Automatic Background Research Articles

Review of Automated Insulin Delivery Systems for Type 1 Diabetes and Associated Time in Range Outcomes.

Automated insulin delivery (AID) systems play an important role in the management of type 1 diabetes mellitus (T1DM). These systems include three components: a continuous glucose monitor (CGM), an insulin pump and an algorithm that adjusts the pump based on the CGM sensor glucose readings. They are not fully automated and still require the user to administer bolus insulin doses for food. Some AID systems have automatic correction boluses, while others only have automatic basal or background insulin adjustments. As CGM has become more accurate and the technology has evolved, AID systems have demonstrated improved glycaemic outcomes. The clinical evaluation of AID systems in randomized controlled trials and real-world studies have shown their utility in helping glycaemic management. In this review, we compare AID systems that are commercially available in the US and summarize the literature, with a special focus on time in range in T1DM. The review also discusses new AID systems on the horizon and explores considerations for personalized care.

Automatic Background Blurring Algorithm Based on Image Perception and Segmentation

Automatic Background Blurring Algorithm Based on Image Perception and Segmentation

Application of Multispectral Camera in Monitoring the Quality Parameters of Fresh Tea Leaves

The production of high-quality tea by Camellia sinensis (L.) O. Ktze is the goal pursued by both producers and consumers. Rapid, nondestructive, and low-cost monitoring methods for monitoring tea quality could improve the tea quality and the economic benefits associated with tea. This research explored the possibility of monitoring tea leaf quality from multi-spectral images. Threshold segmentation and manual sampling methods were used to eliminate the image background, after which the spectral features were constructed. Based on this, the texture features of the multi-spectral images of the tea canopy were extracted. Three machine learning methods, partial least squares regression, support vector machine regression, and random forest regression (RFR), were used to construct and train multiple monitoring models. Further, the four key quality parameters of tea polyphenols, total sugars, free amino acids, and caffeine content were estimated using these models. Finally, the effects of automatic and manual image background removal methods, different regression methods, and texture features on the model accuracies were compared. The results showed that the spectral characteristics of the canopy of fresh tea leaves were significantly correlated with the tea quality parameters (r ≥ 0.462). Among the sampling methods, the EXG_Ostu sampling method was best for prediction, whereas, among the models, RFR was the best fitted modeling algorithm for three of four quality parameters. The R2 and root-mean-square error values of the built model were 0.85 and 0.16, respectively. In addition, the texture features extracted from the canopy image improved the prediction accuracy of most models. This research confirms the modeling application of a combination of multi-spectral images and chemometrics, as a low-cost, fast, reliable, and nondestructive quality control method, which can effectively monitor the quality of fresh tea leaves. This provides a scientific reference for the research and development of portable tea quality monitoring equipment that has general applicability in the future.

A New Workflow for Drug Metabolite Profiling by Utilizing Advanced Tribrid Mass Spectrometry and Data-Processing Techniques.

Drug metabolite profiling utilizes liquid chromatography with tandem mass spectrometry (LC/MS/MS) to acquire ample information for metabolite identification and structural elucidation. However, there are still challenges in detecting and characterizing all potential metabolites that can be masked by a high biological background, especially the unknown and uncommon ones. In this work, a novel metabolite profiling workflow was established on a platform using a state-of-the-art tribrid high-resolution mass spectrometry (HRMS) system. Primarily, an instrumental method was developed based on the novel design of the tribrid system that facilitates in-depth MSn scans with two fragmentation devices. Additionally, different advanced data acquisition techniques were assessed and compared, and automatic background exclusion and deep-scan approaches were adopted to promote assay efficiency and metabolite coverage. Finally, different data-analysis techniques were explored to fully extract metabolite data from the information-rich MS/MS data sets. Overall, a workflow combining tribrid mass spectrometry and advanced acquisition methodology has been developed for metabolite characterization in drug discovery and development. It maximizes the tribrid HRMS platform's utility and enhances the coverage, efficiency, quality, and speed of metabolite profiling assays.

The Endodontic Complexity Assessment Tool (E-CAT): A digital form for assessing root canal treatment case difficulty.

To develop an evidence-based, valid and reliable assessment tool that educational establishments and dental practitioners may use to assess the complexity of root canal treatment (RCT) utilizing digital advancements. The study also aimed to provide a more objective definition of the term 'uncomplicated' root canal treatment as described by the Association for Dental Education in Europe (ADEE) and the European Society of Endodontology (ESE) undergraduate curriculum guidelines for Endodontology. The development process involved a narrative review of the literature to identify the complexity factors associated with root canal treatment on permanent teeth; an iterative development and analysis process to assess the weighting of these factors; and the programming of digital software to enhance the efficiency and user interface of the assessment form. Validation of the tool was sought with a panel of 35 specialist endodontists to assess clinical scenarios and assess the consensus inter-examiner agreement with the outcomes provided by the E-CAT. The inter-user and intra-user reliability studies were conducted with 15 dentists to evaluate the same clinical cases and by repeating the experiment 9months later. The ease of use of the form was also assessed. The E-CAT was successfully developed with a total of 19 complexity criteria and hosted on a secure server under the domain of www.e-cat.uk. The tool provides a smart interactive filtering mechanism and automatic background calculation of the risk scores. Three levels of complexity were defined: class I (uncomplicated), class II (moderately complicated) and class III (highly complicated). The consensus of the panel of endodontists had excellent agreement with the outcome of the E-CAT. The inter-user and intra-user reliability was found to be 0.80 and 0.90, respectively. The average time to assess a case was 1:36min. The E-CAT gave promising results providing an efficient and reliable platform to assess the complexity of cases undergoing root canal treatments. The study design allowed the formulation of a more objective definition to describe 'uncomplicated' root canal treatment as referred to by the ESE and ADEE guidelines. This study is advantageous for educational, public health and referral pathways.

Improving the efficiency of cleaning gas emissions from foundry

The work is devoted to the topical problem of increasing the efficiency of cleaning process of gases in packed-type scrubbers in order to reduce emissions of harmful substances and solid impurities into the atmosphere and improve the technical and economic indicators of wet gas cleaning systems. For this, a triangular cross-cut packing has been developed. Due to the size of the holes and their specific shape, the triangular packing provides longer contact of the packaging with water, which reduces water consumption. The packing is made of alloy steel AISI 316, so it can be used even in the most aggressive environment. In the work, the efficiency of cleaning with a scrubber with this packing is experimentally determined. The tests were performed at an ambient temperature of 23 °C. Several measurements were made for each type of packing, in a typical scrubber design. To conduct these industrial tests, a thermohygrometer-carbon dioxide gas analyzerAZ-7797 was used with high-precision NDIR (infrared) sensor, automatic background calibration (W/ABC), and compensation for deviations during long-term operation. The concentration measurement range is 0-9999 ppm with an error of ± 5 %. The gases were cooled in two stages. At first, they were cooled with ammonia water from 750 to 80 °C. Then they were fed to a primary gas refrigerator (basic type) of direct action, where its temperature were falled to 15 °C. Carbon dioxide concentration was measured after the first stage of cooling, after the final cooling, and after the cleaning process. The comparison is carried out with the most effective types of packing for wet gas cleaning today – chordal wood and Raschig rings. It is shown that the developed triangular packing with cross-shaped notches during the purification of coke oven gas from carbon dioxide improves the purification by 25 % in comparison with the wooden chord one, and by 15 % - with Raschig rings. This allows us to recommend it for widespread implementation.

A novel background updation algorithm using fuzzy c-means clustering for pedestrian detection

The task of pedestrian detection in video surveillance applications will face challenges like dynamic background changes, false human detection (shadow), and illumination variations. In literature, many approaches have been proposed to resolve these challenges. But their performance is not up to the mark. Thus this paper proposes efficient pedestrian detection including shadow removal and automatic dynamic background update. For this firstly, a background frame is initialized where no moving object is present. Then a background subtraction algorithm is applied to each of the key frames from the live video to detect the foreground objects (using fuzzy C means clustering followed by mean absolute difference). Later on this segmented foreground a contour is estimated and passed through the HOG classifier for pedestrian detection. The performance of the proposed approach has been compared using various datasets & state-of-the-art approaches and found to the best with an average precision of 98 %, unlike the others.

DeepHistReg: Unsupervised Deep Learning Registration Framework for Differently Stained Histology Samples

Background and objectiveThe use of several stains during histology sample preparation can be useful for fusing complementary information about different tissue structures. It reveals distinct tissue properties that combined may be useful for grading, classification, or 3-D reconstruction. Nevertheless, since the slide preparation is different for each stain and the procedure uses consecutive slices, the tissue undergoes complex and possibly large deformations. Therefore, a nonrigid registration is required before further processing. The nonrigid registration of differently stained histology images is a challenging task because: (i) the registration must be fully automatic, (ii) the histology images are extremely high-resolution, (iii) the registration should be as fast as possible, (iv) there are significant differences in the tissue appearance, and (v) there are not many unique features due to a repetitive texture. MethodsIn this article, we propose a deep learning-based solution to the histology registration. We describe a registration framework dedicated to high-resolution histology images that can perform the registration in real-time. The framework consists of an automatic background segmentation, iterative initial rotation search and learning-based affine/nonrigid registration. ResultsWe evaluate our approach using an open dataset provided for the Automatic Non-rigid Histological Image Registration (ANHIR) challenge organized jointly with the IEEE ISBI 2019 conference. We compare our solution to the challenge participants using a server-side evaluation tool provided by the challenge organizers. Following the challenge evaluation criteria, we use the target registration error (TRE) as the evaluation metric. Our algorithm provides registration accuracy close to the best scoring teams (median rTRE 0.19% of the image diagonal) while being significantly faster (the average registration time is about 2 seconds). ConclusionsThe proposed framework provides results, in terms of the TRE, comparable to the best-performing state-of-the-art methods. However, it is significantly faster, thus potentially more useful in clinical practice where a large number of histology images are being processed. The proposed method is of particular interest to researchers requiring an accurate, real-time, nonrigid registration of high-resolution histology images for whom the processing time of traditional, iterative methods in unacceptable. We provide free access to the software implementation of the method, including training and inference code, as well as pretrained models. Since the ANHIR dataset is open, this makes the results fully and easily reproducible.

Tomato leaf segmentation algorithms for mobile phone applications using deep learning

Leaf disease recognition using image processing techniques is currently a hot research topic. High disease recognition accuracies have been reported in literature particularly in studies that relied on lab images captured under controlled lighting and uniform background conditions. When these systems were tested under real field conditions, however, their performance dropped sharply. Studies have demonstrated that complex backgrounds significantly contribute to this drop in performance and that background removal enhances disease recognition accuracy. Unfortunately, a fast and accurate means to perform automatic background subtraction for leaf images has so far not yet been developed. In this paper, we propose fully convolutional neural networks to perform automatic background subtraction for leaf images captured in mobile applications. In a mobile application use case, the target leaf would typically dominate an image captured by the farmer. The leaf would also be surrounded by various background features including other leaves, stems, fruits, soil and mulch. The goal of the segmentation network is to remove these background features so that only the target leaf remains. A dataset that is representative of this scenario was prepared in order to train and test the proposed networks. It consists of 1,408 tomato leaf images captured under challenging field conditions and their respective ground truth masks. We report state-of-the-art leaf image segmentation performance of over 0.96 mean weighted intersection over union and over 0.91 boundary F1 score. In particular, our proposed segmentation network KijaniNet outperforms all competitors scoring 0.9766 mean weighted intersection over union and 0.9439 boundary F1 score. The proposed technique supersedes competing background subtraction algorithms yet does not require user intervention nor does it place constraints on the orientation, shape or illumination of the target leaf. Furthermore, all CNN models are able to perform segmentation of a 256x256 pixel RGB image in under 0.12 s when running on a GPU and in less than 2.1 s when running on a CPU; which is much faster than any of the competing techniques.

An Automatic Background Filtering Method for Detection of Road Users in Heavy Traffics Using Roadside 3-D LiDAR Sensors With Noises

Background filtering for roadside Light Detecting and Ranging (LiDAR) data could benefit detection of road users with high frequency and accuracy. But existing methods are unsatisfactory under traffic congestions and neglect noises of LiDAR sensors. This paper attempts to develop background identification and filtering methods for heavy traffics and LiDAR noises. In particular, a 3-D space-time diagram of the LiDAR's detection space over frames is divided into plenty of subspace-frames, where one subspace-frame refers to one subspace from the isometric division of detection space in one frame. For subspace-frames at the same position, an unsupervised clustering method with unknown number of clusters is applied for classifying subspace-frames into different groups and the background group is identified based on background characteristics. The proposed clustering method is a t-distribution mixture model with constraints, where weights follow a Dirichlet distribution so that some weights have the possibility to be 0. A Bayesian estimation framework is developed to carry out the clustering. Then each background subspace-frame is divided into cubes with equal lengths. By aggregating points over frames in the same cube, the cube with aggregated points is regarded as background cube. For background filtering, points in background cubes are background points and excluded. Finally, examined by data from a Velodyne VLP-32 LiDAR sensor, the proposed approach has better filtering results no matter under free-flow conditions or congestions. Using background filtering results for road users' detection is introduced as well.

Two-photon image-scanning microscopy with SPAD array and blind image reconstruction.

Two-photon excitation (2PE) laser scanning microscopy is the imaging modality of choice when one desires to work with thick biological samples. However, its spatial resolution is poor, below confocal laser scanning microscopy. Here, we propose a straightforward implementation of 2PE image scanning microscopy (2PE-ISM) that, by leveraging our recently introduced single-photon avalanche diode (SPAD) array detector and a novel blind image reconstruction method, is shown to enhance the effective resolution, as well as the overall image quality of 2PE microscopy. With our adaptive pixel reassignment procedure ∼1.6 times resolution increase is maintained deep into thick semi-transparent samples. The integration of Fourier ring correlation based semi-blind deconvolution is shown to further enhance the effective resolution by a factor of ∼2 - and automatic background correction is shown to boost the image quality especially in noisy images. Most importantly, our 2PE-ISM implementation requires no calibration measurements or other input from the user, which is an important aspect in terms of day-to-day usability of the technique.

Automatic Background Removal and Correction of Systematic Error Caused by Noise Expecting Bio-Raman Big Data Analysis.

Spectral pretreatments, such as background removal from Raman big data, are crucial to have a smooth link to advanced spectral analysis. Recently, we developed an automated background removal method, where we considered the shortest length of a spectrum by changing the scaling factor of the background spectrum. Here, we propose a practical way to correct the systematic error caused by noise from measurements. This correction has been realized to be more effective and accurate for automatic background removal.

Phase aberration compensation of digital holographic microscopy with curve fitting preprocessing and automatic background segmentation for microstructure testing

In the digital holographic microscopy, the phase aberration is a key problem limiting the quantitative phase measurement, especially for the microstructure whose phase distribution is dense with few and discontinuous background region. A numerical phase aberration compensation method with global curve fitting preprocessing and automatic extraction of the background region for microstructure testing is proposed. The global curve fitting is implemented to compensate most of the tilt, quadratic and partial high order aberrations and make the profile of the measured object significantly distinguishable. Then the background region is automatically extracted by directly segmenting the converted grayscale phase image. At last, the Zernike polynomial fitting is performed on the extracted background region, and the obtained coefficients are used to calculate the phase aberration of the whole phase image. Simulation and experimental results demonstrated that the proposed method is able to accurately extract background region and compensate the phase aberration for the complicated dense microstructure.

Hyperspectral Fluorescence LIDAR Based on a Liquid Crystal Tunable Filter for Marine Environment Monitoring

An innovative hyperspectral LIDAR instrument has been developed for applications in marine environment monitoring research activities, remotely detecting the fluorescence spectra produced in the spectral interval between 400 nm and 720 nm. The detection system is composed by a custom made photomultiplier charge integrating and measuring (CIM) unit, which makes automatic background signal subtraction, and a liquid crystal tunable filter (LCTF). The new instrument therefore has hyperspectral resolution and allows automatic background subtraction; it is compact and automated by custom software that permit to adapt the instrument properties depending on the environmental conditions. Laboratory tests to characterize the instrument performance have been carried out, concluding that this sensor can be employed in remote sites for Chl-a detection.

Multiplexed Quantitative In Situ Hybridization with Subcellular or Single-Molecule Resolution Within Whole-Mount Vertebrate Embryos: qHCR and dHCR Imaging (v3.0).

In situ hybridization based on the mechanism of hybridization chain reaction (HCR) enables multiplexed quantitative mRNA imaging in the anatomical context of whole-mount vertebrate embryos. Third-generation in situ HCR (v3.0) provides automatic background suppression throughout the protocol, dramatically enhancing performance and ease of use. In situ HCR v3.0 supports two quantitative imaging modes: (1) qHCR imaging for analog mRNA relative quantitation with subcellular resolution in an anatomical context and (2) dHCR imaging for digital mRNA absolute quantitation with single-molecule resolution in an anatomical context. Here, we provide protocols for qHCR and dHCR imaging in whole-mount zebrafish, chicken, and mouse embryos.

Multiplexed Quantitative In Situ Hybridization for Mammalian Cells on a Slide: qHCR and dHCR Imaging (v3.0).

In situ hybridization based on the mechanism of hybridization chain reaction (HCR) enables multiplexed quantitative mRNA imaging in diverse sample types. Third-generation in situ HCR (v3.0) provides automatic background suppression throughout the protocol, dramatically enhancing performance and ease of use. In situ HCR v3.0 supports two quantitative imaging modes: (1) qHCR imaging for analog mRNA relative quantitation with subcellular resolution and (2) dHCR imaging for digital mRNA absolute quantitation with single-molecule resolution. Here, we provide protocols for qHCR and dHCR imaging in mammalian cells on a slide.

Multiplexed Quantitative In Situ Hybridization for Mammalian or Bacterial Cells in Suspension: qHCR Flow Cytometry (v3.0).

In situ hybridization based on the mechanism of hybridization chain reaction (HCR) enables high-throughput expression profiling of mammalian or bacterial cells via flow cytometry. Third-generation in situ HCR (v3.0) provides automatic background suppression throughout the protocol, dramatically enhancing performance and ease of use. In situ HCR v3.0 supports analog mRNA relative quantitation via qHCR flow cytometry. Here, we provide protocols for multiplexed qHCR flow cytometry for mammalian or bacterial cells in suspension.

Automatic Background Construction and Object Detection Based on Roadside LiDAR

High-resolution micro traffic data are important to traffic safety and efficiency analysis. In this study, a roadside LiDAR sensor is used to collect 3D point clouds of surrounding objects. An automatic background construction and object detection method is proposed on the basis of the operation principle of the LiDAR sensor. In the algorithm, the discrete horizontal and vertical angular values can be considered as coordinates of pixels in digital images, and the farthest and mean distance of each azimuth are used to construct the background dataset. Then, vehicle and pedestrian points are extracted on the basis of the distance difference of each point with the same angular value between the target frame dataset and the background dataset. A density-based spatial clustering method is employed to group points into clusters and identify vehicles and pedestrians automatically. Finally, the performance of the algorithm is tested for roadside LiDAR data preprocessing under different traffic conditions. Our algorithm can perform well with high accuracy. Experimental results demonstrate that our algorithm can achieve a larger detection range and exhibit lower time complexity in comparison with a previously proposed algorithm.

Automatic Analyte-Ion Recognition and Background Removal for Ambient Mass-Spectrometric Data Based on Cross-Correlation.

Ambient mass spectrometry is a powerful approach for rapid, high-throughput, and direct sample analysis. Due to the open-air desorption and ionization processes, random fluctuations of ambient conditions can lead to large variances in mass-spectral signals over time. The mass-spectral data also can be further complicated due to multiple analytes present in the sample, background-ion signals stemming from the desorption/ionization source itself, and other laboratory-specific conditions (e.g., ambient laboratory air, nearby hardware). Thus, background removal and analyte-ion recognition can be quite difficult, particularly in non-targeted analyses. Here, we demonstrate the use of a cross-correlation-based approach to exploit chemical information encoded in the time domain to group/categorize mass-spectral peaks from a single analysis dataset. Ions that originate from ambient (or other) background species were readily flagged and removed from spectra; the result was a decrease in mass-spectral complexity by over 70% due to the removal of these background ions. Meanwhile, analyte ions were differentiated and categorized based on their time-domain profiles. With sufficient mass resolving-power and mass-spectral acquisition rate, isolated mass spectra containing ions from the same species in a sample could be extracted, leading to a reduction in mass-spectral complexity by more than 98% in some cases. The cross-correlation approach was tested with different ionization sources as well as reproducible and irreproducible sample introduction. Software built in-house enabled fully automated data processing, which can be performed within a few seconds. Ultimately, this approach provides an additional dimension of analyte separation in ambient mass-spectrometric analyses with information that is already recorded throughout the analysis.

Difference Distributions Applicable to Certain Health Physics Measurements.

This paper discusses calculational methods for the determination of the difference distributions associated with certain health physics measurements. These measurements include the check-source response counts relative to an initial reference count, the Albatross (i.e., HPI model 2080B) neutron tube counts relative to the gamma tube counts, and those that involve the use of the automatic background subtraction feature of portable health physics instrumentation. Examples are provided that illustrate the methods for a few specific measurements. For the comparison of a daily source count to its previously determined reference value, minimum counts for various scenarios were presented in order to reliably meet required tolerance limits of ±10% and ±20%. In either case, it was found beneficial that the initial reference readings be established using a counting interval of longer length than the daily interval. For the comparison of Albatross neutron counts to the gamma counts, it was seen that the relative error in the difference distribution was still related to that of the parent distribution. It was seen, therefore, that an effective way of reducing the gamma influence on the Albatross was to increase the counting interval used, hence yielding a significantly larger mean count per interval. For the automatic background subtraction feature, it was noted that net count values near 0 counts would almost always have the negative values of the difference distribution truncated to 0 counts by commercially available off-the-shelf instrumentation, whereas significant net count values would be displayed correctly but with a larger associated variance than the gross count itself. This paper therefore also provides a technical basis for the necessary source strength of a check source in order to meet daily limits, the gamma field limitations of the HPI 2080B Albatross, as well as the consequences of automatic background subtraction.