Identification of Sparse Volterra Systems: An Almost Orthogonal Matching Pursuit Approach.

This paper considers identification of sparse Volterra systems. A method based on the almost orthogonal matching pursuit (AOMP) is proposed. The AOMP algorithm allows one to estimate one non-zero coefficient at a time until all non-zero coefficients are found without losing the optimality and the sparsity, thus avoiding the curse of dimensionality often encountered in Volterra system identification.

Persistence of Excitation for Identifying Switched Linear Systems.

This paper investigates the uniqueness of parameters via persistence of excitation for switched linear systems. The main contribution is a much weaker sufficient condition on the regressors to be persistently exciting that guarantees the uniqueness of the parameter sets and also provides new insights in understanding the relation among different subsystems. It is found that for uniquely determining the parameters of switched linear systems, the needed minimum number of samples derived from our sufficient condition is much smaller than that reported in the literature.

An automated treatment plan alert system to safeguard cancer treatments in radiation therapy.

In radiation oncology, the intricate process of delivering radiation to a patient is detailed by the patient's treatment plan, which is data describing the geometry, construction and strength of the radiation machine and the radiation beam it emits. The patient's life depends upon the accuracy of the treatment plan, which is left in the hands of the vendor-specific software automatically generating the plan after an initial patient consultation and planning with a medical professional. However, corrupted and erroneous treatment plan data have previously resulted in severe patient harm when errors go undetected and radiation proceeds. The aim of this paper is to develop an automatic error-checking system to prevent the accidental delivery of radiation treatment to an area of the human body (i.e., the treatment site) that differs from the plan's documented intended site. To this end, we develop a method for structuring treatment plan data in order to feed machine-learning (ML) classifiers and predict a plan's treatment site. In practice, a warning may be raised if the prediction disagrees with the documented intended site. The contribution of this paper is in the strategic structuring of the complex, intricate, and nonuniform data of modern treatment planning and from multiple vendors in order to easily train ML algorithms. A three-step process utilizing up- and down-sampling and dimension reduction, the method we develop in this paper reduces the thousands of parameters comprising a single treatment plan to a single two-dimensional heat map that is independent of the specific vendor or construction of the machine used for treatment. Our heat-map structure lends itself well to feed well-established ML algorithms, and we train-test random forest, softmax, k-nearest neighbors, shallow neural network, and support vector machine using real clinical treatment plans from several hospitals in the United States. The paper demonstrates that the proposed method characterizes treatment sites so well that ML classifiers may predict head-neck, breast, and prostate treatment sites with an accuracy of about 94%. The proposed method is the first step towards a thorough, fully automated error-checking system in radiation therapy.

Vocal pattern detection of depression among older adults.

Depression is a serious problem for many older adults but is too often undetected by the person, family or providers. Although vocal patterns have been successfully used to detect and predict depression in adults aged 18 to 65 years, no studies to date have included older adults. The study purpose was to determine whether vocal patterns associated with clinical depression in younger people also signify depression in older adults. An observational, repeated measures design was used to enroll 46 volunteer older adults who completed a semi-structured interview composed the 9-item Patient Health Questionnaire or PHQ-9 depression scale and selected speech measures. Recorded interviews were analysed by machine learning algorithms to evaluate whether vocal patterns may predict presence of depression in older adults. In this study, using the PHQ-9 and a supervised machine learning algorithm accurately predicted high and low depression scores between 86% and 92% of the time. Change in raw PHQ-9 scores between interview cycles was predicted within 1.17 points. These results provide strong and promising evidence that vocal patterns can be used effectively to detect clinical depression in adults who are 65 years and older.

Two-Stage Orthogonal Least Squares Methods for Neural Network Construction.

A number of neural networks can be formulated as the linear-in-the-parameters models. Training such networks can be transformed to a model selection problem where a compact model is selected from all the candidates using subset selection algorithms. Forward selection methods are popular fast subset selection approaches. However, they may only produce suboptimal models and can be trapped into a local minimum. More recently, a two-stage fast recursive algorithm (TSFRA) combining forward selection and backward model refinement has been proposed to improve the compactness and generalization performance of the model. This paper proposes unified two-stage orthogonal least squares methods instead of the fast recursive-based methods. In contrast to the TSFRA, this paper derives a new simplified relationship between the forward and the backward stages to avoid repetitive computations using the inherent orthogonal properties of the least squares methods. Furthermore, a new term exchanging scheme for backward model refinement is introduced to reduce computational demand. Finally, given the error reduction ratio criterion, effective and efficient forward and backward subset selection procedures are proposed. Extensive examples are presented to demonstrate the improved model compactness constructed by the proposed technique in comparison with some popular methods.

A Preliminary Study on Cleaning up Erroneous Data and Filling in Missing Values in A Medical Record.

This study investigates various possible approaches in dealing with missing or erroneous data sets. Cleaning up erroneous values and filling in missing values in a meaningful way play a critical role for the consequent data analysis and decision making. What makes a meaningful way depends on available prior information. In this preliminary study, a number of possible approaches are proposed and tested on an actual Huntington disease data, depending on the assumptions.

Dose reduction with adaptive bolus chasing computed tomography angiography.

Computed Tomography (CT) has become an effective diagnosis and evaluating tool in clinical; however, its radiation exposure has drawn great attention as more and more CT scans are performed every year. How to reduce the radiation dose and meanwhile keep the resultant CT images diagnosable becomes an important research topic. In this paper, we propose a dose reduction approach along with the adaptive bolus chasing CT Angiography (CTA) techniques, which are capable of tracking the contrast bolus peak over all the blood vessel segments during the CTA scan. By modulating the tube current (and collimator width) online, we can reduce the total radiation dose and maintain the contrast to noise ratio (CNR) of the blood vessel. Numerical experiments on reference DSA data sets show that by using the proposed dose reduction method, the effective radiation dose can be saved about 39%.

Fatigue and non-fatigue mathematical muscle models during functional electrical stimulation of paralyzed muscle.

Electrical muscle stimulation demonstrates potential for preventing muscle atrophy and for restoring functional movement after spinal cord injury (SCI). Control systems used to optimize delivery of electrical stimulation protocols depend upon the algorithms generated using computational models of paralyzed muscle force output. The Hill-Huxley-type model, while being highly accurate, is also very complex, making it difficult for real-time implementation. In this paper, we propose a Wiener-Hammerstein system to model the paralyzed skeletal muscle under electrical stimulus conditions. The proposed model has substantial advantages in identification algorithm analysis and implementation including computational complexity and convergence, which enable it to be used in real-time model implementation. Experimental data sets from the soleus muscles of fourteen subjects with SCI were collected and tested. The simulation results show that the proposed model outperforms the Hill-Huxley-type model not only in peak force prediction, but also in fitting performance for force output of each individual stimulation train.

Preliminary experimental results on controlled cardiac computed tomography: a phantom study.

In this paper, we present the preliminary experimental results on controlled cardiac computed tomography (CT), which aims to reduce the motion artifacts by means of controlling the x-ray source rotation speed. An innovative cardiac phantom enables us to perform this experiment without modifying the scanner. It is the first experiment on the cardiac CT with speed controlled x-ray source. Experimental results demonstrate that the proposed method successfully separates the phantom images at different phases (improve the temporal resolution) through controlling the x-ray speed.

Identification of a Modified Wiener-Hammerstein System and Its Application in Electrically Stimulated Paralyzed Skeletal Muscle Modeling.

Electrical muscle stimulation demonstrates potential for restoring functional movement and preventing muscle atrophy after spinal cord injury (SCI). Control systems used to optimize delivery of electrical stimulation protocols depend upon mathematical models of paralyzed muscle force outputs. While accurate, the Hill-Huxley-type model is very complex, making it difficult to implement for real-time control. As an alternative, we propose a modified Wiener-Hammerstein system to model the paralyzed skeletal muscle dynamics under electrical stimulus conditions. Experimental data from the soleus muscles of individuals with SCI was used to quantify the model performance. It is shown that the proposed Wiener-Hammerstein system is at least comparable to the Hill-Huxley-type model. On the other hand, the proposed system involves a much smaller number of unknown coefficients. This has substantial advantages in identification algorithm analysis and implementation including computational complexity, convergence and also in real time model implementation for control purposes.

Towards Identification of Wiener Systems with the Least Amount of a priori Information: IIR Cases.

In this paper, we investigate what constitutes the least amount of a priori information on the nonlinearity so that the linear part is identifiable in the non-Gaussian input case. Under the white noise input, three types of a priori information are considered including quadrant information, point information and monotonic information. In all three cases, identifiability has been established and the corresponding nonparametric identification algorithms are developed along with their convergence proofs.

Adaptive Bolus-chasing Computed Tomography Angiography in the Cases of Symmetric and Asymmetric Arterial Flows in Peripheral Arteries.

Synchronization of the contrast bolus peak and CT imaging aperture is a crucial issue for computed tomography angiography (CTA). It affects the CTA image quality and the amount of contrast dose. A whole-body CTA procedure means to scan from the abdominal aorta to pedal arteries. In this context, the synchronization is much more difficult with the asymmetric arterial flow in lower extremities than in the case of symmetric arterial flow. In this paper, we propose an adaptive optimal controller to chase the contrast bolus peak while it propagates in the aorta and lower extremities with symmetric flow. In the case of asymmetric flow after the contrast bolus splitting into two lower limbs, we propose a dynamic programming approach to cover the lower limbs optimally. Simulation and experimental results show that the proposed methods outperform the current constant-speed method substantially.

An in vitro evaluation of cone-beam breast CT methods.

Tomosynthesis was developed for mammography, especially breast cancer detection. However, its limited-angular range scan and resultant data incompleteness causes strong image artifacts and distortions. To address this problem, a hybrid imaging method was proposed in our previous work, which combines tomosynthesis and low-resolution CT into a single system to produce fewer artifacts and distortions at a similar dose level. The purpose of this paper is to evaluate the images reconstructed using the proposed method as compared with that using the conventional tomosynthesis method (ML-convex). For that purpose, the projection datasets are acquired in both numerical simulation and phantom experiments on our breast imaging platform. Three kinds of phantoms are used in our work, including a numerical phantom, a physical phantom and 8 in vitro phantoms made of breast specimens. In addition to visual comparison of the reconstructed images, we employ spatial resolution, image contrast, reconstruction error, and convergence rate to evaluate the results quantitatively. It is observed that the results from our method can achieve significantly higher spatial resolution, higher contrast, smaller reconstruction error and faster convergence rate. Besides, a reader study using 8 in vitro phantoms of breast specimens demonstrates the clinical potential of our method, which significantly outperforms the conventional tomosynthesis.

Adaptive Bolus Chasing Computed Tomography Angiography: Control Scheme and Experimental Results.

In this paper, a new adaptive bolus-chasing control scheme is proposed to synchronize the bolus peak in a patient's vascular system and the imaging aperture of a computed tomography (CT) scanner. The proposed control scheme is theoretically evaluated and experimentally tested on a modified Siemens SOMATOM Volume Zoom CT scanner. The first set of experimental results are reported on bolus-chasing CT angiography using realistic bolus dynamics, real-time CT imaging and adaptive table control with physical vasculature phantoms. The data demonstrate that the proposed control approach tracks the bolus propagation well, and clearly outperforms the constant-speed scheme that is the current clinical standard.

Selectable source rotational velocity for cardiac computed tomography.

The article analyzes the existing algorithms of cardiac imaging reconstructions using multidata segments and derives the ideal data segment conditions. A scheme of selectable velocity scanning is then proposed for cardiac computed tomography with a circular trajectory, which can cover any cardiac phase exactly or approximately to achieve a desirable temporal resolution. Numerical tests show that the selectable source rotational velocity method outperforms the traditional multidata segment algorithms. The proposed method can be also extended into the cases of helical scanning and variable heart rates.

A fast CT reconstruction scheme for a general multi-core PC.

Expensive computational cost is a severe limitation in CT reconstruction for clinical applications that need real-time feedback. A primary example is bolus-chasing computed tomography (CT) angiography (BCA) that we have been developing for the past several years. To accelerate the reconstruction process using the filtered backprojection (FBP) method, specialized hardware or graphics cards can be used. However, specialized hardware is expensive and not flexible. The graphics processing unit (GPU) in a current graphic card can only reconstruct images in a reduced precision and is not easy to program. In this paper, an acceleration scheme is proposed based on a multi-core PC. In the proposed scheme, several techniques are integrated, including utilization of geometric symmetry, optimization of data structures, single-instruction multiple-data (SIMD) processing, multithreaded computation, and an Intel C++ compilier. Our scheme maintains the original precision and involves no data exchange between the GPU and CPU. The merits of our scheme are demonstrated in numerical experiments against the traditional implementation. Our scheme achieves a speedup of about 40, which can be further improved by several folds using the latest quad-core processors.

Bolus characteristics based on Magnetic Resonance Angiography.

BACKGROUND: A detailed contrast bolus propagation model is essential for optimizing bolus-chasing Computed Tomography Angiography (CTA). Bolus characteristics were studied using bolus-timing datasets from Magnetic Resonance Angiography (MRA) for adaptive controller design and validation. METHODS: MRA bolus-timing datasets of the aorta in thirty patients were analyzed by a program developed with MATLAB. Bolus characteristics, such as peak position, dispersion and bolus velocity, were studied. The bolus profile was fit to a convolution function, which would serve as a mathematical model of bolus propagation in future controller design. RESULTS: The maximum speed of the bolus in the aorta ranged from 5-13 cm/s and the dwell time ranged from 7-13 seconds. Bolus characteristics were well described by the proposed propagation model, which included the exact functional relationships between the parameters and aortic location. CONCLUSION: The convolution function describes bolus dynamics reasonably well and could be used to implement the adaptive controller design.

Projection-based bolus detection for computed tomographic angiography.

Computed tomographic (CT) angiography is important for imaging studies on cardiovascular structures, peripheral vessels, and solid organs. In practice, a CT angiography scan is triggered by the bolus arrival at a prespecified anatomical location, which is determined using CT fluoroscopy. In this article, we propose a projection-based method adapted from the Grangeat formula to detect the bolus arrival. Then, we evaluate our new method in numerical and animal studies. Our results indicate that this method allows significantly better temporal resolution and is computationally more efficient, as compared with the image-based methods.

Controlled cardiac computed tomography.

Cardiac computed tomography (CT) has been a hot topic for years because of the clinical importance of cardiac diseases and the rapid evolution of CT systems. In this paper, we propose a novel strategy for controlled cardiac CT that may effectively reduce image artifacts due to cardiac and respiratory motions. Our approach is radically different from existing ones and is based on controlling the X-ray source rotation velocity and powering status in reference to the cardiac motion. We theoretically show that by such a control-based intervention the data acquisition process can be optimized for cardiac CT in the cases of periodic and quasiperiodic cardiac motions. Specifically, we formulate the corresponding coordination/control schemes for either exact or approximate matches between the ideal and actual source positions, and report representative simulation results that support our analytic findings.

Study of an adaptive bolus chasing CT angiography.

To improve imaging quality and to reduce contrast dose and radiation exposure, an adaptive bolus chasing CT angiography was proposed so that the bolus peak position and the imaging aperture can be synchronized. The performance of the proposed adaptive bolus chasing CT angiography was experimentally evaluated based on the actual bolus dynamics. The experimental results show that the controlled table position and the bolus peak position were highly consistent. The results clearly demonstrate that the proposed adaptive bolus chasing CT angiography that synchronizes the bolus peak position with the imaging aperture by a simple adaptive system is computationally and clinically feasible. Similar techniques may also be applied to conventional angiography to improve imaging quality and to reduce contrast dose and/or radiation exposure.