Probabilistic segmentation and intensity estimation for microarray images

We describe a probabilistic approach to simultaneous image segmentation and intensity estimation for complementary DNA microarray experiments. The approach overcomes several limitations of existing methods. In particular, it (a) uses a flexible Markov random field approach to segmentation that allows for a wider range of spot shapes than existing methods, including relatively common 'doughnut-shaped' spots; (b) models the image directly as background plus hybridization intensity, and estimates the two quantities simultaneously, avoiding the common logical error that estimates of foreground may be less than those of the corresponding background if the two are estimated separately; and (c) uses a probabilistic modeling approach to simultaneously perform segmentation and intensity estimation, and to compute spot quality measures. We describe two approaches to parameter estimation: a fast algorithm, based on the expectation-maximization and the iterated conditional modes algorithms, and a fully Bayesian framework. These approaches produce comparable results, and both appear to offer some advantages over other methods. We use an HIV experiment to compare our approach to two commercial software products: Spot and Arrayvision.     

A segmentation approach to long duration surface EMG recordings.

The purpose of this study was to develop an automatic segmentation method in order to identify postural surface EMG segments in long-duration recordings. Surface EMG signals were collected from the cervical erector spinae (CES), erector spinae (ES), external oblique (EO), and tibialis anterior (TA) muscles of 11 subjects using a bipolar electrode configuration. Subjects remained seated in a car seat over the 150-min data-collection period. The modified dynamic cumulative sum (MDCS) algorithm was used to automatically segment the surface EMG signals. Signals were rejected by comparison with an exponential mathematical model of the spectrum of a surface EMG signal. The average power ratio computed between two successive retained segments was used to classify segments as postural or surface EMG. The presence of a negative slope of a regression line fitted to the median frequency values of postural surface EMG segments was taken as an indication of fatigue. Alpha level was set at 0.05. The overall classification error rate was 8%, and could be performed in 25 min for a 150-min signal using a custom-built software program written in C (Borland Software Corporation, CA, USA). This error rate could be enhanced by concentrating on the rejection method, which caused most of the misclassification (6%). Furthermore, the elimination of non-postural surface EMG segments by the use of a segmentation approach enabled muscular fatigue to be identified in signals that contained no evidence of fatigue when analysed using traditional methods.     

Automatic wavelet-based retinal blood vessels segmentation and vessel diameter estimation

Automatic detection of retinal blood vessels and measurement of vessel diameter are important steps in the computer aided diagnosis in ophthalmology. Here, we present a new multi-scale vessel enhancement method based on complex continuous wavelet transform (CCWT). The parameters of CCWT are optimized to represent line structures in all directions and separate them from simple edges. The final vessel network is obtained by applying an adaptive histogram-based thresholding process along with a proper length filtering method. An efficient circular structure operator is employed on the centerline of vessels to estimate their diameters. The performance of the proposed method is measured on the publicly available DRIVE and STARE databases and compared with several state-of-the-art methods as well as second observer. The proposed method shows much higher accuracy (95%) and sensitivity (79%) in the same range of specificity (97%). The predictive value of it is higher than 72.9%. The vessel diameter estimation process also shows lower root mean square error compared to the existing methods and second observer.     

Reliability of muscle fibre conduction velocity distribution estimation from surface EMG

Most of the neuromuscular diseases induce changes in muscle fibre characteristics. For example, Duchenne dystrophy is characterized by a specific loss of fast fibres, and an increase in small diameter fibres. These morphological changes may lead to large modifications in the distribution of fibre diameters, possibly producing bimodal distributions. It has already been shown that it is possible to reveal these morphological modifications through the distribution of muscle fibre conduction velocity (MFCV) as estimated from needle electromyography (EMG) recordings. In this paper, we investigate whether such changes can be extracted from surface EMG signals.

Simulation allows generation of surface EMG signals in which features are well described especially at a morphological level. Therefore, we generated a database of simulated signals both in voluntary and electrically elicited contraction conditions using a bimodal distribution of muscle fibre diameters. MFCV distributions were computed using two short-term methods based on cross-correlation and peak-to-peak techniques for voluntary contraction signals, and using a deconvolution method in time domain for electrically elicited signals. MFCV distributions were compared with true ones, as generated from modelling.

This work reveals that estimating MFCV distribution through these methods does not appear yet as precise and robust enough to accurately characterize changes in redistribution of various muscle fibre diameters. However, it opens to new experimental protocols that can be explored in order to improve the robustness of MFCV distribution estimation for the follow-up of patients suffering from neuromuscular disorders.     

Automatic segmentation and supervised learning-based selection of nuclei in cancer tissue images

Analysis of preferential localization of certain genes within the cell nuclei is emerging as a new technique for the diagnosis of breast cancer. Quantitation requires accurate segmentation of 100-200 cell nuclei in each tissue section to draw a statistically significant result. Thus, for large-scale analysis, manual processing is too time consuming and subjective. Fortuitously, acquired images generally contain many more nuclei than are needed for analysis. Therefore, we developed an integrated workflow that selects, following automatic segmentation, a subpopulation of accurately delineated nuclei for positioning of fluorescence in situ hybridization-labeled genes of interest. Segmentation was performed by a multistage watershed-based algorithm and screening by an artificial neural network-based pattern recognition engine. The performance of the workflow was quantified in terms of the fraction of automatically selected nuclei that were visually confirmed as well segmented and by the boundary accuracy of the well-segmented nuclei relative to a 2D dynamic programming-based reference segmentation method. Application of the method was demonstrated for discriminating normal and cancerous breast tissue sections based on the differential positioning of the HES5 gene. Automatic results agreed with manual analysis in 11 out of 14 cancers, all four normal cases, and all five noncancerous breast disease cases, thus showing the accuracy and robustness of the proposed approach. ? Published 2012 Wiley Periodicals, Inc.     

Progressive resistance training in neuromuscular patients. Effects on force and surface EMG

In a randomized clinical trial the efficacy of strength training was studied in patients with myotonic dystrophy (n=33) and in patients with Charcot-Marie-Tooth disease (n=29). Measurements were performed at the start and after 8, 16 and 24 weeks of progressive resistance training. Surface electromyography (SEMG) of proximal leg muscles was recorded during isometric knee extension at maximum voluntary contraction (MVC) and at 20, 40, 60 and 80% of MVC. Changes in MVC, maximum electrical activity and torque–EMG ratios (TER) were calculated. Fatigue was studied by determining the changes in endurance and in the decline of the median frequency (F_med) of the SEMG during a sustained contraction at 80% MVC. These parameters showed no significant changes after the training in either of the diagnostic groups. Only the Charcot-Marie-Tooth training group showed a gradual significant increase in mean MVC over the whole training period (21%). After 24 weeks, the increase in mean RMS was similar (25%), but this was mainly due to a sharp rise during the first 8 weeks of training (20%). The findings indicate that the initial strength increase was due to a neural factor, while the subsequent increase was mainly due to muscle hypertrophy.     

Neural network committees for finger joint angle estimation from surface EMG signals

Background  

In virtual reality (VR) systems, the user's finger and hand positions are sensed and used to control the virtual environments. Direct biocontrol of VR environments using surface electromyography (SEMG) signals may be more synergistic and unconstraining to the user. The purpose of the present investigation was to develop a technique to predict the finger joint angle from the surface EMG measurements of the extensor muscle using neural network models.     

Improving parameter estimation for cell surface FRAP data

Fluorescence Recovery After Photobleaching (FRAP) using the confocal laser scanning microscope has become a standard method used to determine the diffusion coefficient and mobile fraction of cell surface proteins. A common experimental approach is to bleach a stripe on the cell surface and fit the ensuing FRAP curve to a 1D diffusion model. This model is derived from the time course of recovery to an infinitely long stripe bleached on an infinite flat plane. This choice of model dictates the use of a long bleach stripe. We demonstrate that, in the case of a long bleach stripe, the finite extent of the cell leads to significant errors in parameter estimation. We further show that these errors are reduced when a relatively small stripe is bleached. Unfortunately, diffusion to such a region is fundamentally two dimensional and therefore applying the 1D model of diffusion leads to significant errors. We derive an equation suitable for fitting to FRAP data acquired from small bleach regions and analyze its accuracy using simulated data. We propose that the use of a small bleach region along with a two dimensional diffusion model is the ideal protocol for cell surface FRAP.     

Principles of high-spatial-resolution surface EMG (HSR-EMG): single motor unit detection and application in the diagnosis of neuromuscular disorders

The most detailed information about the structural and functional characteristics of the muscle can be gained from the single motor unit (MU) action potential. In addition, information about the activity of a single MU is essential for the diagnosis of neuromuscular disorders. Due to the low spatial resolution of conventional bipolar surface electromyography (EMG), the resulting signal is a superposition of a large number of simultaneous active MUs. The difficulty is in separating the activity of a single MU from simultaneous active adjacent MUs. In contrast to other non-invasive EMG procedures, the high-spatial-resolution-EMG (HSR-EMG), which is based on the use of a multi-electrode array in combination with a spatial filter procedure, allows the detection of single MU activity in a non-invasive way. It opens access to the excitation spread and enables the determination of the conduction velocity in single MUs, and the localization of the endplate region. In addition, HSR-EMG detects changes in the electrical activities of the MUs which are typical in neuromuscular disorders. Using HSR-EMG it was possible to identify 97% of all investigated volunteers and patients with muscular or neuronal disorders. Therefore, HSR-EMG is suitable as a tool for the non-invasive diagnosis of neuromuscular disorders.     

Automatic detection of motor unit innervation zones of the external anal sphincter by multichannel surface EMG

A method to detect automatically the location of innervation zones (IZs) from 16-channel surface EMG (sEMG) recordings from the external anal sphincter (EAS) muscle is presented in order to guide episiotomy during child delivery. The new algorithm (2DCorr) is applied to individual motor unit action potential (MUAP) templates and is based on bidimensional cross correlation between the interpolated image of each MUAP template and two images obtained by flipping upside-down (around a horizontal axis) and left–right (around a vertical axis) the original one. The method was tested on 640 simulated MUAP templates of the sphincter muscle and compared with previously developed algorithms (Radon Transform, RT; Template Match, TM). Experimental signals were detected from the EAS of 150 subjects using an intra-anal probe with 16 equally spaced circumferential electrodes. The results of the three algorithms were compared with the actual IZ location (simulated signal) and with IZ location provided by visual analysis (VA) (experimental signals). For simulated signals, the inter quartile error range (IQR) between the estimated and the actual locations of the IZ was 0.20, 0.23, 0.42, and 2.32 interelectrode distances (IED) for the VA, 2DCorr, RT and TM methods respectively.     

Automatic liver segmentation in MRI images using an iterative watershed algorithm and artificial neural network

Precise liver segmentation in abdominal MRI images is one of the most important steps for the computer-aided diagnosis of liver pathology. The first and essential step for diagnosis is automatic liver segmentation, and this process remains challenging. Extensive research has examined liver segmentation; however, it is challenging to distinguish which algorithm produces more precise segmentation results that are applicable to various medical imaging techniques. In this paper, we present a new automatic system for liver segmentation in abdominal MRI images. The system includes several successive steps. Preprocessing is applied to enhance the image (edge-preserved noise reduction) by using mathematical morphology. The proposed algorithm for liver region extraction is a combined algorithm that utilizes MLP neural networks and watershed algorithm. The traditional watershed transformation generally results in oversegmentation when directly applied to medical image segmentation. Therefore, we use trained neural networks to extract features of the liver region. The extracted features are used to monitor the quality of the segmentation using the watershed transform and adjust the required parameters automatically. The process of adjusting parameters is performed sequentially in several iterations. The proposed algorithm extracts liver region in one slice of the MRI images and the boundary tracking algorithm is suggested to extract the liver region in other slices, which is left as our future work. This system was applied to a series of test images to extract the liver region. Experimental results showed positive results for the proposed algorithm.     

Automatic decomposition of multichannel intramuscular EMG signals

We describe an automatic algorithm for decomposing multichannel EMG signals into their component motor unit action potential (MUAP) trains, including signals from widely separated recording sites in which MUAPs exhibit appreciable interchannel offset and jitter. The algorithm has two phases. In the clustering phase, the distinct, recurring MUAPs in each channel are identified, the ones that correspond to the same motor units are determined by their temporal relationships, and multichannel templates are computed. In the identification stage, the MUAP discharges in the signal are identified using matched filtering and superimposition resolution techniques. The algorithm looks for the MUAPs with the largest single channel components first, using matches in one channel to guide the search in other channels, and using information from the other channels to confirm or refute each identification. For validation, the algorithm was used to decompose 10 real 6-to-8-channel EMG signals containing activity from up to 25 motor units. Comparison with expert manual decomposition showed that the algorithm identified more than 75% of the total 176 MUAP trains with an accuracy greater than 95%. The algorithm is fast, robust, and shows promise to be accurate enough to be a useful tool for decomposing multichannel signals. It is freely available at http://emglab.stanford.edu.     

EMG muscle scanning: Stability of hand-held surface electrodes

Electromyographic (EMG) muscle scanning measures 2-second samples of integrated muscle action potentials from individual neck and back muscles using a hand-held scanner with post-style surface electrodes separated by a fixed distance. This scanning technique is widely used to expeditiously assess muscle activity in the diagnosis of musculoskeletal disorders. In order to determine if the 2-second sample is sufficiently representative of electrical activity at a specific muscle site, the stability of the signal received by the hand-held scanner was measured bilaterally at six neck and back muscle sites over 40 seconds (20 2-second integration periods) in five seated subjects. Taking the overall average EMG activity as the true value, the mean number of 2-second integration periods required to achieve <5% standard error was calculated to be 1.47 for the 60 muscles tested. Only three sites required more than five integration periods. The validity of EMG scanning as a diagnostic tool is enhanced by longer integration periods     

The diagnostic yield of automatic EMG analysis in neuromuscular diseases

The aim of the study was to evaluate the diagnostic yield of automatic EMG analysis employed in differentiating normal from diseased muscle and myogenic, neural and spinal lesions. The material comprised 520 patients with neuromuscular diseases. Only diagnostically confirmed cases were included into the study. The control group comprised 51 healthy subjects. In all patients and healthy subjects routine EMG examination was performed by means of both the conventional technique and automatic method. On the basis of the statistical analysis of the material the authors concluded that the method of automated EMG using the Polish minicomputer Anops makes possible distinction of the main types of pathological processes affecting the muscles with higher than previously objectivity and reliability. They stress, however, the important role of the examiner and his experience.     

EMG muscle scanning: stability of hand-held surface electrodes

Electromyographic (EMG) muscle scanning measures 2-second samples of integrated muscle action potentials from individual neck and back muscles using a hand-held scanner with post-style surface electrodes separated by a fixed distance. This "scanning" technique is widely used to expeditiously assess muscle activity in the diagnosis of musculoskeletal disorders. In order to determine if the 2-second sample is sufficiently representative of electrical activity at a specific muscle site, the stability of the signal received by the hand-held scanner was measured bilaterally at six neck and back muscle sites over 40 seconds (20 2-second integration periods) in five seated subjects. Taking the overall average EMG activity as the "true" value, the mean number of 2-second integration periods required to achieve less than 5% standard error was calculated to be 1.47 for the 60 muscles tested. Only three sites required more than five integration periods. The validity of EMG scanning as a diagnostic tool is enhanced by longer integration periods.     

The methods of surface EMG analysis

The use of surface emg as a tool for quantification is described. First, the specific advantages of the surface emg are discussed. Techniques for analysis of the emg signal which estimate and detect the action potentials of the individual motor units and estimate some global properties of muscle activity are reviewed. A survey of data on relations between the properties of motor unit action potential, the properties of motor unit activity and the results of signal processing are given.     

Towards optimal multi-channel EMG electrode configurations in muscle force estimation: a high density EMG study.

Surface EMG is an important tool in biomechanics, kinesiology and neurophysiology. In neurophysiology the concept of high-density EMG (HD-EMG), using two dimensional electrode grids, was developed for the measurement of spatiotemporal activation patterns of the underlying muscle and its motor units (MU). The aim of this paper was to determine, with the aid of a HD-EMG grid, the relative importance of a number of electrode sensor configurations for optimizing muscle force estimation. Sensor configurations are distinguished in two categories. The first category concerns dimensions: the size of a single electrode and the inter electrode distance (IED). The second category concerns the sensor's spatial distribution: the total area from which signals are obtained (collection surface) and the number of electrodes per cm(2) (collection density). Eleven subjects performed isometric arm extensions at three elbow angles and three contraction levels. Surface-EMG from the triceps brachii muscle and the external force at the wrist were measured. Compared to a single conventional bipolar electrode pair, the force estimation quality improved by about 30% when using HD-EMG. Among the sensor configurations, the collection surface alone appeared to be responsible for the major part of the EMG based force estimation quality by improving it with 25%.     

EMG muscle scanning: Comparison to attached surface electrodes

Electromyographic (EMG) muscle scanning measures brief samples of integrated muscle action potentials from individual muscles using a hand-held scanner with post-style electrodes. This scanning technique is widely used by biofeedback practitioners to quickly assess muscle activity in the diagnosis of musculoskeletal disorders. In an effort to compare muscle scanning with the established technique using attached surface electrodes, ten healthy subjects (25–35 years old) were scanned using 2-second sampling at five bilateral muscle sites while simultaneously monitoring the same sites with surface electrodes. This was repeated using 10-second scanning samplings. Pearson's product-moment correlations between scanning for 2 seconds and prolonged surface recording at all sites were 0.54–0.89. Scanning for 10 seconds improved the correlations to 0.68–0.91. EMG scanning for 2 seconds compares favorably with attached surface electrode recording. Comparisons are further improved by 10-second scans.