Chen Kan

Spatiotemporal Differentiation of Myocardial Infarctions

Myocardial infarction (MI), also known as a heart attack, is the leading cause of death in the U.S. It often occurs due to the occlusion of coronary arteries, thereby leading to insufficient blood and oxygen supply that damage cardiac muscle cells. Because blood vessels are branching throughout the heart, MI occurs at different spatial locations (e.g., anterior and inferior portions) of the heart. The spatial location of the diseased is rupts normal excitation and propagation of cardiac electrical activity in space and time. Most previous studies focused on the relationships between disease and time-domain biomarkers from 12-lead ECG signals (e.g., Q wave, QT interval, ST elevation/depression, T wave). Few, if any, previous approaches investigated how the spatial location of diseases will alter cardiac vectorcardiogram (VCG) signals in both space and time. This paper presents a novel spatiotemporal warping approach to quantify the dissimilarity of disease-altered patterns in 3-lead spatiotemporal VCG signals. The hypothesis testing shows that there are significant spatiotemporal differences between healthy control, MI-anterior, MI-anterior-septal, MI-anterior-lateral, MI-inferior, and MI-inferior-lateral. Furthermore, we optimize the embedding of each functional recording as a feature vector in the high-dimensional space that preserves the dissimilarity distance matrix. This novel spatial embedding approach facilitates the construction of classification models and yields an averaged accuracy of 95.1% for separating MIs and Healthy Controls (HCs) and an averaged accuracy of 95.8% in identifying anterior-related MIs and inferior-related MIs.

Mobile sensing and network analytics for realizing smart automated systems towards health Internet of Things

Internet of Things (IoT) provides an unprecedented opportunity to realize smart automated systems such as smart manufacturing, smart city and smart home in the past few years. Pervasive sensing and mobile technology deployed in large-scale IoT systems lead to the accumulation of big data. In particular, wearable biosensing accelerates human-centered computing for smart health management. However, limited work has been done to develop advanced IoT technologies for smart monitoring and control of heart health. There is an urgent need to develop a new IoT technology specific to the heart, namely Internet of Hearts (IOH) that will enable and assist (1) the acquisition of electrocardiogram (ECG) signals pertinent to space-time cardiac dynamics at anytime anywhere; (2) real-time management and compact representation of multi-sensor signals; (3) big data analytics in large-scale IoT contexts. This paper presents a new technology of Mobile and E-Network Smart Health (MESH), which is composed of 4 components as follows: 1) Mobile-based ECG sensing device; 2) Space-time representation of cardiac electrical activity; 3) Optimal model-based representation of ECG signals; 4) Dynamic network embedding for disease pattern recognition. Our preliminary experimental results demonstrated that network analytics is efficient and effective for smart health management in IoT contexts. The MESH technology shows strong potentials to provide an indispensable and enabling tool for realizing smart heart health and wellbeing for the population worldwide.

Dynamic spatiotemporal warping for the detection and location of myocardial infarctions

Myocardial infarction (MI), also known as heart attack, is the leading cause of death - about 452,000 per year - in US. It often occurs due to the occlusion of coronary arteries, thereby leading to the insufficient blood and oxygen supply that damage cardiac muscle cells. Because the blood vessels are all over the heart, MI can happen at different spatial locations (e.g., anterior and inferior portions) of the heart. The spatial location of diseases causes the variable excitation and propagation of cardiac electrical activities in space and time. Most of previous studies focused on the relationships between disease and time-domain biomarkers (e.g., QT interval, ST elevation/depression, heart rate) from 12-lead ECG signals. Few, if any, previous approaches have investigated how the spatial location of diseases will alter cardiac vectorcardiogram (VCG) signals in both space and time. This paper presents a novel warping approach to quantify the dissimilarity of disease-altered patterns in 3-lead spatiotemporal VCG signals. The hypothesis testing shows there are significant spatiotemporal differences between healthy controls (HC), MI-anterior, MI-anterior-septal, MI-anterior-lateral, MI-inferior, and MI-inferior-lateral. Further, we optimize the embedding of each functional recording as a feature vector in the high-dimensional space that preserves the dissimilarity distance matrix. This novel spatial embedding approach facilitates the construction of classification models and yields an accuracy of 94.7% for separating MIs and HCs and an accuracy of 96.5% for anterior-related MIs and inferior-related MIs.

Model-driven parametric monitoring of high-dimensional nonlinear functional profiles

In order to cope with system complexity and dynamic environments, modern industries are investing in a variety of sensor networks and data acquisition systems to increase information visibility. Multi-sensor systems bring the proliferation of high-dimensional functional profiles that capture rich information on the evolving dynamics of natural and engineered processes. This provides an unprecedented opportunity for online monitoring of operational quality and integrity of complex systems. However, the classical methodology of statistical process control is not concerned about high-dimensional sensor signals and is limited in the capability to perform multi-sensor fault diagnostics. It is not uncommon that multi-dimensional sensing capabilities are not fully utilized for decision making. This paper presents a new model-driven parametric monitoring strategy for the detection of dynamic fault patterns in high-dimensional functional profiles that are nonlinear and nonstationary. First, we developed a sparse basis function model of high-dimensional functional profiles, thereby reducing the large amount of data to a parsimonious set of model parameters (i.e., weight, shifting and scaling factors) while preserving the information. Further, we utilized the lasso-penalized logistic regression model to select a low-dimensional set of sensitive predictors for fault diagnostics. Experimental results on real-world data from patient monitoring showed that the proposed methodology outperforms traditional methods and effectively identify a sparse set of sensitive features from high-dimensional datasets for process monitoring and fault diagnostics.

Network models for monitoring high-dimensional image profiles

Modern industries are investing in advanced imaging technology to increase information visibility, address system complexity, and improve quality and integrity of complex systems. The proliferation of high-dimensional images pose significant challenges on traditional and next-generation innovation practices for process monitoring and control in manufacturing and healthcare. Traditional statistical process control (SPC) is not concerned with imaging data but key product or process characteristics, and is limited in its ability to readily address complex structures of high-dimensional imaging profiles. Realizing the full potential of advanced imaging technology for process monitoring and control hinges on the development of new SPC methodologies. This paper presents a novel dynamic network methodology for monitoring and control of high-dimensional imaging streams. Experimental results on biomanufacturing and machining imaging profiles show that the proposed approach not only captures complex image structures but also provides an effective online control charts for monitoring image profiles. New dynamic network monitoring schemes are shown to have strong potentials to be generally applicable to research problems in diverse fields with image profiles.

Two-Phase Greedy Pursuit Algorithm for Automatic Detection and Characterization of Transient Calcium Signaling

Ca 2+ plays an important role in the regulation of cellular functions. Local calcium events, e.g., calcium sparks, not only bring insights into Ca 2+ signaling but also contribute to the understanding of various cellular processes. However, it is challenging to detect calcium sparks, due to their transient properties and high level of nonstationary noises in microscopic images. Most of existing algorithms tend to have limitations for the detection of calcium sparks, e.g., empirically defined hard thresholds or poor applicability to nonstationary conditions. This paper presents a novel two-phase greedy pursuit (TPGP) algorithm for automatic detection and characterization of calcium sparks. In Phase I, a coarse-grained search is conducted across the whole image to identify the predominant sparks. In Phase II, adaptive basis function model is developed for the fine-grained representation of detected sparks. It may be noted that the proposed TPGP algorithms overcome the drawback of hard thresholding in most of previous approaches. Furthermore, the morphology of detected sparks is effectively modeled with multiscale basis functions in Phase II, thereby facilitating the analysis of physiological features. We evaluated and validated the TPGP algorithms using both real-word and synthetic images with multiple noise levels and varying baselines. Experimental results show that TPGP algorithms yield better performances than previous hard-thresholding approaches in terms of both sensitivities and positive predicted values. The present research provides the community a robust tool for the automatic detection and characterization of transient calcium signaling.

Heartbeat sensing and control of the 3D LED cube

Recent advancement of sensing technology has fueled increasing interests in the development of cardiac monitoring systems. However, existing devices are limited in their ability to effectively characterize different disease patterns in a 3D way. An ECG sensing device with high visualizability can assist in the decision-making process of cardiovascular disease treatments. In this undergraduate project, we designed and developed a new device to characterize and visualize single-channel ECG signals in a 3D LED cube. Collected signals are processed using signal processing techniques, e.g., smoothing, gradient, and Laplacian. Processed signals are then used as inputs to control the hue, saturation and brightness of LEDs in a 3D LED cube. As such, disease characteristics of ECG signals are dynamically represented by colored patterns in the LED cube. This device shows strong potentials to increase the visibility and interpretability of information pertinent to the underlying complex cardiac activity.