Automatic Pleural Line Extraction and COVID-19 Scoring From Lung Ultrasound Data.

Recent works highlighted the significant potential of lung ultrasound (LUS) imaging in the management of subjects affected by COVID-19. In general, the development of objective, fast, and accurate automatic methods for LUS data evaluation is still at an early stage. This is particularly true for COVID-19 diagnostic. In this article, we propose an automatic and unsupervised method for the detection and localization of the pleural line in LUS data based on the hidden Markov model and Viterbi Algorithm. The pleural line localization step is followed by a supervised classification procedure based on the support vector machine (SVM). The classifier evaluates the healthiness level of a patient and, if present, the severity of the pathology, i.e., the score value for each image of a given LUS acquisition. The experiments performed on a variety of LUS data acquired in Italian hospitals with both linear and convex probes highlight the effectiveness of the proposed method. The average overall accuracy in detecting the pleura is 84% and 94% for convex and linear probes, respectively. The accuracy of the SVM classification in correctly evaluating the severity of COVID-19 related pleural line alterations is about 88% and 94% for convex and linear probes, respectively. The results as well as the visualization of the detected pleural line and the predicted score chart, provide a significant support to medical staff for further evaluating the patient condition.

Rayleigh-Rice Mixture Parameter Estimation via EM Algorithm for Change Detection in Multispectral Images.

The problem of estimating the parameters of a Rayleigh-Rice mixture density is often encountered in image analysis (e.g., remote sensing and medical image processing). In this paper, we address this general problem in the framework of change detection (CD) in multitemporal and multispectral images. One widely used approach to CD in multispectral images is based on the change vector analysis. Here, the distribution of the magnitude of the difference image can be theoretically modeled by a Rayleigh-Rice mixture density. However, given the complexity of this model, in applications, a Gaussian-mixture approximation is often considered, which may affect the CD results. In this paper, we present a novel technique for parameter estimation of the Rayleigh-Rice density that is based on a specific definition of the expectation-maximization algorithm. The proposed technique, which is characterized by good theoretical properties, iteratively updates the parameters and does not depend on specific optimization routines. Several numerical experiments on synthetic data demonstrate the effectiveness of the method, which is general and can be applied to any image processing problem involving the Rayleigh-Rice mixture density. In the CD context, the Rayleigh-Rice model (which is theoretically derived) outperforms other empirical models. Experiments on real multitemporal and multispectral remote sensing images confirm the validity of the model by returning significantly higher CD accuracies than those obtained by using the state-of-the-art approaches.

Classification of time series of multispectral images with limited training data.

Image classification usually requires the availability of reliable reference data collected for the considered image to train supervised classifiers. Unfortunately when time series of images are considered, this is seldom possible because of the costs associated with reference data collection. In most of the applications it is realistic to have reference data available for one or few images of a time series acquired on the area of interest. In this paper, we present a novel system for automatically classifying image time series that takes advantage of image(s) with an associated reference information (i.e., the source domain) to classify image(s) for which reference information is not available (i.e., the target domain). The proposed system exploits the already available knowledge on the source domain and, when possible, integrates it with a minimum amount of new labeled data for the target domain. In addition, it is able to handle possible significant differences between statistical distributions of the source and target domains. Here, the method is presented in the context of classification of remote sensing image time series, where ground reference data collection is a highly critical and demanding task. Experimental results show the effectiveness of the proposed technique. The method can work on multimodal (e.g., multispectral) images.

EEG decoding of semantic category reveals distributed representations for single concepts.

Achieving a clearer picture of categorial distinctions in the brain is essential for our understanding of the conceptual lexicon, but much more fine-grained investigations are required in order for this evidence to contribute to lexical research. Here we present a collection of advanced data-mining techniques that allows the category of individual concepts to be decoded from single trials of EEG data. Neural activity was recorded while participants silently named images of mammals and tools, and category could be detected in single trials with an accuracy well above chance, both when considering data from single participants, and when group-training across participants. By aggregating across all trials, single concepts could be correctly assigned to their category with an accuracy of 98%. The pattern of classifications made by the algorithm confirmed that the neural patterns identified are due to conceptual category, and not any of a series of processing-related confounds. The time intervals, frequency bands and scalp locations that proved most informative for prediction permit physiological interpretation: the widespread activation shortly after appearance of the stimulus (from 100 ms) is consistent both with accounts of multi-pass processing, and distributed representations of categories. These methods provide an alternative to fMRI for fine-grained, large-scale investigations of the conceptual lexicon.

A novel technique for subpixel image classification based on support vector machine.

This paper presents a novel support vector machine classifier designed for sub-pixel image classification (pixel/spectral unmixing). The proposed classifier generalizes the properties of SVMs to the identification and modeling of the abundances of classes in mixed pixels by using fuzzy logic. This results in the definition of a fuzzy-input fuzzy-output support vector machine (F2SVM) classifier that can: i) process fuzzy information given as input to the classification algorithm for modeling the sub-pixel information in the learning phase of the classifier, and ii) provide a fuzzy modeling of the classification results, allowing a relation many-to-one between classes and pixels. The presented binary F2SVM can address multicategory problems according to two strategies: the fuzzy one-against-all (FOAA) and the fuzzy one-against-one strategies (FOAO). These strategies generalize to the fuzzy case techniques based on ensembles of binary classifiers used for addressing multicategory problems in crisp classification problems. The effectiveness of the proposed F2SVM classifier is tested on three problems related to image classification in presence of mixed pixels having different characteristics. Experimental results confirm the validity of the proposed sub-pixel classification method.

A context-sensitive technique robust to registration noise for change detection in VHR multispectral images.

This paper presents an automatic context-sensitive technique robust to registration noise (RN) for change detection (CD) in multitemporal very high geometrical resolution (VHR) remote sensing images. Exploiting the properties of RN in VHR images, the proposed technique analyzes the distribution of the spectral change vectors (SCVs) computed according to the change vector analysis (CVA) in a quantized polar domain. The method studies the SCVs falling into each quantization cell at different resolution levels (scales) to automatically identify the effects of RN in the polar domain. This information is jointly exploited with the spatial context information contained in the neighborhood of each pixel for generating the final CD map. The spatial context information is modeled through the definition of adaptive regions homogeneous both in spatial and temporal domain (parcels). Experimental results obtained on real VHR remote sensing multitemporal images confirm the effectiveness of the proposed technique.

An automatic system for the analysis and classification of human atrial fibrillation patterns from intracardiac electrograms.

This paper presents an automatic system for the analysis and classification of atrial fibrillation (AF) patterns from bipolar intracardiac signals. The system is made up of: 1) a feature-extraction module that defines and extracts a set of measures potentially useful for characterizing AF types on the basis of their degree of organization; 2) a feature-selection module (based on the Jeffries-Matusita distance and a branch and bound search algorithm) identifying the best subset of features for discriminating different AF types; and 3) a support vector machine technique-based classification module that automatically discriminates the AF types according to the Wells' criteria. The automatic system was applied on 100 intracardiac AF signal strips and on a selection of 11 representative features, demonstrating: a) the possibility to properly identify the most significant features for the discrimination of AF types; b) higher accuracy (97.7% using the seven most informative features) than the traditional maximum likelihood classifier; and c) effectiveness in AF classification also with few training samples (accuracy = 88.3% with only five training signals). Finally, the system identifies a combination of indices characterizing changes of morphology of atrial activation waves and perturbation of the isoelectric line as the most effective in separating the AF types.