two decisions are fused for the final classification decision. The proposed method is validated on the baseline MIT-BIH arrhythmia database and it yields an overall accuracy (i.e., the percentage of heartbeats correctly classified) of 99.3% (99.7% with 2.4% rejection) in the "class-oriented" evaluation and an accuracy of 86.4% in the "subject-oriented" evaluation, comparable to the state-of-the-art results for automatic heartbeat classification.

Customizing the training dataset to an individual for improved heartbeat recognition performance in long-term ECG signals.

This work presents an investigation of the potential benefits of customizing the analysis of long-term ECG signals, collected from individuals using wearable sensors, by incorporating small amount of data from these individuals in the training set of our classifiers. The global training dataset selected was from the MIT-BIH Arrhythmias Database. This proposal is validated on long-term ECG recordings collected via wearable technology in unsupervised environments, as well on the MIT-BIH Normal Sinus Rhythm Database. Results illustrate that heartbeat classification performance could improve significantly if short periods of data (e.g., data from the first 5-minutes of every 2 hours) from the specific individual are regularly selected and incorporated into the global training dataset for training a customized classifier.

Arrhythmia detection and classification using morphological and dynamic features of ECG signals.

Computer-assisted cardiac arrhythmia detection and classification can play a significant role in the management of cardiac disorders. In this paper, we propose a new approach for arrhythmia classification based on a combination of morphological and dynamic features. Wavelet Transform (WT) and Independent Component Analysis (ICA) are applied separately to each heartbeat to extract corresponding coefficients, which are categorized as 'morphological' features. In addition, RR interval information is also obtained characterizing the 'rhythm' around the corresponding heartbeat providing 'dynamic' features. These two different types of features are then concatenated and Support Vector Machine (SVM) is utilized for the classification of heartbeats into 15 classes. The procedure is applied to the data from two ECG leads independently and the two results are fused for the final decision. Compare the two classification results and the classification result is kept if the two are identical or the one with greater classification confidence is picked up if the two are inconsistent. The proposed method was tested over the entire MIT-BIH Arrhythmias Database [1] and it yields an overall accuracy of 99.66% on 85945 heartbeats, better than any other published results.

Quantitative comparison of segmentation methods for in-body images.

In this paper, we present a numerical comparison of how well segmentation algorithms approximate the manual segmentation of gastroenterologists for a set of endoscopic images. Different areas in these images demand different levels of analysis by a clinician and some provide critical information about the patient. Our objective is thus to segment endoscopic images so that the results mimic as closely as possible the areas that were considered relevant by doctors. We focus on a detailed quantitative comparison of two popular segmentation algorithms, mean shift and normalized cuts, when applied to in-body images, most specifically for vital-stained magnification endoscopy. Segmentation results are compared with the manual annotations of the same images performed by two specialist clinicians. Results show that if we simply consider the most relevant segmented patch, normalized cuts performs better. However, if we allow the annotated area to be represented by multiple patches, mean shift is clearly a better choice, although automatic ways to determine its kernel's bandwidth are highly desirable.