Memory-inspired spiking hyperdimensional network for robust online learning.

Recently, brain-inspired computing models have shown great potential to outperform today's deep learning solutions in terms of robustness and energy efficiency. Particularly, Spiking Neural Networks (SNNs) and HyperDimensional Computing (HDC) have shown promising results in enabling efficient and robust cognitive learning. Despite the success, these two brain-inspired models have different strengths. While SNN mimics the physical properties of the human brain, HDC models the brain on a more abstract and functional level. Their design philosophies demonstrate complementary patterns that motivate their combination. With the help of the classical psychological model on memory, we propose SpikeHD, the first framework that fundamentally combines Spiking neural network and hyperdimensional computing. SpikeHD generates a scalable and strong cognitive learning system that better mimics brain functionality. SpikeHD exploits spiking neural networks to extract low-level features by preserving the spatial and temporal correlation of raw event-based spike data. Then, it utilizes HDC to operate over SNN output by mapping the signal into high-dimensional space, learning the abstract information, and classifying the data. Our extensive evaluation on a set of benchmark classification problems shows that SpikeHD provides the following benefit compared to SNN architecture: (1) significantly enhance learning capability by exploiting two-stage information processing, (2) enables substantial robustness to noise and failure, and (3) reduces the network size and required parameters to learn complex information.

GrapHD: Graph-Based Hyperdimensional Memorization for Brain-Like Cognitive Learning.

Memorization is an essential functionality that enables today's machine learning algorithms to provide a high quality of learning and reasoning for each prediction. Memorization gives algorithms prior knowledge to keep the context and define confidence for their decision. Unfortunately, the existing deep learning algorithms have a weak and nontransparent notion of memorization. Brain-inspired HyperDimensional Computing (HDC) is introduced as a model of human memory. Therefore, it mimics several important functionalities of the brain memory by operating with a vector that is computationally tractable and mathematically rigorous in describing human cognition. In this manuscript, we introduce a brain-inspired system that represents HDC memorization capability over a graph of relations. We propose GrapHD, hyperdimensional memorization that represents graph-based information in high-dimensional space. GrapHD defines an encoding method representing complex graph structure while supporting both weighted and unweighted graphs. Our encoder spreads the information of all nodes and edges across into a full holistic representation so that no component is more responsible for storing any piece of information than another. Then, GrapHD defines several important cognitive functionalities over the encoded memory graph. These operations include memory reconstruction, information retrieval, graph matching, and shortest path. Our extensive evaluation shows that GrapHD: (1) significantly enhances learning capability by giving the notion of short/long term memorization to learning algorithms, (2) enables cognitive computing and reasoning over memorization graph, and (3) enables holographic brain-like computation with substantial robustness to noise and failure.

Stochastic Sequential Modeling: Toward Improved Prostate Cancer Diagnosis Through Temporal-Ultrasound.

Prostate cancer (PCa) is a common, serious form of cancer in men that is still prevalent despite ongoing developments in diagnostic oncology. Current detection methods lead to high rates of inaccurate diagnosis. We present a method to directly model and exploit temporal aspects of temporal enhanced ultrasound (TeUS) for tissue characterization, which improves malignancy prediction. We employ a probabilistic-temporal framework, namely, hidden Markov models (HMMs), for modeling TeUS data obtained from PCa patients. We distinguish malignant from benign tissue by comparing the respective log-likelihood estimates generated by the HMMs. We analyze 1100 TeUS signals acquired from 12 patients. Our results show improved malignancy identification compared to previous results, demonstrating over 85% accuracy and AUC of 0.95. Incorporating temporal information directly into the models leads to improved tissue differentiation in PCa. We expect our method to generalize and be applied to other types of cancer in which temporal-ultrasound can be recorded.

Markov Decision Process Modeling for Multi-stage Optimization of Intervention and Treatment Strategies in Breast Cancer.

The breast cancer is a prevalent problem that undermines quality of patients' lives and causes significant impacts on psychosocial wellness. Advanced sensing provides unprecedented opportunities to develop smart cancer care. The available sensing data captured from individuals enable the extraction of information pertinent to the breast cancer conditions to construct efficient and personalized intervention and treatment strategies. This research develops a novel sequential decision-making framework to determine optimal intervention and treatment planning for breast cancer patients. We design a Markov decision process (MDP) model for both objectives of intervention and treatment costs as well as quality adjusted life years (QALYs) with the data-driven and state-dependent intervention and treatment actions. The state space is defined as a vector of age, health status, prior intervention, and treatment plans. Also, the action space includes wait, prophylactic surgery, radiation therapy, chemotherapy, and their combinations. Experimental results demonstrate that prophylactic mastectomy and chemotherapy are more effective than other intervention and treatment plans in minimizing the expected cancer cost of 25 to 60 years-old patient with in-situ stage of cancer. However, wait policy leads to an optimal quality of life for a patient with the same state. The proposed MDP framework can also be generally applicable to a variety of medical domains that entail evidence-based decision making.

Hierarchical Gaussian Process Modeling and Estimation of State-action Transition Dynamics in Breast Cancer.

Breast cancer is the most prevalent type of cancer in the US. Available treatments, including mastectomy, radiation, and chemotherapy, vary in curability, cost, and mortality probability of patients. This research aims at tracking the result of post-treatment for evidence-based decision making in breast cancer. Based on available big data, we implemented conditional probability to estimate multi-age transition probability matrices to predict the progression of disease conditions. The patient state is defined based on patients' age, cancer stage, and treatment history. To tackle the incomplete data in the matrix, we design a novel Hierarchical Gaussian Distribution (HGP) to estimate the missing part of the table. The HGP model leads to the lowest Root Mean Square Error (RMSE), which is 35% lower than the Gaussian Process and 40% lower than Linear Regression. Results of transition probability estimation show that the chance of survival within a year for 40 to 50 years old patient with the distant stage of cancer is 96.5%, which is higher than even younger age groups.

Correction to: Stochastic Sequential Modeling: Toward Improved Prostate Cancer Diagnosis Through Temporal-Ultrasound.

The authors have noted an omission in the original acknowledgements. The correct acknowledgements are as follows: Acknowledgements: This work was partially supported by Grants from NSERC Discovery to Hagit Shatkay and Parvin Mousavi, NSERC and CIHR CHRP to Parvin Mousavi and NIH R01 LM012527, NIH U54 GM104941, NSF IIS EAGER #1650851 & NSF HDR #1940080 to Hagit Shatkay.

Heterogeneous Recurrence Analysis of Disease-Altered Spatiotemporal Patterns in Multi-Channel Cardiac Signals.

Heart diseases alter the rhythmic behaviors of cardiac electrical activity. Recent advances in sensing technology bring the ease to acquire space-time electrical activity of the heart such as vectorcardiogram (VCG) signals. Recurrence analysis of successive heartbeats is conducive to detect the disease-altered cardiac activities. However, conventional recurrence analysis is more concerned about homogeneous recurrences, and overlook heterogeneous types of recurrence variations in VCG signals (i.e., in terms of state properties and transition dynamics). This paper presents a new framework of heterogeneous recurrence analysis for the characterization and modeling of disease-altered spatiotemporal patterns in multi-channel cardiac signals. Experimental results show that the proposed approach yields an accuracy of 96.9%, a sensitivity of 95.0%, and a specificity of 98.7% for the identification of myocardial infarctions. The proposed method of heterogeneous recurrence analysis shows strong potential to be further extended for the analysis of other physiological signals such as electroencephalogram (EEG) and electromyography (EMG) signals towards medical decision making.

Stochastic Modeling of Temporal Enhanced Ultrasound: Impact of Temporal Properties on Prostate Cancer Characterization.

OBJECTIVES: Temporal enhanced ultrasound (TeUS) is a new ultrasound-based imaging technique that provides tissue-specific information. Recent studies have shown the potential of TeUS for improving tissue characterization in prostate cancer diagnosis. We study the temporal properties of TeUS-temporal order and length-and present a new framework to assess their impact on tissue information. METHODS: We utilize a probabilistic modeling approach using hidden Markov models (HMMs) to capture the temporal signatures of malignant and benign tissues from TeUS signals of nine patients. We model signals of benign and malignant tissues (284 and 286 signals, respectively) in their original temporal order as well as under order permutations. We then compare the resulting models using the Kullback-Liebler divergence and assess their performance differences in characterization. Moreover, we train HMMs using TeUS signals of different durations and compare their model performance when differentiating tissue types. RESULTS: Our findings demonstrate that models of order-preserved signals perform statistically significantly better (85% accuracy) in tissue characterization compared to models of order-altered signals (62% accuracy). The performance degrades as more changes in signal order are introduced. Additionally, models trained on shorter sequences perform as accurately as models of longer sequences. CONCLUSION: The work presented here strongly indicates that temporal order has substantial impact on TeUS performance; thus, it plays a significant role in conveying tissue-specific information. Furthermore, shorter TeUS signals can relay sufficient information to accurately distinguish between tissue types. SIGNIFICANCE: Understanding the impact of TeUS properties facilitates the process of its adopting in diagnostic procedures and provides insights on improving its acquisition.

Investigation of Physical Phenomena Underlying Temporal-Enhanced Ultrasound as a New Diagnostic Imaging Technique: Theory and Simulations.

Temporal-enhanced ultrasound (TeUS) is a novel noninvasive imaging paradigm that captures information from a temporal sequence of backscattered US radio frequency data obtained from a fixed tissue location. This technology has been shown to be effective for classification of various in vivo and ex vivo tissue types including prostate cancer from benign tissue. Our previous studies have indicated two primary phenomena that influence TeUS: 1) changes in tissue temperature due to acoustic absorption and 2) micro vibrations of tissue due to physiological vibration. In this paper, first, a theoretical formulation for TeUS is presented. Next, a series of simulations are carried out to investigate micro vibration as a source of tissue characterizing information in TeUS. The simulations include finite element modeling of micro vibration in synthetic phantoms, followed by US image generation during TeUS imaging. The simulations are performed on two media, a sparse array of scatterers and a medium with pathology mimicking scatterers that match nuclei distribution extracted from a prostate digital pathology data set. Statistical analysis of the simulated TeUS data shows its ability to accurately classify tissue types. Our experiments suggest that TeUS can capture the microstructural differences, including scatterer density, in tissues as they react to micro vibrations.

Detection of prostate cancer using temporal sequences of ultrasound data: a large clinical feasibility study.

PURPOSE: This paper presents the results of a large study involving fusion prostate biopsies to demonstrate that temporal ultrasound can be used to accurately classify tissue labels identified in multi-parametric magnetic resonance imaging (mp-MRI) as suspicious for cancer. METHODS: We use deep learning to analyze temporal ultrasound data obtained from 255 cancer foci identified in mp-MRI. Each target is sampled in axial and sagittal planes. A deep belief network is trained to automatically learn the high-level latent features of temporal ultrasound data. A support vector machine classifier is then applied to differentiate cancerous versus benign tissue, verified by histopathology. Data from 32 targets are used for the training, while the remaining 223 targets are used for testing. RESULTS: Our results indicate that the distance between the biopsy target and the prostate boundary, and the agreement between axial and sagittal histopathology of each target impact the classification accuracy. In 84 test cores that are 5 mm or farther to the prostate boundary, and have consistent pathology outcomes in axial and sagittal biopsy planes, we achieve an area under the curve of 0.80. In contrast, all of these targets were labeled as moderately suspicious in mp-MR. CONCLUSION: Using temporal ultrasound data in a fusion prostate biopsy study, we achieved a high classification accuracy specifically for moderately scored mp-MRI targets. These targets are clinically common and contribute to the high false-positive rates associated with mp-MRI for prostate cancer detection. Temporal ultrasound data combined with mp-MRI have the potential to reduce the number of unnecessary biopsies in fusion biopsy settings.

Biomechanically Constrained Surface Registration: Application to MR-TRUS Fusion for Prostate Interventions.

In surface-based registration for image-guided interventions, the presence of missing data can be a significant issue. This often arises with real-time imaging modalities such as ultrasound, where poor contrast can make tissue boundaries difficult to distinguish from surrounding tissue. Missing data poses two challenges: ambiguity in establishing correspondences; and extrapolation of the deformation field to those missing regions. To address these, we present a novel non-rigid registration method. For establishing correspondences, we use a probabilistic framework based on a Gaussian mixture model (GMM) that treats one surface as a potentially partial observation. To extrapolate and constrain the deformation field, we incorporate biomechanical prior knowledge in the form of a finite element model (FEM). We validate the algorithm, referred to as GMM-FEM, in the context of prostate interventions. Our method leads to a significant reduction in target registration error (TRE) compared to similar state-of-the-art registration algorithms in the case of missing data up to 30%, with a mean TRE of 2.6 mm. The method also performs well when full segmentations are available, leading to TREs that are comparable to or better than other surface-based techniques. We also analyze robustness of our approach, showing that GMM-FEM is a practical and reliable solution for surface-based registration.

Computer-Aided Prostate Cancer Detection Using Ultrasound RF Time Series: In Vivo Feasibility Study.

UNLABELLED: This paper presents the results of a computer-aided intervention solution to demonstrate the application of RF time series for characterization of prostate cancer, in vivo. METHODS: We pre-process RF time series features extracted from 14 patients using hierarchical clustering to remove possible outliers. Then, we demonstrate that the mean central frequency and wavelet features extracted from a group of patients can be used to build a nonlinear classifier which can be applied successfully to differentiate between cancerous and normal tissue regions of an unseen patient. RESULTS: In a cross-validation strategy, we show an average area under receiver operating characteristic curve (AUC) of 0.93 and classification accuracy of 80%. To validate our results, we present a detailed ultrasound to histology registration framework. CONCLUSION: Ultrasound RF time series results in differentiation of cancerous and normal tissue with high AUC.

Augmenting MRI-transrectal ultrasound-guided prostate biopsy with temporal ultrasound data: a clinical feasibility study.

PURPOSE: In recent years, fusion of multi-parametric MRI (mp-MRI) with transrectal ultrasound (TRUS)-guided biopsy has enabled targeted prostate biopsy with improved cancer yield. Target identification is solely based on information from mp-MRI, which is subsequently transferred to the subject coordinates through an image registration approach. mp-MRI has shown to be highly sensitive to detect higher-grade prostate cancer, but suffers from a high rate of false positives for lower-grade cancer, leading to unnecessary biopsies. This paper utilizes a machine-learning framework to further improve the sensitivity of targeted biopsy through analyzing temporal ultrasound data backscattered from the prostate tissue. METHODS: Temporal ultrasound data were acquired during targeted fusion prostate biopsy from suspicious cancer foci identified in mp-MRI. Several spectral features, representing the signature of backscattered signal from the tissue, were extracted from the temporal ultrasound data. A supervised support vector machine classification model was trained to relate the features to the result of histopathology analysis of biopsy cores obtained from cancer foci. The model was used to predict the label of biopsy cores for mp-MRI-identified targets in an independent group of subjects. RESULTS: Training of the classier was performed on data obtained from 35 biopsy cores. A fivefold cross-validation strategy was utilized to examine the consistency of the selected features from temporal ultrasound data, where we achieved the classification accuracy and area under receiver operating characteristic curve of 94 % and 0.98, respectively. Subsequently, an independent group of 25 biopsy cores was used for validation of the model, in which mp-MRI had identified suspicious cancer foci. Using the trained model, we predicted the tissue pathology using temporal ultrasound data: 16 out of 17 benign cores, as well as all three higher-grade cancer cores, were correctly identified. CONCLUSION: The results show that temporal analysis of ultrasound data is potentially an effective approach to complement mp-MRI-TRUS-guided prostate cancer biopsy, specially to reduce the number of unnecessary biopsies and to reliably identify higher-grade cancers.

Ultrasound-Based Characterization of Prostate Cancer Using Joint Independent Component Analysis.

OBJECTIVE: This paper presents the results of a new approach for selection of RF time series features based on joint independent component analysis for in vivo characterization of prostate cancer. METHODS: We project three sets of RF time series features extracted from the spectrum, fractal dimension, and the wavelet transform of the ultrasound RF data on a space spanned by five joint independent components. Then, we demonstrate that the obtained mixing coefficients from a group of patients can be used to train a classifier, which can be applied to characterize cancerous regions of a test patient. RESULTS: In a leave-one-patient-out cross validation, an area under receiver operating characteristic curve of 0.93 and classification accuracy of 84% are achieved. CONCLUSION: Ultrasound RF time series can be used to accurately characterize prostate cancer, in vivo without the need for exhaustive search in the feature space. SIGNIFICANCE: We use joint independent component analysis for systematic fusion of multiple sets of RF time series features, within a machine learning framework, to characterize PCa in an in vivo study.

Ultrasound-guided characterization of interstitial ablated tissue using RF time series: feasibility study.

This paper presents the results of a feasibility study to demonstrate the application of ultrasound RF time series imaging to accurately differentiate ablated and nonablated tissue. For 12 ex vivo and two in situ tissue samples, RF ultrasound signals are acquired prior to, and following, high-intensity ultrasound ablation. Spatial and temporal features of these signals are used to characterize ablated and nonablated tissue in a supervised-learning framework. In cross-validation evaluation, a subset of four features extracted from RF time series produce a classification accuracy of 84.5%, an area under ROC curve of 0.91 for ex vivo data, and an accuracy of 85% for in situ data. Ultrasound RF time series is a promising approach for characterizing ablated tissue.

Tissue classification using ultrasound-induced variations in acoustic backscattering features.

Ultrasound (US) radio-frequency (RF) time series is an effective tissue classification method that enables accurate cancer diagnosis, but the mechanisms underlying this method are not completely understood. This paper presents a model to describe the variations in tissue temperature and sound speed that take place during the RF time series scanning procedures and relate these variations to US backscattering. The model was used to derive four novel characterization features. These features were used to classify three animal tissues, and they obtained accuracies as high as 88.01%. The performance of the proposed features was compared with RF time series features proposed in a previous study. The results indicated that the US-induced variations in tissue temperature and sound speed, which were used to derive the proposed features, were important contributors to the tissue typing capabilities of the RF time series. Simulations carried out to estimate the heating induced during the scanning procedure employed in this study showed temperature rises lower than 2 °C. The model and results presented in this paper can be used to improve the RF time series.

Ultrasound-based characterization of prostate cancer: an in vivo clinical feasibility study.

UNLABELLED: This paper presents the results of an in vivo clinical study to accurately characterize prostate cancer using new features of ultrasound RF time series. METHODS: The mean central frequency and wavelet features of ultrasound RF time series from seven patients are used along with an elaborate framework of ultrasound to histology registration to identify and verify cancer in prostate tissue regions as small as 1.7 mm x 1.7 mm. RESULTS: In a leave-one-patient-out cross-validation strategy, an average classification accuracy of 76% and the area under ROC curve of 0.83 are achieved using two proposed RF time series features. The results statistically significantly outperform those achieved by previously reported features in the literature. The proposed features show the clinical relevance of RF time series for in vivo characterization of cancer.

Respiratory syncytial virus matrix protein induces lung epithelial cell cycle arrest through a p53 dependent pathway.

Respiratory syncytial virus (RSV) is the major cause of viral respiratory infections in children. Our previous study showed that the RSV infection induced lung epithelial cell cycle arrest, which enhanced virus replication. To address the mechanism of RSV-induced cell cycle arrest, we examined the contribution of RSV-matrix (RSV-M) protein. In this report, we show that in both the A549 cell line and primary human bronchial epithelial (PHBE) cells, transfection with RSV-M protein caused the cells to proliferate at a slower rate than in control cells. The cell cycle analysis showed that RSV-M protein induced G1 phase arrest in A549 cells, and G1 and G2/M phase arrest in PHBE cells. Interestingly, RSV-M expression induced p53 and p21 accumulation and decreased phosphorylation of retinoblastoma protein (Rb). Further, induction of cell cycle arrest by RSV-M was not observed in a p53-deficient epithelial cell line (H1299). However, cell cycle arrest was restored after transfection of p53 cDNA into H1299 cells. Taken together, these results indicate that RSV-M protein regulates lung epithelial cell cycle through a p53-dependent pathway, which enhances RSV replication.

Inosine-containing RNA is a novel innate immune recognition element and reduces RSV infection.

During viral infections, single- and double-stranded RNA (ssRNA and dsRNA) are recognized by the host and induce innate immune responses. The cellular enzyme ADAR-1 (adenosine deaminase acting on RNA-1) activation in virally infected cells leads to presence of inosine-containing RNA (Ino-RNA). Here we report that ss-Ino-RNA is a novel viral recognition element. We synthesized unmodified ssRNA and ssRNA that had 6% to16% inosine residues. The results showed that in primary human cells, or in mice, 10% ss-Ino-RNA rapidly and potently induced a significant increase in inflammatory cytokines, such as interferon (IFN)-ß (35 fold), tumor necrosis factor (TNF)-α (9.7 fold), and interleukin (IL)-6 (11.3 fold) (p<0.01). Flow cytometry data revealed a corresponding 4-fold increase in influx of neutrophils into the lungs by ss-Ino-RNA treatment. In our in vitro experiments, treatment of epithelial cells with ss-Ino-RNA reduced replication of respiratory syncytial virus (RSV). Interestingly, RNA structural analysis showed that ss-Ino-RNA had increased formation of secondary structures. Our data further revealed that extracellular ss-Ino-RNA was taken up by scavenger receptor class-A (SR-A) which activated downstream MAP Kinase pathways through Toll-like receptor 3 (TLR3) and dsRNA-activated protein kinase (PKR). Our data suggests that ss-Ino-RNA is an as yet undescribed virus-associated innate immune stimulus.

Protein kinase R is a novel mediator of CD40 signaling and plays a critical role in modulating immunoglobulin expression during respiratory syncytial virus infection.

Effective immunoglobulin responses play a vital role in protection against most pathogens. However, the molecular mediators and mechanisms responsible for signaling and selective expression of immunoglobulin types remain to be elucidated. Previous studies in our laboratory have demonstrated that protein kinase R (PKR) plays a crucial role in IgE responses to double-stranded RNA (dsRNA) in vitro. In this study, we show that PKR plays a critical role in IgG expression both in vivo and in vitro. PKR(-/-) mice show significantly altered serum IgG levels during respiratory syncytial virus (RSV) infection. IgG2a expression is particularly sensitive to a lack of PKR and is below the detection level in mock- or RSV-infected PKR(-/-) mice. Interestingly, we show that upon activation by anti-CD40 and gamma interferon (IFN-γ), B cells from PKR(-/-) mice show diminished major histocompatibility complex class II (MHC II), CD80, and CD86 levels on the cell surface compared to wild-type (WT) mice. Our data also show that PKR is necessary for optimal expression of adhesion molecules, such as CD11a and ICAM-1, that are necessary for homotypic aggregation of B cells. Furthermore, in this report we demonstrate for the first time that upon CD40 ligation, PKR is rapidly phosphorylated and activated, indicating that PKR is an early and novel downstream mediator of CD40 signaling pathways.