Search

Objective: Surgical activity recognition is a fundamental step in computer-assisted interventions. This paper reviews the state-of-the-art in methods for automatic recognition of fine-grained gestures in robotic surgery focusing on recent data-driven approaches and outlines the open questions and future research directions. Methods: An article search was performed on 5 bibliographic databases with the following search terms: robotic, robot-assisted, JIGSAWS, surgery, surgical, gesture, fine-grained, surgeme, action, trajectory, segmentation, recognition, parsing. Selected articles were classified based on the level of supervision required for training and divided into different groups representing major frameworks for time series analysis and data modelling. Results: A total of 52 articles were reviewed. The research field is showing rapid expansion, with the majority of articles published in the last 4 years. Deep-learning-based temporal models with discriminative feature extraction and multi-modal data integration have demonstrated promising results on small surgical datasets. Currently, unsupervised methods perform significantly less well than the supervised approaches. Conclusion: The development of large and diverse open-source datasets of annotated demonstrations is essential for development and validation of robust solutions for surgical gesture recognition. While new strategies for discriminative feature extraction and knowledge transfer, or unsupervised and semi-supervised approaches, can mitigate the need for data and labels, they have not yet been demonstrated to achieve comparable performance. Important future research directions include detection and forecast of gesture-specific errors and anomalies. Significance: This paper is a comprehensive and structured analysis of surgical gesture recognition methods aiming to summarize the status of this rapidly evolving field. [ABSTRACT FROM AUTHOR]

The muscle synergy hypothesis assumes that the nervous system controls muscles in groups to simplify behavioral tasks, which makes it possible for modularizing motor function assessment. This paper presents a new assessment method based on muscle synergy space (MSS) model to evaluate motor functions after stroke. It consists of spatiotemporal feature module, muscle activation module and synergy activation module, and focuses on the spatial and temporal characteristics of muscle synergies via synergy vectors and activation coefficients. We further applied this method to reveal spatial and temporal characteristics difference of muscle synergy between healthy controls and stroke patients. The effectiveness and accuracy of MSS model were proved by significant positive correlations between Fugl-Meyer score and the total number of optimal synergies of three modules. This measurement methodology could serve as a quantitative indicator for motor function and provide more scientific rehabilitation guidance. [ABSTRACT FROM AUTHOR]

Objective: Parkinson’s Disease (PD) is a progressive neurodegenerative disorder, manifesting with subtle early signs, which, often hinder timely and early diagnosis and treatment. The development of accessible, technology-based methods for longitudinal PD symptoms tracking in daily living, offers the potential for transforming disease assessment and accelerating diagnosis. Methods: A privacy-aware method for classifying patients and healthy controls (HC), on the grounds of speech impairment present in PD, is proposed. Voice features from running speech signals were extracted from passively-captured recordings over voice calls. Language-aware training of multiple- and single-instance learning classifiers was employed to fuse and predict on voice features and demographic data from a multilingual cohort of 498 subjects (392/106 self-reported HC/PD patients). Results: By means of leave-one-subject-out cross-validation, the best-performing models yielded 0.69/0.68/0.63/0.83 area under the Receiver Operating Characteristic curve (AUC) for the binary classification of PD patient vs. HC in sub-cohorts of English/Greek/German/Portuguese-speaking subjects, respectively. Out-of sample testing of the best performing models was conducted in an additional dataset, generated by 63 clinically-assessed subjects (24/39 HC/early PD patients). Testing has resulted in 0.84/0.93/0.83 AUC for the English/Greek/German-speaking sub-cohorts, respectively. Conclusions: The proposed approach outperforms other methods proposed for language-aware PD detection considering the ecological validity of the voice data. Significance: This paper introduces for the first time a high-frequency, privacy-aware and unobtrusive PD screening tool based on analysis of voice samples captured during routine phone calls. [ABSTRACT FROM AUTHOR]

Objective: Despite numerous neural computational models proposed to explain physiological and pathological mechanisms of brain activity, a large gap remains between theory and application of the models. Building on the successful application of data-driven methods in epileptic seizure detection, we aim to build a bridge between data and models in this paper. Methods: We first propose a novel model-driven seizure detection method based on dynamic features in epileptic EEGs, where the rationale for dynamic features in epileptic EEGs can be clarified in theory by characterizing the variation of parameters of the model. Then we apply the proposed D&F-model-driven method to the problem of early epileptic seizure detection, where the evolution of model parameters selected and optimized by the proposed method is measured and used to detect the starting point of the seizure. Results: Numerical results on two open EEG databases demonstrate that our proposed method does a good job of early epileptic seizure detection. The average detection sensitivity, false positive rate and early detection period attain 100%, 0.1/h, and 7.1 s respectively. Conclusion: This paper provides a strategy to characterize EEG signals using a NMM-related method and the model parameters optimized by real EEG may then serve as features in their own right for early seizure detection. Significance: An useful attempt to early detect epileptic seizures by combining the neural mass model with data analysis. [ABSTRACT FROM AUTHOR]

Brain functional connectivity network (FCN) based on resting-state functional magnetic resonance imaging (rs-fMRI) has been widely used to identify neuropsychiatric disorders such as autism spectrum disorder (ASD). Most existing FCN-based methods only estimate the correlation between brain regions of interest (ROIs), without exploring more informative higher-level interactions among multiple ROIs which could be beneficial to disease diagnosis. To fully explore the discriminative information provided by different brain networks, a cluster-based multi-view high-order FCN (Ho-FCN) framework is proposed in this paper. Specifically, we first group the functional connectivity (FC) time series into different clusters and compute the multi-order central moment series for the FC time series in each cluster. Then we utilize the correlation of central moment series between different clusters to reveal the high-order FC relationships among multiple ROIs. In addition, to address the phase mismatch issue in conventional FCNs, we also adopt the central moments of the correlation time series as the temporal-invariance features to capture the dynamic characteristics of low-order dynamic FCN (Lo-D-FCN). Experimentalresults on the ABIDE dataset validate that: 1) the proposed multi-view Ho-FCNs is able to explore rich discriminative information for ASD diagnosis; 2) the phase mismatch issue can be well circumvented by using central moments; and 3) the combination of different types of FCNs can significantly improve the diagnostic accuracy of ASD (86.2%). [ABSTRACT FROM AUTHOR]

Breast histology image classification is a crucial step in the early diagnosis of breast cancer. In breast pathological diagnosis, Convolutional Neural Networks (CNNs) have demonstrated great success using digitized histology slides. However, tissue classification is still challenging due to the high visual variability of the large-sized digitized samples and the lack of contextual information. In this paper, we propose a novel CNN, called Multi-level Context and Uncertainty aware (MCUa) dynamic deep learning ensemble model. MCUa model consists of several multi-level context-aware models to learn the spatial dependency between image patches in a layer-wise fashion. It exploits the high sensitivity to the multi-level contextual information using an uncertainty quantification component to accomplish a novel dynamic ensemble model. MCUa model has achieved a high accuracy of 98.11% on a breast cancer histology image dataset. Experimental results show the superior effectiveness of the proposed solution compared to the state-of-the-art histology classification models. [ABSTRACT FROM AUTHOR]

This paper addresses an interesting problem to model common spatial pattern (CSP) using an objective function employed to segregate EEG signals for a given cognitive task into two classes. The novelty of the present research is to include phase information of the EEG signal along with the amplitude for differentiating class boundaries. Two modified CSP algorithms are proposed in this paper. The first one introduces the composite effect of amplitude and phase angle of the EEG signal in CSP formulation and is solved using Lagrange’s multiplier method taking phase information of EEG into account. In the second approach, a novel CSP algorithm is proposed in this paper which has the efficacy of handling the non-linearities hidden in the brain signal, here EEG. Experiments undertaken confirm that the proposed phase-sensitive CSP yields the best performance than their non-phase sensitive counterparts by a large margin with respect to classification accuracy. [ABSTRACT FROM AUTHOR]

Objective: Preterm birth is the first cause of perinatal morbidity and mortality. Despite continuous clinical routine improvements, the preterm rate remains steady. Moreover, the specificity of the early diagnosis stays poor as many hospitalized women for preterm delivery threat finally deliver at term. In this context, the use of electrohysterograms may increase the sensitivity and the specificity of early diagnosis of preterm labor. Methods: This paper proposes a clinical application of electrohysterogram processing for the classification of patients as prone to deliver within a week or later. The approach relies on non-linear correlation analysis for the contraction bursts extraction and uses computation of various features combined with the use of Gaussian mixture models for their classification. The method is tested on a new dataset of 68 records collected on women hospitalized for preterm delivery threat. Results: This paper presents promising results for the automatic segmentation of the contraction and a classification sensitivity, specificity, and accuracy of, respectively, 80.7%, 76.3%, and 76.2%. Conclusion: These results are in accordance with the gold standards but have the advantage to be non-invasive and could be performed at home. Significance: Diagnosis of imminent labor is possible by electrohysterography recording and may help in avoiding over-medication and in providing better cares to at-risk pregnant women. [ABSTRACT FROM AUTHOR]

Objective: Multi-modal brain functional connectivity (FC) data have shown great potential for providing insights into individual variations in behavioral and cognitive traits. The joint learning of multi-modal data can utilize intrinsic association, and thus can boost learning performance. Although several multi-task based learning models have already been proposed by viewing feature learning on each modality as one task, most of them ignore the structural information inherent across the modalities, which may play an important role in extracting discriminative features. Methods: In this paper, we propose a new manifold regularized multi-task learning model by simultaneously considering between-subject and between-modality relationships. Specifically, the $l_{2,1}$ -norm (i.e., group-sparsity) regularizer is enforced to jointly select a few common features across different modalities. A novelly designed manifold regularizer is further imposed as a crucial underpinning to preserve the structural information both within and between modalities. Such designed regularizers will make our model more adaptive to realistic neuroimaging data, which are usually of small sample size but high dimensional features. Results: Our model is validated on the Philadelphia Neurodevelopmental Cohort dataset, where our modalities are regarded as two types of functional MRI (fMRI) data collected under two paradigms. We conduct experimental studies on fMRI-based FC network data in two task conditions for intelligence quotient (IQ) prediction. The results show that our proposed model can not only achieve improved prediction performance, but also yield a set of IQ-relevant biomarkers. Conclusion and Significance: This paper develops a new multi-task learning model, enabling the discovery of significant biomarkers that may account for a proportion of the variance in human intelligence. [ABSTRACT FROM AUTHOR]

Objective: This paper describes how non-invasive wearable sensors can be used in combination with deep learning to classify artificially induced gait alterations without the requirement for a medical professional or gait analyst to be present. This approach is motivated by the goal of diagnosing gait abnormalities on a symptom-by-symptom basis, irrespective of other neuromuscular movement disorders the patients may be affected by. This could lead to improvements in treatment and offer a greater insight into movement disorders. Methods: In-shoe pressure was measured for 12 able-bodied participants, each subject to eight artificially induced gait alterations, achieved by modifying the underside of the shoe. The data were recorded at 100 Hz over 2520 data channels and were analyzed using the deep learning architecture and the long term short term memory networks. Additionally, the rationale for the decision-making process of these networks was investigated. Conclusion: Long term short term memory networks are applicable to the classification of the gait function. The classifications can be made using only 2 s of sparse data (82.0% accuracy over 96 000 instances of test data) from participants who were not a part of the training set. Significance: This paper provides potential for the gait function to be accurately classified using non-invasive techniques, and at more regular intervals, outside of a clinical setting, without the need for healthcare professionals to be present. [ABSTRACT FROM AUTHOR]

Seizure prediction for drug-refractory epilepsy patients can improve their quality of life, reduce their anxiety, and help them take the necessary precautions. Nowadays, numerous deep learning algorithms have been proposed to predict seizure onset and obtain better performance than traditional machine learning methods. However, these methods require a large set of parameters and large hardware resources; they also have high energy consumption. Therefore, these methods cannot be implemented on compact, low-power wearable, or implantable medical devices. The devices should operate on a real-time basis to continually inform the epileptic patients. In this paper, we describe energy-efficient and hardware-friendly methods to predict the epileptic seizures. A model of only 45 kB was obtained by the neural architecture search and was evaluated across three datasets. The overall sensitivity, false prediction rate, and area under receiver operating characteristic curve were 99.81%, 0.005/h, 1 and 93.48%, 0.063/h, 0.977 and 85.19%, 0.116/h, 0.933, respectively, for three public datasets. This model was further reduced with several methods for model compression. The performances for the model sizes less than 50 kB for scalp EEG data and less than 10 kB for intracranial EEG data outperformed all the other models of similar model sizes. In particular, the energy consumption estimation was less than 10 mJ per inference for scalp EEG signal and less than 0.5 mJ per inference for intracranial EEG signal, which meet the requirements for low-power wearable and implantable devices, respectively. [ABSTRACT FROM AUTHOR]

Objective: Pain assessment in children continues to challenge clinicians and researchers, as subjective experiences of pain require inference through observable behaviors, both involuntary and deliberate. The presented approach supplements the subjective self-report-based method by fusing electrodermal activity (EDA) recordings with video facial expressions to develop an objective pain assessment metric. Such an approach is specifically important for assessing pain in children who are not capable of providing accurate self-pain reports, requiring nonverbal pain assessment. We demonstrate the performance of our approach using data recorded from children in post-operative recovery following laparoscopic appendectomy. We examined separately and combined the usefulness of EDA and video facial expression data as predictors of children's self-reports of pain following surgery through recovery. Findings indicate that EDA and facial expression data independently provide above chance sensitivities and specificities, but their fusion for classifying clinically significant pain vs. clinically nonsignificant pain achieved substantial improvement, yielding 90.91% accuracy, with 100% sensitivity and 81.82% specificity. The multimodal measures capitalize upon different features of the complex pain response. Thus, this paper presents both evidence for the utility of a weighted maximum likelihood algorithm as a novel feature selection method for EDA and video facial expression data and an accurate and objective automated classification algorithm capable ofdiscriminating clinically significant pain from clinically nonsignificant pain in children. [ABSTRACT FROM AUTHOR]

Objective: Wearable systems that enable continuous non-invasive monitoring of hemodynamic parameters can aid in cardiac health evaluation in non-hospital settings. The seismocardiogram (SCG) is a non-invasively acquired cardiovascular biosignal for which timings of fiducial points, like aortic valve opening (AO) and aortic valve closing (AC), can enable estimation of key hemodynamic parameters. However, SCG is susceptible to motion artifacts, making accurate estimation of these points difficult when corrupted by high-g or in-band vibration artifacts. In this paper, a novel denoising pipeline is proposed that removes vehicle-vibration artifacts from corrupted SCG beats for accurate fiducial point detection. Methods: The noisy SCG signal is decomposed with ensemble empirical mode decomposition (EEMD). Corrupted segments of the decomposed signal are then identified and removed using the quasi-periodicity of the SCG. Signal quality assessment of the reconstructed SCG beats then removes unreliable beats before feature extraction. The overall approach is validated on simulated vehicle-corrupted SCG generated by adding real subway collected vibration signals onto clean SCG. Results: SNR increased by 8.1dB in the AO complex and 11.5dB in the AC complex of the SCG signal. Hemodynamic timing estimation errors reduced by 16.5% for pre-ejection period (PEP), 67.2% for left ventricular ejection time (LVET), and 57.7% for PEP/LVET—a feature previously determined in prior work to be of great importance for assessing blood volume status during hemorrhage. Conclusion: These findings suggest that usable SCG signals can be recovered from vehicle-corrupted SCG signals using the presented denoising framework, allowing for accurate hemodynamic timing estimation. Significance: Reliable hemodynamic estimates from vehicle-corrupted SCG signals will enable the adoption of the SCG in outside-of-hospital settings. [ABSTRACT FROM AUTHOR]

Objective: The speed of sound (SoS) has great potential as a quantitative imaging biomarker since it is sensitive to pathological changes in tissues. In this paper, a target-aware deep neural (TAD) network reconstructing an SoS image quantitatively from pulse-echo phase-shift maps gathered from a single conventional ultrasound probe is presented. Methods: In the proposed TAD network, the reconstruction process is guided by feature maps created from segmented target images for accuracy and contrast. In addition, the feature extraction process utilizes phase difference information instead of direct pulse-echo radio frequency (RF) data for robust image reconstruction against noise in the pulse-echo data. Results: The TAD network outperforms the fully convolutional network in root mean square error (RMSE), contrast-to-noise ratio (CNR), and structural similarity index (SSIM) in the presence of nearby reflectors. The measured RMSE and CNR are 5.4 m/s and 22 dB, respectively with the tissue attenuation coefficient of 2 dB/cm/MHz, which are 72% and 13 dB improvement over the state of the art design in RMSE and CNR, respectively. In the in-vivo test, the proposed method classifies the tissues in the neck area using SoS with a p-value below 0.025. Conclusion: The proposed TAD network is the most accurate and robust single-probe SoS image reconstruction method reported to date. Significance: The accuracy and robustness demonstrated by the proposed SoS imaging method open up the possibilities of wide-spread clinical application of the single-probe SoS imaging system. [ABSTRACT FROM AUTHOR]

Reducing radiation dose in cardiac catheter-based X-ray procedures increases safety but also image noise and artifacts. Excessive noise and artifacts can compromise vital image information, which can affect clinical decision-making. Developing more effective X-ray denoising methodologies will be beneficial to both patients and healthcare professionals by allowing imaging at lower radiation dose without compromising image information. This paper proposes a framework based on a convolutional neural network (CNN), namely Ultra-Dense Denoising Network (UDDN), for low-dose X-ray image denoising. To promote feature extraction, we designed a novel residual block which establishes a solid correlation among multiple-path neural units via abundant cross connections in its representation enhancement section. Experiments on synthetic additive noise X-ray data show that the UDDN achieves statistically significant higher peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) than other comparative methods. We enhanced the clinical adaptability of our framework by training using normally-distributed noise and tested on clinical data taken from procedures at St. Thomas’ hospital in London. The performance was assessed by using local SNR and by clinical voting using ten cardiologists. The results show that the UDDN outperforms the other comparative methods and is a promising solution to this challenging but clinically impactful task. [ABSTRACT FROM AUTHOR]

Arrhythmia detection and classification is a crucial step for diagnosing cardiovascular diseases. However, deep learning models that are commonly used and trained in end-to-end fashion are not able to provide good interpretability. In this paper, we address this deficiency by proposing the first novel interpretable arrhythmia classification approach based on a human-machine collaborative knowledge representation. Our approach first employs an AutoEncoder to encode electrocardiogram signals into two parts: hand-encoding knowledge and machine-encoding knowledge. A classifier then takes as input the encoded knowledge to classify arrhythmia heartbeats with or without human in the loop (HIL). Experiments and evaluation on the MIT-BIH Arrhythmia Database demonstrate that our new approach not only can effectively classify arrhythmia while offering interpretability, but also can improve the classification accuracy by adjusting the hand-encoding knowledge with our HIL mechanism. [ABSTRACT FROM AUTHOR]

Objective: Croup, a respiratory tract infection common in children, causes an inflammation of the upper airway restricting normal breathing and producing cough sounds typically described as seallike “barking cough.” Physicians use the existence of barking cough as the defining characteristic of croup. This paper aims to develop automated cough sound analysis methods to objectively diagnose croup. Methods: In automating croup diagnosis, we propose the use of mathematical features inspired by the human auditory system. In particular, we utilize the cochleagram for feature extraction, a time-frequency representation where the frequency components are based on the frequency selectivity property of the human cochlea. Speech and cough share some similarities in the generation process and physiological wetware used. As such, we also propose the use of mel-frequency cepstral coefficients which has been shown to capture the relevant aspects of the short-term power spectrum of speech signals. Feature combination and backward sequential feature selection are also experimented with. Experimentation is performed on cough sound recordings from patients presenting various clinically diagnosed respiratory tract infections divided into croup and non-croup. The dataset is divided into training and test sets of 364 and 115 patients, respectively, with automatically segmented cough sound segments. Results: Croup and non-croup patient classification on the test dataset with the proposed methods achieve a sensitivity and specificity of 92.31% and 85.29%, respectively. Conclusion: Experimental results show the significant improvement in automatic croup diagnosis against earlier methods. Significance: This paper has the potential to automate croup diagnosis based solely on cough sound analysis. [ABSTRACT FROM AUTHOR]

Evaluating progress throughout a patient's rehabilitation episode is critical for determining the effectiveness of the selected treatments and is an essential ingredient in personalised and evidence-based rehabilitation practice. The evaluation process is complex due to the inherently large human variations in motor recovery and the limitations of commonly used clinical measurement tools. Information recorded during a robot-assisted rehabilitation process can provide an effective means to continuously quantitatively assess movement performance and rehabilitation progress. However, selecting appropriate motion features for rehabilitation evaluation has always been challenging. This paper exploits unsupervised feature learning techniques to reduce the complexity of building the evaluation model of patients’ progress. A new feature learning technique is developed to select the most significant features from a large amount of kinematic features measured from robotics, providing clinically useful information to health practitioners with reduction of modeling complexity. A novel indicator that uses monotonicity and trendability is proposed to evaluate kinematic features. The data used to develop the feature selection technique consist of kinematic data from robot-aided rehabilitation for a population of stroke patients. The selected kinematic features allow for human variations across a population of patients as well as over the sequence of rehabilitation sessions. The study is based on data records pertaining to 41 stroke patients using three different robot assisted exercises for upper limb rehabilitation. Consistent with the literature, the results indicate that features based on movement smoothness are the best measures among 17 kinematic features suitable to evaluate rehabilitation progress. [ABSTRACT FROM AUTHOR]

Objective: Detection of Atrial fibrillation (AF) from premature atrial contraction (PAC) and premature ventricular contraction (PVC) is difficult as frequent occurrences of these ectopic beats can mimic the typical irregular patterns of AF. In this paper, we present a novel density Poincaré plot-based machine learning method to detect AF from PAC/PVCs using electrocardiogram (ECG) recordings. Methods: First, we propose the generation of this new density Poincaré plot which is derived from the difference of the heart rate (DHR) and provides the overlapping phase-space trajectory information of the DHR. Next, from this density Poincaré plot, several image processing domain-based approaches including statistical central moments, template correlation, Zernike moment, discrete wavelet transform and Hough transform features are used to extract suitable features. Subsequently, the infinite latent feature selection algorithm is implemented to rank the features. Finally, classification of AF vs. PAC/PVC is performed using K-Nearest Neighbor, Support vector machine (SVM) and Random Forest (RF) classifiers. Our method is developed and validated using a subset of Medical Information Mart for Intensive Care (MIMIC) III database containing 10 AF and 10 PAC/PVC subjects. Results- During the segment-wise 10-fold cross-validation, SVM achieved the best performance with 98.99% sensitivity, 95.18% specificity and 97.45% accuracy with the extracted features. In subject-wise scenario, RF achieved the highest accuracy of 91.93%. Moreover, we further validated the proposed method using two other databases: wearable armband ECG data and the Physionet AFPDB. 100% PAC detection accuracy was obtained for both databases without any further training. Conclusion: Our proposed density Poincaré plot-based method showed superior performance when compared with four existing algorithms; thus showing the efficacy of the extracted image domain-based features. Significance: From intensive care unit's ECG to wearable armband ECGs, the proposed method is shown to discriminate PAC/PVCs from AF with high accuracy. [ABSTRACT FROM AUTHOR]

Objective: in this paper we propose a system to detect a subject's sympathetic reaction, which is related to unexpected or challenging events during a car drive. Methods: we use the Electrocardiogram (ECG) signal and the Skin Potential Response (SPR) signal, which has several advantages with respect to other Electrodermal (EDA) signals. We record one SPR signal for each hand, and use an algorithm that, selecting the smoother signal, is able to remove motion artifacts. We extract statistical features from the ECG and SPR signals in order to classify signal segments and identify the presence or absence of emotional events via a Supervised Learning Algorithm. The experiments were carried out in a company which specializes in driving simulator equipment, using a motorized platform and a driving simulator. Different subjects were tested with this setup, with different challenging events happening on predetermined locations on the track. Results: we obtain an Accuracy as high as 79.10% for signal blocks and as high as 91.27% for events. Conclusion: results demonstrate the good performance of the presented system in detecting sympathetic reactions, and the effectiveness of the motion artifact removal procedure. Significance: our work demonstrates the possibility to classify the emotional state of the driver, using the ECG and EDA signals and a slightly invasive setup. In particular, the proposed use of SPR and of the motion artifact removal procedure are crucial for the effectiveness of the system. [ABSTRACT FROM AUTHOR]

Objective: This paper proposes a novel method to localize origins of premature ventricular contractions (PVCs) from 12-lead electrocardiography (ECG) using convolutional neural network (CNN) and a realistic computer heart model. Methods: The proposed method consists of two CNNs (Segment CNN and Epi-Endo CNN) to classify among ventricular sources from 25 segments and from epicardium (Epi) or endocardium (Endo). The inputs are the full time courses and the first half of QRS complexes of 12-lead ECG, respectively. After registering the ventricle computer model with an individual patient's heart, the training datasets were generated by multiplying ventricular current dipoles derived from single pacing at various locations with patient-specific lead field. The origins of PVC are localized by calculating the weighted center of gravity of classification returned by the CNNs. A number of computer simulations were conducted to evaluate the proposed method under a variety of noise levels and heart registration errors. Furthermore, the proposed method was evaluated on 90 PVC beats from nine human patients with PVCs and compared against ablation outcome in the same patients. Results: The computer simulation evaluation returned relatively high accuracies for Segment CNN (∼78%) and Epi-Endo CNN (∼90%). Clinical testing in nine PVC patients resulted an averaged localization error of 11 mm. Conclusion: Our simulation and clinical evaluation results demonstrate the capability and merits of the proposed CNN-based method for localization of PVC. Significance: This paper suggests a new approach for cardiac source localization of origin of arrhythmias using only the 12-lead ECG by means of CNN, and may have important applications for future real-time monitoring and localizing origins of cardiac arrhythmias guiding ablation treatment. [ABSTRACT FROM AUTHOR]

Objective: This paper describes a gait classification method that utilizes measured motion of the thigh segment provided by an inertial measurement unit. Methods: The classification method employs a phase-variable description of gait, and identifies a given activity based on the expected curvature characteristics of that activity over a gait cycle. The classification method was tested in experiments conducted with seven healthy subjects performing three different locomotor activities: level ground walking, stair descent, and stair ascent. Classification accuracy of the phase variable classification method was assessed for classifying each activity, and transitions between activities, and compared to a linear discriminant analysis (LDA) classifier as a benchmark. Results: For the subjects tested, the phase variable classification method outperformed LDA when using nonsubject-specific training data, while the LDA outperformed the phase variable approach when using subject-specific training. Conclusions: The proposed method may provide improved classification accuracy for gait classification applications trained with nonsubject-specific data. Significance: This paper offers a new method of gait classification based on a phase variable description. The method is shown to provide improved classification accuracy relative to an LDA pattern recognition framework when trained with nonsubject-specific data. [ABSTRACT FROM AUTHOR]

Objective: Wrist joint space narrowing is a main radiographic outcome of rheumatoid arthritis (RA). Yet, automatic radiographic wrist joint space width (JSW) quantification for RA patients has not been widely investigated. The aim of this paper is to present an automatic method to quantify the JSW of three wrist joints that are least affected by bone overlapping and are frequently involved in RA. These joints are located around the scaphoid bone, viz. the multangular-navicular, capitate-navicular-lunate, and radiocarpal joints. Methods: The joint space around the scaphoid bone is detected by using consecutive searches of separate path segments, where each segment location aids in constraining the subsequent one. For joint margin delineation, first the boundary not affected by X-ray projection is extracted, followed by a backtrace process to obtain the actual joint margin. The accuracy of the quantified JSW is evaluated by comparison with the manually obtained ground truth. Results: Two of the 50 radiographs used for evaluation of the method did not yield a correct path through all three wrist joints. The delineated joint margins of the remaining 48 radiographs were used for JSW quantification. It was found that 90% of the joints had a JSW deviating less than 20% from the mean JSW of manual indications, with the mean JSW error less than 10%. Conclusion: The proposed method is able to automatically quantify the JSW of radiographic wrist joints reliably. Significance: The proposed method may aid clinical researchers to study the progression of wrist joint damage in RA studies. [ABSTRACT FROM PUBLISHER]

Mobile technology is opening a wide range of opportunities for transforming the standard of care for chronic disorders. Using smartphones as tools for longitudinally tracking symptoms could enable personalization of drug regimens and improve patient monitoring. Parkinson's disease (PD) is an ideal candidate for these tools. At present, evaluation of PD signs requires trained experts to quantify motor impairment in the clinic, limiting the frequency and quality of the information available for understanding the status and progression of the disease. Mobile technology can help clinical decision making by completing the information of motor status between hospital visits. This paper presents an algorithm to detect PD by analyzing the typing activity on smartphones independently of the content of the typed text. We propose a set of touchscreen typing features based on a covariance, skewness, and kurtosis analysis of the timing information of the data to capture PD motor signs. We tested these features, both independently and in a multivariate framework, in a population of 21 PD and 23 control subjects, achieving a sensitivity/specificity of $0.81/0.81$ for the best performing feature and $0.73/0.84$ for the best multivariate method. The results of the alternating finger-tapping, an established motor test, measured in our cohort are $0.75/0.78$. This paper contributes to the development of a home-based, high-compliance, and high-frequency PD motor test by analysis of routine typing on touchscreens. [ABSTRACT FROM AUTHOR]

Objective: Obstructive sleep apnea (OSA) is a serious chronic disease and a risk factor for cardiovascular diseases. Snoring is a typical symptom of OSA patients. Knowledge of the origin of obstruction and vibration within the upper airways is essential for a targeted surgical approach. Aim of this paper is to systematically compare different acoustic features, and classifiers for their performance in the classification of the excitation location of snore sounds. Methods: Snore sounds from 40 male patients have been recorded during drug-induced sleep endoscopy, and categorized by Ear, Nose & Throat (ENT) experts. Crest Factor, fundamental frequency, spectral frequency features, subband energy ratio, mel-scale frequency cepstral coefficients, empirical mode decomposition-based features, and wavelet energy features have been extracted and fed into several classifiers. Using the ReliefF algorithm, features have been ranked and the selected feature subsets have been tested with the same classifiers. Results: A fusion of all features after a ReliefF feature selection step in combination with a random forests classifier showed the best classification results of 78% unweighted average recall by subject independent validation. Conclusion: Multifeature analysis is a promising means to help identify the anatomical mechanisms of snore sound generation in individual subjects. Significance: This paper describes a novel approach for the machine-based multifeature classification of the excitation location of snore sounds in the upper airway. [ABSTRACT FROM PUBLISHER]

Objective: The neck is a very attractive measurement location for multimodal physiological monitoring, since it offers the possibility of extracting clinically relevant parameters, which cannot be obtained from other body locations, such as lung volumes. It is for this reason that obtaining PPG from the neck would be of interest. PPG signals, however, are very susceptible to artifacts which greatly compromise their quality. But the extent of this is going to depend on, the nature of the artifacts and the strength of the sensed signal, both of which are location dependent. This paper presents for the first time the characterization of artifacts affecting neck PPG signals. Methods: Neck PPG data was recorded from 19 participants, who performed ten different activities to deliberately introduce common artifacts. 41 PPG features were extracted and statistically analyzed to investigate which ones showed the greatest ability to differentiate normal PPG from each artifact. A customized minimum Redundancy Maximum Relevance (mRMR) feature selection approach was implemented, to select the top 10 features. Results: Artifacts caused by Swallowing, Yawning and Coughing exhibited larger Spectral Entropy, Average Power and smaller Spectral Kurtosis, than normal PPG. Head movement artifacts, also demonstrated highly disordered and noisy frequency spectra, and were characterized by having larger and irregular time domain features. In addition, the analysis showed that different respiratory states that could be of clinical interests, such as presence of apneas, were also distinguishable from sources of interference. Significance: These findings are important for the development of PPG denoising algorithms and subsequent obtention of biomarkers of interest, or alternatively for applications where the events of interest are the artifacts themselves. [ABSTRACT FROM AUTHOR]

Recognizing activities of daily living (ADL) provides vital contextual information that enhances the effectiveness of various mobile health and wellness applications. Development of wearable motion sensors along with machine learning algorithms offer a great opportunity for ADL recognition. However, the performance of the ADL recognition systems may significantly degrade when they are used by a new user due to inter-subject variability. This issue limits the usability of these systems. In this paper, we propose a deep learning assisted personalization framework for ADL recognition with the aim to maximize the personalization performance while minimizing solicitation of inputs or labels from the user to reduce user's burden. The proposed framework consists of unsupervised retraining of automatic feature extraction layers and supervised fine-tuning of classification layers through a novel active learning model based on a given model's uncertainty. We design a Bayesian deep convolutional neural network with stochastic latent variables that allows us to estimate both aleatoric (data-dependent) and epistemic (model-dependent) uncertainties in recognition task. In this study, for the first time, we show how distinguishing between the two aforementioned sources of uncertainty leads to more effective active learning. The experimental results show that our proposed method improves the accuracy of ADL recognition on a new user by 25% on average compared to the case of using a model for a new user with no personalization with an average final accuracy of 89.2%. Moreover, our method achieves higher personalization accuracy while significantly reducing user's burden in terms of soliciting inputs and labels compared to other methods. [ABSTRACT FROM AUTHOR]

Early identification of dementia at the stage of mild cognitive impairment (MCI) is crucial for timely diagnosis and intervention of Alzheimer's disease (AD). Although several pioneering studies have been devoted to automated AD diagnosis based on resting-state functional magnetic resonance imaging (rs-fMRI), their performance is somewhat limited due to non-effective mining of spatial-temporal dependency. Besides, few of these existing approaches consider the explicit detection and modeling of discriminative brain regions (i.e., network hubs) that are sensitive to AD progression. In this paper, we propose a unique Spatial-Temporal convolutional-recurrent neural Network (STNet) for automated prediction of AD progression and network hub detection from rs-fMRI time series. Our STNet incorporates the spatial-temporal information mining and AD-related hub detection into an end-to-end deep learning model. Specifically, we first partition rs-fMRI time series into a sequence of overlapping sliding windows. A sequence of convolutional components are then designed to capture the local-to-global spatially-dependent patterns within each sliding window, based on which we are able to identify discriminative hubs and characterize their unique contributions to disease diagnosis. A recurrent component with long short-term memory (LSTM) units is further employed to model the whole-brain temporal dependency from the spatially-dependent pattern sequences, thus capturing the temporal dynamics along time. We evaluate the proposed method on 174 subjects with 563 rs-fMRI scans from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, with results suggesting the effectiveness of our method in both tasks of disease progression prediction and AD-related hub detection. [ABSTRACT FROM AUTHOR]

Objective: Joint analysis of multi-subject brain imaging datasets has wide applications in biomedical engineering. In these datasets, some sources belong to all subjects (joint), a subset of subjects (partially-joint), or a single subject (individual). In this paper, this source model is referred to as joint/partially-joint/individual multiple datasets unidimensional (JpJI-MDU), and accordingly, a source extraction method is developed. Method: We present a deflation-based algorithm utilizing higher order cumulants to analyze the JpJI-MDU source model. The algorithm maximizes a cost function which leads to an eigenvalue problem solved with thin-SVD (singular value decomposition) factorization. Furthermore, we introduce the JpJI-feature which indicates the spatial shape of each source and the amount of its jointness with other subjects. We use this feature to determine the type of sources. Results: We evaluate our algorithm by analyzing simulated data and two real functional magnetic resonance imaging (fMRI) datasets. In our simulation study, we will show that the proposed algorithm determines the type of sources with the accuracy of 95% and 100% for 2-class and 3-class clustering scenarios, respectively. Furthermore, our algorithm extracts meaningful joint and partially-joint sources from the two real datasets, which are consistent with the existing neuroscience studies. Conclusion: Our results in analyzing the real datasets reveal that both datasets follow the JpJI-MDU source model. This source model improves the accuracy of source extraction methods developed for multi-subject datasets. Significance: The proposed joint blind source separation algorithm is robust and avoids parameters which are difficult to fine-tune. [ABSTRACT FROM AUTHOR]

Objectives: This paper introduces a novel method for the detection and classification of aortic stenosis (AS) using the time-frequency features of chest cardio-mechanical signals collected from wearable sensors, namely seismo-cardiogram (SCG) and gyro-cardiogram (GCG) signals. Such a method could potentially monitor high-risk patients out of the clinic. Methods: Experimental measurements were collected from twenty patients with AS and twenty healthy subjects. Firstly, a digital signal processing framework is proposed to extract time-frequency features. The features are then selected via the analysis of variance test. Different combinations of features are evaluated using the decision tree, random forest, and artificial neural network methods. Two classification tasks are conducted. The first task is a binary classification between normal subjects and AS patients. The second task is a multi-class classification of AS patients with co-existing valvular heart diseases. Results: In the binary classification task, the average accuracies achieved are 96.25% from decision tree, 97.43% from random forest, and 95.56% from neural network. The best performance is from combined SCG and GCG features with random forest classifier. In the multi-class classification, the best performance is 92.99% using the random forest classifier and SCG features. Conclusion: The results suggest that the solution could be a feasible method for classifying aortic stenosis, both in the binary and multi-class tasks. It also indicates that most of the important time-frequency features are below 11 Hz.Significance: The proposed method shows great potential to provide continuous monitoring of valvular heart diseases to prevent patients from sudden critical cardiac situations. [ABSTRACT FROM AUTHOR]

Real-time wearable electrocardiogram monitoring sensor is one of the best candidates in assisting cardiovascular disease diagnosis. In this paper, we present a novel real-time machine learning system for Arrhythmia classification. The system is based on the parallel Delta modulation and QRS/PT wave detection algorithms. We propose a patient dependent rotated linear-kernel support vector machine classifier that combines the global and local classifiers, with three types of feature vectors extracted directly from the Delta modulated bit-streams. The performance of the proposed system is evaluated using the MIT-BIH Arrhythmia database. According to the AAMI standard, two binary classifications are performed and evaluated, which are supraventricular ectopic beat (SVEB) versus the rest four classes, and ventricular ectopic beat (VEB) versus the rest. For SVEB classification, the preferred SkP-32 method's F1 score, sensitivity, specificity, and positive predictivity value are 0.83, 79.3%, 99.6%, and 88.2%, respectively, and for VEB classification, the numbers are 0.92%, 92.8%, 99.4%, and 91.6%, respectively. The results show that the performance of our proposed approach is comparable to that of published research. The proposed low-complexity algorithm has the potential to be implemented as an on-sensor machine learning solution. [ABSTRACT FROM AUTHOR]

Objective: This paper targets a major challenge in developing practical electroencephalogram (EEG)-based brain–computer interfaces (BCIs): how to cope with individual differences so that better learning performance can be obtained for a new subject, with minimum or even no subject-specific data? Methods: We propose a novel approach to align EEG trials from different subjects in the Euclidean space to make them more similar, and hence improve the learning performance for a new subject. Our approach has three desirable properties: first, it aligns the EEG trials directly in the Euclidean space, and any signal processing, feature extraction, and machine learning algorithms can then be applied to the aligned trials; second, its computational cost is very low; and third, it is unsupervised and does not need any label information from the new subject. Results: Both offline and simulated online experiments on motor imagery classification and event-related potential classification verified that our proposed approach outperformed a state-of-the-art Riemannian space data alignment approach, and several approaches without data alignment. Conclusion: The proposed Euclidean space EEG data alignment approach can greatly facilitate transfer learning in BCIs. Significance: Our proposed approach is effective, efficient, and easy to implement. It could be an essential pre-processing step for EEG-based BCIs. [ABSTRACT FROM AUTHOR]

Objective: The purpose of this paper is to propose a novel algorithm for joint optic disc and cup segmentation, which aids the glaucoma detection. Methods: By assuming the shapes of cup and disc regions to be elliptical, we proposed an end-to-end region-based convolutional neural network for joint optic disc and cup segmentation (referred to as JointRCNN). Atrous convolution is introduced to boost the performance of feature extraction module. In JointRCNN, disc proposal network (DPN) and cup proposal network (CPN) are proposed to generate bounding box proposals for the optic disc and cup, respectively. Given the prior knowledge that the optic cup is located in the optic disc, disc attention module is proposed to connect DPN and CPN, where a suitable bounding box of the optic disc is first selected and then continued to be propagated forward as the basis for optic cup detection in our proposed network. After obtaining the disc and cup regions, which are the inscribed ellipses of the corresponding detected bounding boxes, the vertical cup-to-disc ratio is computed and used as an indicator for glaucoma detection. Results: Comprehensive experiments clearly show that our JointRCNN model outperforms state-of-the-art methods for optic disc and cup segmentation task and glaucoma detection task. Conclusion: Joint optic disc and cup segmentation, which utilizes the connection between optic disc and cup, could improve the performance of optic disc and cup segmentation. Significance: The proposed method improves the accuracy of glaucoma detection. It is promising to be used for glaucoma screening. [ABSTRACT FROM AUTHOR]

Segmentation of cardiac ventricle from magnetic resonance images is significant for cardiac disease diagnosis, progression assessment, and monitoring cardiac conditions. Manual segmentation is so time consuming, tedious, and subjective that automated segmentation methods are highly desired in practice. However, conventional segmentation methods performed poorly in cardiac ventricle, especially in the right ventricle. Compared with the left ventricle, whose shape is a simple thick-walled circle, the structure of the right ventricle is more complex due to ambiguous boundary, irregular cavity, and variable crescent shape. Hence, effective feature extractors and segmentation models are preferred. In this paper, we propose a dilated-inception net (DIN) to extract and aggregate multi-scale features for right ventricle segmentation. The DIN outperforms many state-of-the-art models on the benchmark database of right ventricle segmentation challenge. In addition, the experimental results indicate that the proposed model has potential to reach expert-level performance in right ventricular epicardium segmentation. More importantly, DIN behaves similarly to clinical expert with high correlation coefficients in four clinical cardiac indices. Therefore, the proposed DIN is promising for automated cardiac right ventricle segmentation in clinical applications. [ABSTRACT FROM AUTHOR]

In this paper, we present a deep learning framework “Rehab-Net” for effectively classifying three upper limb movements of the human arm, involving extension, flexion, and rotation of the forearm, which, over the time, could provide a measure of rehabilitation progress. The proposed framework, Rehab-Net is formulated with a personalized, light weight and low-complex, customized convolutional neural network (CNN) model, using two-layers of CNN, interleaved with pooling layers, followed by a fully connected layer that classifies the three movements from tri-axial acceleration input data collected from the wrist. The proposed Rehab-Net framework was validated on sensor data collected in two situations: 1) semi-naturalistic environment involving an archetypal activity of “making-tea” with four stroke survivors and 2) natural environment, where ten stroke survivors were free to perform any desired arm movement for the duration of 120 min. We achieved an overall accuracy of 97.89% on semi-naturalistic data and 88.87% on naturalistic data which exceeded state-of-the-art learning algorithms namely, linear discriminant analysis, support vector machines, and k-means clustering with an average accuracy of 48.89%, 44.14%, and 27.64%. Subsequently, a computational complexity analysis of the proposed model has been discussed with an eye toward hardware implementation. The clinical significance of this study is to accurately monitor the clinical progress of the rehabilitated subjects under the ambulatory settings. [ABSTRACT FROM AUTHOR]

Gesture recognition using sparse multichannel surface electromyography (sEMG) is a challenging problem, and the solutions are far from optimal from the point of view of muscle–computer interface. In this paper, we address this problem from the context of multi-view deep learning. A novel multi-view convolutional neural network (CNN) framework is proposed by combining classical sEMG feature sets with a CNN-based deep learning model. The framework consists of two parts. In the first part, multi-view representations of sEMG are modeled in parallel by a multistream CNN, and a performance-based view construction strategy is proposed to choose the most discriminative views from classical feature sets for sEMG-based gesture recognition. In the second part, the learned multi-view deep features are fused through a view aggregation network composed of early and late fusion subnetworks, taking advantage of both early and late fusion of learned multi-view deep features. Evaluations on 11 sparse multichannel sEMG databases as well as five databases with both sEMG and inertial measurement unit data demonstrate that our multi-view framework outperforms single-view methods on both unimodal and multimodal sEMG data streams. [ABSTRACT FROM AUTHOR]

Objective: Spectral power analysis plays a predominant role in electroencephalogram-based emotional recognition. It can reflect activity differences among multiple brain regions. In addition to activation difference, different emotions also involve different large-scale network during related information processing. In this paper, both information propagation patterns and activation difference in the brain were fused to improve the performance of emotional recognition. Methods: We constructed emotion-related brain networks with phase locking value and adopted a multiple feature fusion approach to combine the compensative activation and connection information for emotion recognition. Results: Recognition results on three public emotional databases demonstrated that the combined features are superior to either single feature based on power distribution or network character. Furthermore, the conducted feature fusion analysis revealed the common characters between activation and connection patterns involved in the positive, neutral, and negative emotions for information processing. Significance: The proposed feasible combination of both information propagation patterns and activation difference in the brain is meaningful for developing the effective human–computer interaction systems by adapting to human emotions in the real world applications. [ABSTRACT FROM AUTHOR]

Goal: In this paper, we propose methods for (1) automatic feature extraction and classification for acetic acid and Lugol's iodine cervigrams and (2) methods for combining features/diagnosis of different contrasts in cervigrams for improved performance. Methods: We developed algorithms to pre-process pathology-labeled cervigrams and extract simple but powerful color and textural-based features. The features were used to train a support vector machine model to classify cervigrams based on corresponding pathology for visual inspection with acetic acid, visual inspection with Lugol's iodine, and a combination of the two contrasts. Results: The proposed framework achieved a sensitivity, specificity, and accuracy of 81.3%, 78.6%, and 80.0%, respectively, when used to distinguish cervical intraepithelial neoplasia (CIN+) relative to normal and benign tissues. This is superior to the average values achieved by three expert physicians on the same data set for discriminating normal/benign cases from CIN+ (77% sensitivity, 51% specificity, and 63% accuracy). Conclusion: The results suggest that utilizing simple color- and textural-based features from visual inspection with acetic acid and visual inspection with Lugol's iodine images may provide unbiased automation of cervigrams. Significance: This would enable automated, expert-level diagnosis of cervical pre-cancer at the point of care. [ABSTRACT FROM AUTHOR]

Cough is a protective reflex conveying information on the state of the respiratory system. Cough assessment has been limited so far to subjective measurement tools or uncomfortable (i.e., non-wearable) cough monitors. This limits the potential of real-time cough monitoring to improve respiratory care. Objective: This paper presents a machine hearing system for audio-based robust cough segmentation that can be easily deployed in mobile scenarios. Methods: Cough detection is performed in two steps. First, a short-term spectral feature set is separately computed in five predefined frequency bands: [0, 0.5), [0.5, 1), [1, 1.5), [1.5, 2), and [2, 5.5125] kHz. Feature selection and combination are then applied to make the short-term feature set robust enough in different noisy scenarios. Second, high-level data representation is achieved by computing the mean and standard deviation of short-term descriptors in 300 ms long-term frames. Finally, cough detection is carried out using a support vector machine trained with data from different noisy scenarios. The system is evaluated using a patient signal database which emulates three real-life scenarios in terms of noise content. Results: The system achieves 92.71% sensitivity, 88.58% specificity, and 90.69% Area Under Receiver Operating Charcteristic (ROC) curve (AUC), outperforming state-of-the-art methods. Conclusion: Our research outcome paves the way to create a device for cough monitoring in real-life situations. Significance: Our proposal is aligned with a more comfortable and less disruptive patient monitoring, with benefits for patients (allows self-monitoring of cough symptoms), practitioners (e.g., assessment of treatments or better clinical understanding of cough patterns), and national health systems (by reducing hospitalizations). [ABSTRACT FROM AUTHOR]

In recent years, an increasing number of people have become concerned about their health. Most chronic diseases are related to lifestyle, and daily activity records can be used as an important indicator of health. Specifically, using advanced technology to automatically monitor actual activities can effectively prevent and manage chronic diseases. The data used in this paper were obtained from acceleration sensors and gyroscopes integrated in smartphones. We designed an efficient Adaboost-Stump running on a smartphone to classify five common activities: cycling, running, sitting, standing, and walking and achieved a satisfactory classification accuracy of 98%. We designed an online learning method, and the classification model requires continuous training with actual data. The parameters in the model then become increasingly fitted to the specific user, which allows the classification accuracy to reach 95% under different use environments. In addition, this paper also utilized the OpenCL framework to design the program in parallel. This process can enhance the computing efficiency approximately ninefold. [ABSTRACT FROM AUTHOR]

Objectives: The use of remote sensing technologies such as radar is gaining popularity as a technique for contactless detection of physiological signals and analysis of human motion. This paper presents a methodology for classifying different events in a collection of phase modulated continuous wave radar returns. The primary application of interest is to monitor inmates where the presence of human vital signs amidst different, interferences needs to be identified. Methods: A comprehensive set of features is derived through time and frequency domain analyses of the radar returns. The Bhattacharyya distance is used to preselect the features with highest class separability as the possible candidate features for use in the classification process. The uncorrelated linear discriminant analysis is performed to decorrelate, denoise, and reduce the dimension of the candidate feature set. Linear and quadratic Bayesian classifiers are designed to distinguish breathing, different human motions, and nonhuman motions. The performance of these classifiers is evaluated on a pilot dataset of radar returns that contained different events including breathing, stopped breathing, simple human motions, and movement of fan and water. Results: Our proposed pattern classification system achieved accuracies of up to $93$% in stationary subject detection, $90$% in stop-breathing detection, and $86$% in interference detection. Conclusion: Our proposed radar pattern recognition system was able to accurately distinguish the predefined events amidst interferences. Significance: Besides inmate monitoring and suicide attempt detection, this paper can be extended to other radar applications such as home-based monitoring of elderly people, apnea detection, and home occupancy detection. [ABSTRACT FROM AUTHOR]

Objective: Extraction and analysis of various clinically significant features of photoplethysmogram (PPG) signals for monitoring several physiological parameters, as well as for biometric authentication have become important areas of research in recent years. However, PPG signal compression; particularly quality-guaranteed compression, and steganography of patient's secret information is still lagging behind. Method: This paper presents a robust, reliable and highly efficient singular value decomposition and lossless ASCII character encoding (LL-ACE)-based quality-guaranteed PPG compression algorithm. This algorithm cannot only be used to compress PPG signals, but also do so for steganographed PPG signals that include the patient information. Result and conclusion: It is worth mentioning that such an algorithm is being proposed for the first time to compress steganographed PPG signals. The algorithm is tested on PPG signals collected from four different databases, and its performance is assessed using both quantitative and qualitative measures. The proposed steganographed PPG compression algorithm provides a compression ratio that is much higher than that provided by other algorithms that are designed to compress the PPG signals only. Significance: first, the clinical quality of the reconstructed PPG signal can be controlled precisely, second, the patient's personal information is restored with no errors, third, high compression ratio, and fourth, the PPG signal reconstruction error is neither dependent on the steganographic operation nor on the size of the patient information data. [ABSTRACT FROM AUTHOR]

Objective: Chinese women are seriously threatened by breast cancer with high morbidity and mortality. The lack of robust prognosis models results in difficulty for doctors to prepare an appropriate treatment plan that may prolong patient survival time. An alternative prognosis model framework to predict invasive disease-free survival (iDFS) for early stage breast cancer patients, called MP4Ei, is proposed. MP4Ei framework gives an excellent performance to predict the relapse or metastasis breast cancer of Chinese patients in five years. Methods: MP4Ei is built based on statistical theory and gradient boosting decision tree framework. 5246 patients, derived from the clinical research center for breast in West China Hospital of Sichuan University, with early-stage (stage I–III) breast cancer are eligible for inclusion. Stratified feature selection, including statistical and ensemble methods, is adopted to select 23 out of the 89 patient features about the patient’ demographics, diagnosis, pathology, and therapy. Then, 23 selected features as the input variables are imported into the XGBoost algorithm, with Bayesian parameter tuning and cross validation, to find out the optimum simplified model for five-year iDFS prediction. Results: For eligible data, with 4196 patients (80%) for training, and with 1050 patients (20%) for testing, MP4Ei achieves comparable accuracy with AUC 0.8451, which has a significant advantage (p < 0.05). Conclusion: This work demonstrates the complete iDFS prognosis model with very competitive performance. Significance: The proposed method in this paper could be used in clinical practice to predict patients’ prognosis and future surviving state, which may help doctors make treatment plan. [ABSTRACT FROM AUTHOR]

Epilepsy is a neurological disorder arising from anomalies of the electrical activity in the brain, affecting about 65 millions individuals worldwide. Objective: This paper proposes a patient-specific approach for short-term prediction (i.e., within few minutes) of epileptic seizures. Methods: We use noninvasive EEG data, since the aim is exploring the possibility of developing a noninvasive monitoring/control device for the prediction of seizures. Our approach is based on finding synchronization patterns in the EEG that allow to distinguish in real time preictal from interictal states. In practice, we develop easily computable functions over a graph model to capture the variations in the synchronization, and employ a classifier for identifying the preictal state. Results: We compare two state-of-the-art classification algorithms and a simple and computationally inexpensive threshold-based classifier developed ad hoc. Results on publicly available scalp EEG database and on scalp data of the patients of the Unit of Neurology and Neurophysiology at University of Siena show that this simple and computationally viable processing is able to highlight the changes in synchronization when a seizure is approaching. Conclusion and significance: The proposed approach, characterized by low computational requirements and by the use of noninvasive techniques, is a step toward the development of portable and wearable devices for real-life use. [ABSTRACT FROM AUTHOR]

In this paper, we present a novel framework for dermoscopy image recognition via both a deep learning method and a local descriptor encoding strategy. Specifically, deep representations of a rescaled dermoscopy image are first extracted via a very deep residual neural network pretrained on a large natural image dataset. Then these local deep descriptors are aggregated by orderless visual statistic features based on Fisher vector (FV) encoding to build a global image representation. Finally, the FV encoded representations are used to classify melanoma images using a support vector machine with a Chi-squared kernel. Our proposed method is capable of generating more discriminative features to deal with large variations within melanoma classes, as well as small variations between melanoma and nonmelanoma classes with limited training data. Extensive experiments are performed to demonstrate the effectiveness of our proposed method. Comparisons with state-of-the-art methods show the superiority of our method using the publicly available ISBI 2016 Skin lesion challenge dataset. [ABSTRACT FROM AUTHOR]

Objective: Up to 10% of free flap cases are compromised, and without prompt intervention, amputation and even death can occur. Hourly monitoring improves salvage rates, but the gold standard for monitoring requires experienced personnel to operate and suffers from high false-positive rates as high as 31% that result in costly and unnecessary surgeries. In this paper, we investigate free flap patency monitoring using automatic hardware-only classification systems that eliminate the need for experienced personnel. The expected flow ranges of the antegrade and retrograde veins for breast reconstruction are studied using a syringe pump to create the laminar flow seen in veins. Methods: Feature data extracted from the Doppler blood flow signals are analyzed for sensitivity, specificity, and false-positive rates. Hardware is built to perform the classification automatically in real-time and output a decision at the end of the observation period. Results: Experimental results using the hardware-only classifier for a 50 ms window size show high sensitivity (96.75%), specificity (90.20%), and low false-positive rate (9.803%). The experimental and theoretical classification results show close agreement. Conclusion: This work indicates that automatic hardware-only classifiers can eliminate the need for experienced personnel to monitor free flap patency. Significance: The hardware-only classification is amenable to a monolithic implementation and future studies should study a totally implantable wirelessly-powered blood flow classifier. The high classifier performance in a short window period indicates that duty-cycled powering can be used to extend the safe operational depth of an implant. This is particularly relevant for the difficult buried free flap applications. [ABSTRACT FROM AUTHOR]

This paper introduces the “encoded local projections” (ELP) as a new dense-sampling image descriptor for search and classification problems. The gradient changes of multiple projections in local windows of gray-level images are encoded to build a histogram that captures spatial projection patterns. Using projections is a conventional technique in both medical imaging and computer vision. Furthermore, powerful dense-sampling methods, such as local binary patterns and the histogram of oriented gradients, are widely used for image classification and recognition. Inspired by many achievements of such existing descriptors, we explore the design of a new class of histogram-based descriptors with particular applications in medical imaging. We experiment with three public datasets (IRMA, Kimia Path24, and CT Emphysema) to comparatively evaluate the performance of ELP histograms. In light of the tremendous success of deep architectures, we also compare the results with deep features generated by pretrained networks. The results are quite encouraging as the ELP descriptor can surpass both conventional and deep descriptors in performance in several experimental settings. [ABSTRACT FROM AUTHOR]

Goal: Automatic segmentation of brainstem gliomas and prediction of genotype (H3 K27M) mutation status based on magnetic resonance (MR) images are crucial but challenging tasks for computer-aided diagnosis in neurosurgery. In this paper, we present a novel cascaded deep convolutional neural network (CNN) to address these two challenging tasks simultaneously. Methods: Our novel segmentation task contains two feature-fusion modules: the Gaussian-pyramid multiscale input features-fusion technique and the brainstem-region feature enhancement. The aim is to resolve very difficult problems in brainstem glioma segmentation. Our prediction model combines CNN features and support-vector-machine classifier to automatically predict genotypes without region-of-interest labeled-MR images and is learned jointly with the segmentation task. First, Gaussian-pyramid multiscale input feature fusion is added to our glioma-segmentation task to solve the problems of size variety and weak brainstem-gliomas boundaries. Second, the two feature-fusion modules provide both local and global contexts to retain higher frequency details for sharper tumor boundaries, handling the problem of the large variation of tumor shape, and volume resolution. Results and Conclusion: Experiments demonstrate that our cascaded CNN method achieves not only a good tumor segmentation result with a high Dice similarity coefficient of 77.03%, but also a competitive genotype prediction result with an average accuracy of 94.85% upon fivefold cross-validation. [ABSTRACT FROM AUTHOR]

Objective: In this paper, we accurately detect the state-sequence first heart sound (S1)–systole–second heart sound (S2)–diastole, i.e., the positions of S1 and S2, in heart sound recordings. We propose an event detection approach without explicitly incorporating a priori information of the state duration. This renders it also applicable to recordings with cardiac arrhythmia and extendable to the detection of extra heart sounds (third and fourth heart sound), heart murmurs, as well as other acoustic events. Methods: We use data from the 2016 PhysioNet/CinC Challenge, containing heart sound recordings and annotations of the heart sound states. From the recordings, we extract spectral and envelope features and investigate the performance of different deep recurrent neural network (DRNN) architectures to detect the state sequence. We use virtual adversarial training, dropout, and data augmentation for regularization. Results: We compare our results with the state-of-the-art method and achieve an average score for the four events of the state sequence of ${\bf F}_{1}\approx 96$ % on an independent test set. Conclusion: Our approach shows state-of-the-art performance carefully evaluated on the 2016 PhysioNet/CinC Challenge dataset. Significance: In this work, we introduce a new methodology for the segmentation of heart sounds, suggesting an event detection approach with DRNNs using spectral or envelope features. [ABSTRACT FROM AUTHOR]

This paper proposes a segmentation-free radiomics method to classify malignant and benign breast tumors with shear-wave elastography (SWE) data. The method is targeted to integrate the advantage of both SWE in providing important elastic with morphology information and convolutional neural network (CNN) in automatic feature extraction and accurate classification. Compared to traditional methods, the proposed method is designed to directly extract features from the dataset without the prerequisite of segmentation and manual operation. This can keep the peri-tumor information, which is lost by segmentation-based methods. With the proposed model trained on 540 images (318 of malignant breast tumors and 222 of benign breast tumors, respectively), an accuracy of 95.8%, a sensitivity of 96.2%, and a specificity of 95.7% was obtained for the final test. The superior performances compared to the existing state-of-the-art methods and its automatic nature both demonstrate that the proposed method has a great potential to be applied to clinical computer-aided diagnosis of breast cancer. [ABSTRACT FROM AUTHOR]