Baseline Estimation Algorithm Research Articles

RPE layer detection and baseline estimation using statistical methods and randomization for classification of AMD from retinal OCT

Background and Objective: Age-related macular degeneration (AMD) is a condition of the eye that affects the aged people. Optical coherence tomography (OCT) is a diagnostic tool capable of analyzing and identifying the disease affected retinal layers with high resolution. The objective of this work is to extract the retinal pigment epithelium (RPE) layer and the baseline (natural eye curvature, particular to every patient) from retinal spectral-domain OCT (SD-OCT) images. It uses them to find the height of drusen (abnormalities) in the RPE layer and classify it as AMD or normal.Methods: In the proposed work, the contrast enhancement based adaptive denoising technique is used for speckle elimination. Pixel grouping and iterative elimination based on the knowledge of typical layer intensities and positions are used to obtain the RPE layer. Using this estimate, randomization techniques are employed, followed by polynomial fitting and drusen removal to arrive at a baseline estimate. The classification is based on the drusen height obtained by taking the difference between the RPE and baseline levels. We have used a patient, wise classification approach where a patient is classified diseased if more than a threshold number of patient images have drusen of more than a certain height. Since all slices of an affected patient will not show drusen, we are justified in adopting this technique.Results: The proposed method is tested on a public data set of 2130 images/slices, which belonged to 30 patient volumes (15 AMD and 15 Normal) and achieved an overall accuracy of 96.66%, with no false positives. In comparison with existing works, the proposed method achieved higher overall accuracy and a better baseline estimate.Conclusions: The proposed work focuses on AMD/normal classification using a statistical approach. It does not require any training. The proposed method modifies the motion restoration paradigm to obtain an application-specific denoising algorithm. The existing RPE detection algorithm is modified significantly to make it robust and applicable even to images where the RPE is not very evident/there is a significant amount of perforations (drusen). The baseline estimation algorithm employs a powerful combination of randomization, iterative polynomial fitting, and pixel elimination in contrast to mere fitting techniques. The main highlight of this work is, it achieved an exact estimation of the baseline in the retinal image compared to the existing methods.

The accuracy evaluation method of baseline estimation algorithms in energy dispersive X‐ray fluorescence spectrum analysis

In energy dispersive X‐ray fluorescence analysis (EDXRF), many baseline estimation algorithms have been proposed for the accurate characteristic peak area. However, the true value of the characteristic peak area of measured spectrum is unknown and cannot be used to evaluate the accuracy of the baseline estimation algorithms. In this article, an assessment method was proposed based on Monte Carlo simulation, which can obtain the characteristic peak area, and evaluate the accuracy of the baseline estimation algorithms directly. Meanwhile, the accuracy and practicality of four baseline estimation algorithms were evaluated by the assessment method, which include statistics‐sensitive nonlinear iterative peak‐clipping (SINP), fast Fourier transform (FFT), adaptive iteratively reweighted penalized least squares (AirPLS), and automated iterative moving averaging (AIMA). Comparing the relative error of the characteristic peak area, AirPLS gave the best performance for baseline estimation in EDXRF.

Estimation of the foetal heart rate baseline based on singular spectrum analysis and empirical mode decomposition

In this paper, we propose a novel automatic baseline estimation algorithm for foetal heart rate (FHR), and we verify the correctness and effectiveness of the algorithm through clinical trials. First, Singular Spectrum Analysis (SSA) is used to improve the denoising algorithm during the pre-processing of FHR. Compared with the traditional denoising method that simply uses the sliding average method, the use of the SSA method to denoise, in terms of the overall aspect, not only maintains the signal trend that is consistent with the traditional method, but it also produces no additional signal decay and distortion, which verifies the correctness of the algorithm. The SSA method could ensure that the processed signal remains smooth, unlike the sliding average method that is susceptible to the influence of oscillatory noise, causing the signal to have still abruptly changed the noise after being filtered. Subsequently, we propose the Empirical Mode Decomposition (EMD) iterative pruning method for the extraction of the FHR baseline. This algorithm combines the characteristics of the two classical algorithms and includes the EMD to make the algorithm more adaptive. This algorithm overcomes the difficulties in the classical algorithms, and the extracted baseline can more accurately reflect the real baseline and improve the effect of acceleration and deceleration detection.

A Self-Calibrating IoT Portable Electrochemical Immunosensor for Serum Human Epididymis Protein 4 as a Tumor Biomarker for Ovarian Cancer.

Nowadays, analytical techniques are moving towards the development of smart biosensing strategies for the point-of-care accurate screening of disease biomarkers, such as human epididymis protein 4 (HE4), a recently discovered serum marker for early ovarian cancer diagnosis. In this context, the present work represents the first implementation of a competitive enzyme-labelled magneto-immunoassay exploiting a homemade IoT Wi-Fi cloud-based portable potentiostat for differential pulse voltammetry readout. The electrochemical device was specifically designed to be capable of autonomous calibration and data processing, switching between calibration, and measurement modes: in particular, firstly, a baseline estimation algorithm is applied for correct peak computation, then calibration function is built by interpolating data with a four-parameter logistic function. The calibration function parameters are stored on the cloud for inverse prediction to determine the concentration of unknown samples. Interpolation function calibration and concentration evaluation are performed directly on-board, thus reducing the power consumption. The analytical device was validated in human serum, demonstrating good sensing performance for analysis of HE4 with detection and quantitation limits in human serum of 3.5 and 29.2 pM, respectively, reaching the sensitivity that is required for diagnostic purposes, with high potential for applications as portable and smart diagnostic tool for point-of-care testing.

Estimation of Spectral Emissivity and S/Cu Ratio From Emissions of Copper Concentrates at the Flash Smelting Process

The project focused on the investigation of new sensing techniques in the copper production industry, specifically in the flash smelting of copper concentrate process. In this paper, we report a direct relationship between the visible and near-infrared emission spectra in the combustion of copper concentrates by changing some operating conditions such as the sulfur-copper and the oxygen ratios provided to the reaction zone. Spectral processing techniques are applied to the measured spectra. The first one aims to separate both continuous radiations mainly associated to incandescent particles and heating walls with discontinuous emissions associated with some emitting atoms and molecules. This goal was carried out using airPLS baseline estimation algorithm. The second processing technique aims to find the continuous emission only associated with the combustion of copper concentrate particles, eliminating the background spectra associated with the smelter walls. This goal was carried out by directly measuring walls emission at operating temperature and in the absence of flame. The most relevant results show that the estimation of the total radiation associated with each measured spectra is an intrinsic parameter of the process that can provide useful information to the operator that supervises the industrial process. It allows estimate quantitatively the sulfur-copper ratio in order to online monitor the mineral characteristics of the copper concentrate that is entering the process. On the other hand, the approach of a first prototype of the emissivity model for the copper concentrate particles, which validated with measurements, becomes a promising tool that will allow increasing the development of optoelectronic applications around this industry process.

An Adaptive and Fully Automated Baseline Correction Method for Raman Spectroscopy Based on Morphological Operations and Mollification.

Baseline drift is a commonly identified and severe problem in Raman spectra, especially for biological samples. The main cause of baseline drift in Raman spectroscopy is fluorescence generated within the sample. If left untreated, it will affect the following qualitative or quantitative analysis. In this paper, an adaptive and fully automated baseline estimation algorithm based on iteratively averaging morphological opening and closing operations is presented. The proposed method is able to deal with different shapes and amplitudes of baselines. It is tested on both simulated and experimental Raman spectra. Comparison of the proposed method with other morphology-based methods and a well-developed penalized least squares-based method is made. The results demonstrate the superior performance of the proposed method and its advantages-in terms of accuracy, adaptivity, and computing speed-over other algorithms. In general, this method can also be applied to other spectroscopic data or other types of one-dimensional data.

BASELINE ESTIMATION ALGORITHM WITH BLOCK ADJUSTMENT FOR MULTI-PASS DUAL-ANTENNA INSAR

Abstract. Baseline parameters and interferometric phase offset need to be estimated accurately, for they are key parameters in processing of InSAR (Interferometric Synthetic Aperture Radar). If adopting baseline estimation algorithm with single pass, it needs large quantities of ground control points to estimate interferometric parameters for mosaicking multiple passes dual-antenna airborne InSAR data that covers large areas. What’s more, there will be great difference between heights derived from different passes due to the errors of estimated parameters. So, an estimation algorithm of interferometric parameters with block adjustment for multi-pass dual-antenna InSAR is presented to reduce the needed ground control points and height’s difference between different passes. The baseline estimation experiments were done with multi-pass InSAR data obtained by Chinese dual-antenna airborne InSAR system. Although there were less ground control points, the satisfied results were obtained, as validated the proposed baseline estimation algorithm.

BASELINE ESTIMATION ALGORITHM WITH BLOCK ADJUSTMENT FOR MULTI-PASS DUAL-ANTENNA INSAR

Baseline parameters and interferometric phase offset need to be estimated accurately, for they are key parameters in processing of InSAR (Interferometric Synthetic Aperture Radar). If adopting baseline estimation algorithm with single pass, it needs large quantities of ground control points to estimate interferometric parameters for mosaicking multiple passes dual-antenna airborne InSAR data that covers large areas. What’s more, there will be great difference between heights derived from different passes due to the errors of estimated parameters. So, an estimation algorithm of interferometric parameters with block adjustment for multi-pass dual-antenna InSAR is presented to reduce the needed ground control points and height’s difference between different passes. The baseline estimation experiments were done with multi-pass InSAR data obtained by Chinese dual-antenna airborne InSAR system. Although there were less ground control points, the satisfied results were obtained, as validated the proposed baseline estimation algorithm.

Evaluating the fetal heart rate baseline estimation algorithms by their influence on detection of clinically important patterns

A correctly estimated component of fetal heart rate signal (FHR) – so called baseline – is a precondition for proper recognition of acceleration and deceleration patterns. A number of various algorithms for estimating the FHR baseline was proposed so far. However, there is no reference standard enabling their objective evaluation, and thus no methodology of comparing the different algorithms still exists. In this paper we propose a method for evaluation of automatically determined baseline in reference to a set of experts, based on ten separate groups of signals comprising typical variability patterns observed in the fetal heart rate. As it was proposed earlier [1], the given algorithm is evaluated based on the characteristic patterns detected using the obtained baseline, instead of direct analysis of the baseline shape. For the purpose of quantitative assessment of the estimated baseline a new synthetic inconsistency coefficient was applied. The proposed methodology enabled to evaluate eleven well-known algorithms. We believe that the method will be a valuable tool for assessment of the existing algorithms, as well as for developing the new ones.

Fetal heart rate baseline estimation with analysis of fetal movement signal.

In order to assign appropriate baseline estimation algorithms to different fetal heart rate tracing, a method to evaluate the fetal heart rate (FHR) baseline combining with the fetal movement information was proposed. Fetal actography and tocography were used to extract the fetal movement information. The results showed that the combined method, where the fetal movement detection result was the union of results of actography and tocography, achieved a better performance with the highest sensitivity and an acceptable positive predictive value (PPV). Furthermore, the mean absolute errors (MAEs) of basal FHR values between the two algorithms and the expert were calculated with respect to the duration coefficient of fetal movement. The results showed that the algorithm using empirical mode decomposition (EMD) and Kohonen neural network (KNN) had lower MAEs than a traditional linear baseline estimation algorithm as the duration coefficient increased. However, if the duration coefficient is below 0.2, the errors may be tolerant for the FHR baseline estimation by a linear baseline estimation algorithm, which indicates that different algorithms may be selected for FHR baseline estimation based on different duration coefficients of fetal movement.

Improving fetal heart rate signal interpretation by application of myriad filtering

Analysis of the fetal heart rate (FHR) signal is aimed at detection of clinically important patterns like bradycardia or tachycardia, accelerations and decelerations, as well as quantification of instantaneous FHR variability. Automated pattern recognition methods are based on estimation of so-called FHR baseline. It is a common opinion that the baseline estimation algorithm determines the efficiency of an entire process of quantitative signal analysis. Automated methods for baseline determination have been continuously improved for many years since there are still new classes of FHR signals being identified, for which the previous methods fail. The new method proposed for the baseline estimation is based on the weighted myriad filtering. The application of this method required filter parameter selection ensuring its operation according to clinical guidelines for baseline estimation. A very important feature of the myriad filtering is that there is no need for preliminary interpolation of signal loss segments. Our new algorithm was tested against two other methods. Thirty one-hour FHR recordings were selected for the analysis. Quantitative inconsistency was measured using differences between corresponding baseline samples. Additionally, the baselines were evaluated as regards their influence on identification of the acceleration and deceleration patterns. Obtained results allow us to conclude that the new algorithm delivers more reliable baselines particularly for signals with specific changes of the basal FHR level which has been recognized as difficult for baseline estimation.

A general-purpose baseline estimation algorithm for spectroscopic data

A common feature of many modern technologies used in proteomics--including nuclear magnetic resonance imaging and mass spectrometry--is the generation of large amounts of data for each subject in an experiment. Extracting the signal from the background noise, however, poses significant challenges. One important part of signal extraction is the correct identification of the baseline level of the data. In this article, we propose a new algorithm (the "BXR algorithm") for baseline estimation that can be directly applied to different types of spectroscopic data, but also can be specifically tailored to different technologies. We then show how to adapt the algorithm to a particular technology--matrix-assisted laser desorption/ionization Fourier transform ion cyclotron resonance mass spectrometry--which is rapidly gaining popularity as an analytic tool in proteomics. Finally, we compare the performance of our algorithm to that of existing algorithms for baseline estimation. The BXR algorithm is computationally efficient, robust to the type of one-sided signal that occurs in many modern applications (including NMR and mass spectrometry), and improves on existing baseline estimation algorithms. It is implemented as the function baseline in the R package FTICRMS, available either from the Comprehensive R Archive Network (http://www.r-project.org/) or from the first author.