Search

In recent years, the wide application of deep neural network models has brought serious risks of intellectual property rights infringement. Embedding a watermark in a network model is an effective solution to protect intellectual property rights. Although researchers have proposed schemes to add watermarks to models, they cannot prevent attackers from adding and overwriting original information, and embedding rates cannot be quantified. Therefore, aiming at these problems, this paper designs a high embedding rate and tamper-proof watermarking scheme. We employ wet paper coding (WPC), in which important parameters are regarded as wet blocks and the remaining unimportant parameters are regarded as dry blocks in the model. To obtain the important parameters more easily, we propose an optimized probabilistic selection strategy (OPSS). OPSS defines the unimportant-level function and sets the importance threshold to select the important parameter positions and to ensure that the original function is not affected after the model parameters are changed. We regard important parameters as an unmodifiable part, and only modify the part that includes the unimportant parameters. We selected the MNIST, CIFAR-10, and ImageNet datasets to test the performance of the model after adding a watermark and to analyze the fidelity, robustness, embedding rate, and comparison schemes of the model. Our experiment shows that the proposed scheme has high fidelity and strong robustness along with a high embedding rate and the ability to prevent malicious tampering.

Paper spray ionization has been used as a fast sampling/ionization method for the direct mass spectrometric analysis of biological samples at ambient conditions. Here, we demonstrated that by utilizing paper spray ionization-mass spectrometry (PSI-MS) coupled with field asymmetric waveform ion mobility spectrometry (FAIMS), predictive metabolic and lipidomic profiles of routine breast core needle biopsies could be obtained effectively. By the combination of machine learning algorithms and pathological examination reports, we developed a classification model, which has an overall accuracy of 87.5% for an instantaneous differentiation between cancerous and noncancerous breast tissues utilizing metabolic and lipidomic profiles. Our results suggested that paper spray ionization-ion mobility spectrometry-mass spectrometry (PSI-IMS-MS) is a powerful approach for rapid breast cancer diagnosis based on altered metabolic and lipidomic profiles.

The ACR Incidental Findings Committee (IFC) presents recommendations for managing adnexal masses incidentally detected on CT and MRI. These recommendations represent an update of those provided in our previous JACR 2013 white paper. The Adnexal Subcommittee, which included six radiologists with subspecialty expertise in abdominal imaging or ultrasound and one gynecologist, developed this algorithm. The recommendations draw from published evidence and expert opinion and were finalized by iterative consensus. Algorithm branches successively categorize adnexal masses based on patient characteristics (eg, pre- versus postmenopausal) and imaging features. They terminate with a management recommendation. The algorithm addresses most, but not all, pathologies and clinical scenarios. Our goal is to improve quality of care by providing guidance on how to manage incidentally detected adnexal masses.

One of the most widely used measures of scientific impact is the number of citations. However, due to its heavy-tailed distribution, citations are fundamentally difficult to predict but can be improved. This study was aimed at investigating the factors and parts influencing the citation number of a scientific paper in the otology field. Therefore, this work proposes a new solution that utilizes machine learning and natural language processing to process English text and provides a paper citation as the predicted results. Different algorithms are implemented in this solution, such as linear regression, boosted decision tree, decision forest, and neural networks. The application of neural network regression revealed that papers’ abstracts have more influence on the citation numbers of otological articles. This new solution has been developed in visual programming using Microsoft Azure machine learning at the back end and Programming Without Coding Technology at the front end. We recommend using machine learning models to improve the abstracts of research articles to get more citations.

Today, computer graphics and graphic image processing techniques have been widely used in daily life and industrial production. Due to the development of computers, computer graphics has brought more convenience to our daily life. In order to give full play to the value of computers, this paper takes the Hakka paper-cut art with local characteristics as the starting point, first of all its development history, artistic characteristics, compositional forms, expression techniques, cultural connotations, Hakka paper-cut patterns, and the symbolic meaning of folk customs, and then we design a visualization system for the paper-cut works of Gannan Hakka based on computer graphics. In addition, the system provides a solution for the integration of Gannan Hakka paper-cut art and Jiangxi native product packaging design and provides a reference for the theory and practice of modern native product packaging design.

Aiming at the problem of easy tampering and difficult integrity authentication of paper text documents, this paper proposes a robust content authentication method for printed documents based on text watermarking scheme resisting print-and-scan attack. Firstly, an authentication watermark signal sequence related to content of text document is generated based on the Logistic chaotic map model; then, the authentication watermark signal sequence is embedded into printed paper document by using a robust text watermarking scheme; finally, the watermark information is extracted from scanned image of paper document, and compared with the authentication watermark information calculated in real time by the text document content obtained by OCR technology, thereby performing content integrity authentication of the paper text documents. Experimental results show that our method can achieve the robust content integrity authentication of paper text documents, and can also accurately locate the tampering position. In addition, the document after embedding the watermark information has a good visual effect, and the text watermarking scheme has a large information capacity.

A new tool for the solution of electromigrative separations in paper-based microfluidics devices is presented. The implementation is based on a recently published complete mathematical model for describing these types of separations, and was developed on top of the open-source toolbox electroMicroTransport, based on OpenFOAM® , inheriting all its features as native 3D problem handling, support for parallel computation, and a GNU GPL license . The presented tool includes full support for paper-based electromigrative separations (including EOF and the novel mechanical and electrical dispersion effects), compatibility with a well-recognized electrolyte database, and a novel algorithm for computing and controlling the electric current in arbitrary geometries. Additionally, the installation on any operating system is available due to its novel installation option in the form of a Docker image. A validation example with data from literature is included, and two extra application examples are provided, including a 2D free-flow IEF problem, which demonstrates the capabilities of the toolbox for dealing with computational and physicochemical modeling challenges simultaneously. This tool will enable efficient and reliable numerical prototypes of paper-based electrophoretic devices to accompany the contemporary fast growth in paper-based microfluidics.

There is increasing focus on applying deep learning methods to electrocardiograms (ECGs), with recent studies showing that neural networks (NNs) can predict future heart failure or atrial fibrillation from the ECG alone. However, large numbers of ECGs are needed to train NNs, and many ECGs are currently only in paper format, which are not suitable for NN training. We developed a fully-automated online ECG digitisation tool to convert scanned paper ECGs into digital signals. Using automated horizontal and vertical anchor point detection, the algorithm automatically segments the ECG image into separate images for the 12 leads and a dynamical morphological algorithm is then applied to extract the signal of interest. We then validated the performance of the algorithm on 515 digital ECGs, of which 45 were printed, scanned and redigitised. The automated digitisation tool achieved 99.0% correlation between the digitised signals and the ground truth ECG (n = 515 standard 3-by-4 ECGs) after excluding ECGs with overlap of lead signals. Without exclusion, the performance of average correlation was from 90 to 97% across the leads on all 3-by-4 ECGs. There was a 97% correlation for 12-by-1 and 3-by-1 ECG formats after excluding ECGs with overlap of lead signals. Without exclusion, the average correlation of some leads in 12-by-1 ECGs was 60–70% and the average correlation of 3-by-1 ECGs achieved 80–90%. ECGs that were printed, scanned, and redigitised, our tool achieved 96% correlation with the original signals. We have developed and validated a fully-automated, user-friendly, online ECG digitisation tool. Unlike other available tools, this does not require any manual segmentation of ECG signals. Our tool can facilitate the rapid and automated digitisation of large repositories of paper ECGs to allow them to be used for deep learning projects.

The report of the American Association of Physicists in Medicine (AAPM) Task Group No. 132 published in 2017 reviewed rigid image registration and deformable image registration (DIR) approaches and solutions to provide recommendations for quality assurance and quality control of clinical image registration and fusion techniques in radiotherapy. However, that report did not include the use of DIR for advanced applications such as dose warping or warping of other matrices of interest. Considering that DIR warping tools are now readily available, discussions were hosted by the Medical Image Registration Special Interest Group (MIRSIG) of the Australasian College of Physical Scientists & Engineers in Medicine in 2018 to form a consensus on best practice guidelines. This position statement authored by MIRSIG endorses the recommendations of the report of AAPM task group 132 and expands on the best practice advice from the ‘Deforming to Best Practice’ MIRSIG publication to provide guidelines on the use of DIR for advanced applications.

The purpose of this article is to present algorithms for the diagnostic management of solitary bone lesions incidentally encountered on computed tomography (CT) and magnetic resonance (MRI) in adults. Based on review of the current literature and expert opinion, the Practice Guidelines and Technical Standards Committee of the Society of Skeletal Radiology (SSR) proposes a bone reporting and data system (Bone-RADS) for incidentally encountered solitary bone lesions on CT and MRI with four possible diagnostic management recommendations (Bone-RADS1, leave alone; Bone-RADS2, perform different imaging modality; Bone-RADS3, perform follow-up imaging; Bone-RADS4, biopsy and/or oncologic referral). Two algorithms for CT based on lesion density (lucent or sclerotic/mixed) and two for MRI allow the user to arrive at a specific Bone-RADS management recommendation. Representative cases are provided to illustrate the usability of the algorithms.

Background Brugada syndrome is a rare inherited arrhythmic syndrome with a coved type 1 ST-segment elevation on ECG and an increased risk of sudden death. Many studies have evaluated risk stratification performance based on ECG-derived parameters. However, since historical Brugada patient cohorts included mostly paper ECGs, most studies have been based on manual ECG parameter measurements. We hypothesized that it would be possible to run automated algorithm-based analysis of paper ECGs. We aimed: 1) to validate the digitization process for paper ECGs in Brugada patients; and 2) to quantify the acute class I antiarrhythmic drug effect on relevant ECG parameters in Brugada syndrome. Methods A total of 176 patients (30% female, 43 ± 13 years old) with induced type 1 Brugada syndrome ECG were included in the study. All of the patients had paper ECGs before and during class I antiarrhythmic drug challenge. Twenty patients also had a digital ECG, in whom printouts were used to validate the digitization process. Paper ECGs were scanned and then digitized using ECGScan software, version 3.4.0 (AMPS, LLC, New York, NY, USA) to obtain FDA HL7 XML format ECGs. Measurements were automatically performed using the Bravo (AMPS, LLC, New York, NY, USA) and Glasgow algorithms. Results ECG parameters obtained from digital and digitized ECGs were closely correlated (r = 0.96 ± 0.07, R2 = 0.93 ± 0.12). Class I antiarrhythmic drugs significantly increased the global QRS duration (from 113 ± 20 to 138 ± 23, p Conclusions Automated algorithm-based measurements of depolarization and repolarization parameters from digitized paper ECGs are reliable and could quantify the acute effects of class 1 antiarrhythmic drug challenge in Brugada patients. Our results support using computerized automated algorithm-based analyses from digitized paper ECGs to establish risk stratification decision trees in Brugada syndrome.

To develop and evaluate methods for assembling radiopaque printed paper sheets to realistic patient phantoms for CT dose and image quality testing. CT images of two patients were radiopaque printed with aqueous potassium iodide solution (0.6 g/ml) on paper. Two methods were developed for assembling the paper sheets to head and neck phantoms. (1) Printed sheets were fed to a paper-based 3D printer along with corresponding 3D printable STL files. (2) Paper stacks of 5-mm thickness were glued with toner, cut to the patient shape and assembled to a phantom. In a sample application study, both phantoms were examined with five different tube current settings. Images were reconstructed using filtered-back projection (FBP) and iterative reconstruction (AIDR 3D) with three strength levels. Dose length product (DLP), signal-to-noise ratios (SNR) and contrast-to-noise ratios (CNRs) were analysed. Data were analysed using 2-way analysis of variance (ANOVA). Both methods achieved anthropomorphic phantoms with detailed patient anatomy. The 3D printer yielded a precise reproduction of the external patient shape, but caused visible glue artefacts. Gluing with toner avoided these artefacts and yielded more flexibility with regard to phantom size. In the sample application study, non-inferior SNR and CNR and up to 83.7% lower DLP were achieved on the phantoms with AIDR 3D compared with FBP. Two methods for assembling radiopaque printed paper sheets to phantoms of individual patients are presented. The sample application demonstrates potential for simulation of patient imaging and systematic CT dose and image quality assessment. • Two methods were developed to create realistic CT phantoms of individual patients from radiopaque printed paper sheets. • Analysis of five tube current and four reconstruction settings on two radiopaque 3D printed patient phantoms yielded non-inferior SNR and CNR and up to 83.7% lower dose with iterative reconstruction in comparison with filtered back projection. • Radiopaque 3D printed phantoms can simulate patients and allow systematic analysis of CT dose and image quality parameters.

The amount of available scientific literature is increasing, and studies have proposed various methods for evaluating document-document similarity in order to cluster or classify documents for science mapping and knowledge discovery. In this paper, we propose hybrid methods for bibliographic coupling (BC) and linear evaluation of text or content similarity: We combined BC with BM25, Cosine, and PMRA to compare their performances with single methods in paper recommendation tasks using TREC Genomics Track 2005datasets. For paper recommendation, BC and text-based methods complement each other, and hybrid methods were better than single methods. The combinations of BC with BM25 and BC with Cosine performed better than BC with PMRA. The performances were best when the weights of BM25, Cosine, and PMRA were 0.025, 0.2, and 0.2, respectively, in hybrid methods. For paper recommendation, the combinations of BC with text-based methods were better than BC or text-based methods used alone. The choice of method should depend on the actual data and research needs. In the future, the underlying reasons for the differences in performance and the specific part or type of information they complement in text clustering or recommendation need to be examined.

The application of big data, radiomics, machine learning, and artificial intelligence (AI) algorithms in radiology requires access to large data sets containing personal health information. Because machine learning projects often require collaboration between different sites or data transfer to a third party, precautions are required to safeguard patient privacy. Safety measures are required to prevent inadvertent access to and transfer of identifiable information. The Canadian Association of Radiologists (CAR) is the national voice of radiology committed to promoting the highest standards in patient-centered imaging, lifelong learning, and research. The CAR has created an AI Ethical and Legal standing committee with the mandate to guide the medical imaging community in terms of best practices in data management, access to health care data, de-identification, and accountability practices. Part 2 of this article will inform CAR members on the practical aspects of medical imaging de-identification, strengths and limitations of de-identification approaches, list of de-identification software and tools available, and perspectives on future directions.

This letter points out a conceptual error made by the authors of a published paper, which presents a review and evaluation of computational methods in lncRNA identification. The error was made in the execution of the BASiNET method when considering an example file (toy model) made available by the authors with the aim of showing how a classification model could be stored in a file for later use. In this letter, this error is contextualized, the correct use of the BASiNET method is pointed out and the results of its correct execution to one of the datasets used in the review article are presented. The results clearly show the misuse of the method and present its correct use so that it can be fairly compared with other methods in the literature and prevent its misuse from being replicated by new studies.

Although paper-based transmission of medical information might seem outdated, it has proven efficient, and remains structurally safe from massive data leaks. As part of the ICIPEMIR project for improving medical imaging report, we explored the idea of structured data storage within a medical report, by embedding the data themselves in a QR-Code (and no URL-to-the-data). Three different datasets from ICIPEMIR were serialized, then encoded in a QR-Code. We compared 4 compression algorithms to reduce file size before QR-Encoding. YAML was the most concise format (character sparing), and allowed for embedding of a 2633-character serialized file within a QR-Code. The best compression rate was obtained with gzip, with a compression ratio of 2.32 in 15.7ms. Data were easily extracted and decompressed from a digital QR-Code using a simple command line. YAML file was also successfully recovered from the printed QR-Code with both Android and iOS smartphone. Minimal detected size was 3*3cm.

The ACR Committee on Incidental Findings presents recommendations for managing liver lesions that are incidentally detected on CT. These recommendations represent an update from the liver component of the ACR 2010 white paper on managing incidental findings in the pancreas, adrenal glands, kidneys, and liver. The Liver Subcommittee-which included five abdominal radiologists, one hepatologist, and one hepatobiliary surgeon-developed this algorithm. The recommendations draw from published evidence and expert opinion and were finalized by informal iterative consensus. Algorithm branches categorize liver lesions on the basis of patient characteristics and imaging features. They terminate with an assessment of benignity or a specific follow-up recommendation. The algorithm addresses most, but not all, pathologies and clinical scenarios. The goal is to improve the quality of care by providing guidance on how to manage incidentally detected liver lesions.

Letter to the Editor concerning "Describing center of pressure movement in stabilometry by ellipse area approximation" from Agnieszka Gołąb.

International audience; The objective of this article was to evaluate the evidence currently available about the clinical value of artificial intelligence (AI) in breast imaging. Nine experts from the disciplines involved in breast disease management – including physicists and radiologists – convened a meeting on June 3, 2019 to discuss the evidence for the use of this technology in plenary and focused sessions. Prior to the meeting, the group performed a literature review on predefined topics. This paper presents the consensus reached by this working group on recommendations for the future use of AI in breast screening and related research topics.

The migration of five different photoinitiators from kraft paper to two fatty food simulants, Tenax(®) and 95% ethanol, was investigated under different conditions. The effects of temperature and storage time, as well as the physicochemical properties of the photoinitiators on migration, were discussed. Mathematical models based on Fick's second law generated from two cases, single- and two-side contacts, were applied to predict the migration behaviour from the paper to the food simulants. The partition coefficients estimated from the model decreased with temperature. The diffusion coefficients of the selected photoinitiators from the paper ranged from 1.55 × 10(-10) to 7.54 × 10(-9) cm(2) s(-1) for Tenax and from 2.79 × 10(-9) to 8.03 × 10(-8) cm(2) s(-1) for 95% ethanol. The results indicate that the applied model can predict the migration of photoinitiators in the initial short period before equilibrium, and the migration from paper to Tenax through a single-side contact demonstrated an especially high concordance.

Highlights • In this position paper, we provide a collection of views on the role of AI in the COVID-19 pandemic, from the clinical needs to the design of AI-based systems, to the translation of the developed tools to the clinic. We highlight key factors in designing system solutions - per specific task; as well as design issues in managing the disease on the national level. We focus on three specific use-cases for which AI systems can be built: from the early disease detection, the management of the disease in a hospital setting, and building patient-specific predictive models that require the combination of imaging with additional clinical features. Infrastructure considerations and population modeling in two European countries will be described. This pandemic has made the practical and scientific challenges of making AI solutions very explicit. A discussion concludes this paper, with a list of challenges facing the community in the AI road ahead., In this position paper, we provide a collection of views on the role of AI in the COVID-19 pandemic, from clinical requirements to the design of AI-based systems, to the translation of the developed tools to the clinic. We highlight key factors in designing system solutions - per specific task; as well as design issues in managing the disease at the national level. We focus on three specific use-cases for which AI systems can be built: early disease detection, management in a hospital setting, and building patient-specific predictive models that require the combination of imaging with additional clinical data. Infrastructure considerations and population modeling in two European countries will be described. This pandemic has made the practical and scientific challenges of making AI solutions very explicit. A discussion concludes this paper, with a list of challenges facing the community in the AI road ahead.

The Canadian Association of Radiologists Incidental Findings Working Group consists of both academic subspecialty and general radiologists and is tasked with adapting and expanding upon the American College of Radiology incidental findings white papers to more closely apply to Canadian practice patterns, particularly more comprehensively dealing with the role of ultrasound and pursuing more cost-effective approaches to the workup of incidental findings without compromising patient care. Presented here are the 2020 Canadian guidelines for the management of hepatobiliary incidental findings. Topics covered include initial assessment of hepatic steatosis and cirrhosis, the workup of incidental liver masses identified on ultrasound and computed tomography (with algorithms presented), incidental gallbladder findings (wall thickening, calcification, and polyps), and management of incidental biliary dilatation.

Objective Most preventable adverse drug events and medication errors occur during medication ordering. Medication order entry and clinical decision support are available on paper or as computerized systems. In this post-hoc analysis we investigated frequency and clinical impact of blood glucose (BG) documentation- and user-related calculation errors as well as workflow deviations in diabetes management. We aimed to compare a paper-based protocol to a computerized medication management system combined with clinical workflow and decision support. Methods Seventy-nine hospitalized patients with type 2 diabetes mellitus were treated with an algorithm driven basal-bolus insulin regimen. BG measurements, which were the basis for insulin dose calculations, were manually entered either into the paper-based workflow protocol (PaperG: 37 patients) or into GlucoTab ® —a mobile tablet PC based system (CompG: 42 patients). We used BG values from the laboratory information system as a reference. A workflow simulator was used to determine user calculation errors as well as workflow deviations and to estimate the effect of errors on insulin doses. The clinical impact of insulin dosing errors and workflow deviations on hypo- and hyperglycemia was investigated. Results The BG documentation error rate was similar for PaperG (4.9%) and CompG group (4.0%). In PaperG group, 11.1% of manual insulin dose calculations were erroneous and the odds ratio (OR) of a hypoglycemic event following an insulin dosing error was 3.1 (95% CI: 1.4–6.8). The number of BG values influenced by insulin dosing errors was eightfold higher than in the CompG group. In the CompG group, workflow deviations occurred in 5.0% of the tasks which led to an increased likelihood of hyperglycemia, OR 2.2 (95% CI: 1.1–4.6). Discussion Manual insulin dose calculations were the major source of error and had a particularly strong influence on hypoglycemia. By using GlucoTab ® , user calculation errors were entirely excluded. The immediate availability and automated handling of BG values from medical devices directly at the point of care has a high potential to reduce errors. Computerized systems facilitate the safe use of more complex insulin dosing algorithms without compromising usability. In CompG group, missed or delayed tasks had a significant effect on hyperglycemia, while in PaperG group insufficient precision of documentation times limited analysis. The use of old BG measurements was clinically less relevant. Conclusion Insulin dosing errors and workflow deviations led to measurable changes in clinical outcome. Diabetes management systems including decision support should address nurses as well as physicians in a computerized way. Our analysis shows that such systems reduce the frequency of errors and therefore decrease the probability of hypo- and hyperglycemia.

The lateral-flow immunoassay (LFA) is a well-established diagnostic technology that has recently seen significant advancements due in part to the rapidly expanding fields of paper diagnostics and paper-fluidics. As LFA-based diagnostics become more complex, it becomes increasingly important to quantitatively determine important parameters during the design and evaluation process. However, current experimental methods for determining these parameters have certain limitations when applied to LFA systems. In this work, we describe our novel methods of combining paper and radioactive measurements to determine nanoprobe molarity, the number of antibodies per nanoprobe, and the forward and reverse rate constants for nanoprobe binding to immobilized target on the LFA test line. Using a model LFA system that detects for the presence of the protein transferrin (Tf), we demonstrate the application of our methods, which involve quantitative experimentation and mathematical modeling. We also compare the results of our rate constant experiments with traditional experiments to demonstrate how our methods more appropriately capture the influence of the LFA environment on the binding interaction. Our novel experimental approaches can therefore more efficiently guide the research process for LFA design, leading to more rapid advancement of the field of paper-based diagnostics.

This paper presents a portable quantitative method for the on-site determination of uric acid in urine using surface-enhanced Raman spectroscopy (SERS) and gold nanoparticle-coated paper as a substrate. A procedure was developed for the rapid preparation of cost-effective SERS substrates that enabled the adequate control of a homogeneous active area and the use of small quantities of gold nanoparticles per substrate. The standard addition method and multivariate curve resolution-alternating least squares (MCR-ALS) were applied to compensate for the matrix effect and to address overlapping bands between uric acid and interference SERS spectra. The proposed methodology demonstrated better performance than conventional univariate methods (in terms of linearity, accuracy and precision), a wide linear range (0-3.5 mmol L(-1)) and an adequate limit of detection (0.11 mmol L(-1)). For the first time, a portable SERS method coupled with chemometrics was developed for the routine analysis of uric acid at clinically relevant concentrations with minimal sample preparation and easy extension for the on-site determination of other biomarkers in complex sample matrices.

The assessment of pesticide residue levels demands fast, low cost and easy-to-use procedures which are not found in conventional methods. In this work, SERS substrates based on the deposition of gold nanoparticles (GNPs) on common office paper were prepared using a wax printer. These substrates combined with Data Driven Soft Independent Modelling of Class Analogies (DD-SIMCA), a one-class classifier algorithm, were used for detection of pesticide residues in water extracts of mango peels. Paper-based substrates made sample collection easier compared with conventional SERS methods, since few microliters of the pesticide aqueous extract from fruit peels needed to be deposited onto the substrate. Moreover, one-class classifiers dismiss the need for quantification or calibration curves. Classification of a fruit with residue levels in accordance to regulatory bodies' limits is based on a mathematical threshold. Just as in an authentication problem, all the possibilities for a given analysed fruit are now restricted to agreeing or not agreeing with current regulations. The performance of the one-class model was demonstrated by detecting thiabendazole (TBZ) residues at various mango samples, with all results being confirmed by HPLC-DAD analysis. The final model could distinguish samples with TBZ levels above the ones allowed by the Brazilian Health Regulatory Agency with 94% of selectivity and 92% of sensitivity, even in the presence of other pesticides.

The electrocardiogram (ECG) signal describes the heart’s electrical activity, allowing it to detect several health conditions, including cardiac system abnormalities and dysfunctions. Nowadays, most patient medical records are still paper-based, especially those made in past decades. The importance of collecting digitized ECGs is twofold: firstly, all medical applications can be easily implemented with an engineering approach if the ECGs are treated as signals; secondly, paper ECGs can deteriorate over time, therefore a correct evaluation of the patient’s clinical evolution is not always guaranteed. The goal of this paper is the realization of an automatic conversion algorithm from paper-based ECGs (images) to digital ECG signals. The algorithm involves a digitization process tested on an image set of 16 subjects, also with pathologies. The quantitative analysis of the digitization method is carried out by evaluating the repeatability and reproducibility of the algorithm. The digitization accuracy is evaluated both on the entire signal and on six ECG time parameters (R-R peak distance, QRS complex duration, QT interval, PQ interval, P-wave duration, and heart rate). Results demonstrate the algorithm efficiency has an average Pearson correlation coefficient of 0.94 and measurement errors of the ECG time parameters are always less than 1 mm. Due to the promising experimental results, the algorithm could be embedded into a graphical interface, becoming a measurement and collection tool for cardiologists.

In this paper, we propose an end-to-end approach to addressing QRS complex detection and measurement of Electrocardiograph (ECG) paper using convolutional neural networks (CNNs). Unlike conventional detection solutions that convert images to digital data, our method can directly detect QRS complex in images using Faster-RCNN, then the R-peak can be located and measured through a CNN. Validated by clinical ECG data in the St.-Petersburg Institute of Cardiological Technics 12-lead Arrhythmia Database and real ECG paper from Peking University People’s Hospital, the proposed method can achieve the recall of 98.32%, the precision of 99.01% in detecting and 0.012 mv of mean absolute error in measuring. Experimental results demonstrate the superior performance of our method over conventional solutions, which would pave the way to detect and measure ECG paper using CNNs.

In CERME12, our working group "Algorithmics" started its work as a newly established TWG. Since algorithms have always been at the heart of mathematics and their importance has been steadily increasing since the beginnings of theoretical computer science, the design and analysis of algorithms – called algorithmics (Traub 1964, Knuth 1985) – lies at the intersection of mathematics and computer science. For this reason, on the one hand, various algorithms and algorithmic activities have their traditional place in mathematics curricula at all levels. At the school level, mathematics and computer science have interacted since the 1980s, when many schools set up labs with computers equipped with programming software. On the other hand, many questions arise in the context of teaching and learning algorithms: a first, more applied group of questions aims at algorithms in mathematics education and curricula, a second, more theoretical group of questions seeks to clarify the concepts of algorithm and algorithmic thinking, + ID der Publikation: phlu_16641 + Art des Beitrages: Buchkapitel/Beitrag in Sammelband + Seiten: 100 - 107 + Sprache: Englisch + Letzte Aktualisierung: 2023-01-31 14:17:15

Images can be helpful for eliciting data in the form of responses from participants. Sometimes photographs can help participants speak about issues, events, thoughts and emotions which they find difficult to talk about. This paper discusses how photos can be used and how the data collected through their use in a discussion can be analysed using Correspondence Analysis (CA). Although CA is considered a quantitative tool for analysing data, this paper describes how it can be used with qualitative data.

Background Electrocardiograms (ECGs) are routinely recorded and stored in a variety of paper or scanned image format. Current ECG recording machines record ECG on graph paper, also it provides digitized ECG signal along with automated cardiovascular diagnosis (CVD). However, such recording machines cannot analyse preserved paper ECG records as it requires input in terms of digitized signal. Therefore, it is important to extract ECG signal from these preserved paper ECG records using digitization method. There are different paper degradations that adversely affect digitization process. The purpose of this work is to perform an image enhancement and digitization of the degraded ECG images to extract continuous ECG signal. Methods In this paper, we propose entropy-based bit plane slicing (EBPS) algorithm in which pre-processing is done using dominant color detection and local bit plane slicing. Maximum entropy based adaptive bit plane selection is applied to the pre-processed image. Discontinuous ECG correction (DECGC) is then done to produce continuous ECG signal. Results The algorithm is tested on 836 different degraded paper ECG records obtained from various diagnostic centers. After analysis with 101 known ground truth ECG signals the accuracy, sensitivity, specificity and overall F-measure of ECG is 99.42%, 99.69%, 99.81% and 99.26% respectively. The RMS error and correlation between the extracted digitized signal and ground truth for 101 cases is 0.040 and 99.89% respectively. Conclusions The EBPS method is able to remove all types of degradation in paper ECG records to generate a uniform digitized signal. Instead of manual measurement and prediction from archived paper ECG records, automated prediction (using already existing cardiovascular diagnosis software) is possible with the help of extracted digitized signal obtained using proposed digitization method, which will also help retrospective cardiovascular analysis.

BACKGROUND Computerized methods to analyze pain drawings (PDs) have been developed and may aid to measure the pain area more precisely. OBJECTIVE The aim of this study was to verify whether examiners can reproduce the patient's PDs with acceptable reliability. METHODS This was an intra-rater and inter-rater reliability study. The protocol consisted of 4 steps: (1) scanning of paper PDs; (2) sharing the digitalized PD images between examiners; (3) reproducing the PD images in the sketching application; and (4) calculating the pain area in pixels and percentages. We calculated intraclass correlation coefficients (ICCs; 2,1), the standard error of the measurement (SEM), and the smallest detectable difference (SDD). RESULTS Reliability was tested using 31 PDs from 17 patients in our database (11 female [64.7%], mean age: 53.23 ± 11.57 years). Intra-rater reliability varied from ICC (2,1) = 0.991 (95% confidence interval [CI] = 0.982 to 0.996; SEM = 3,432.45; SDD = 162.39 pixels; P

In the last 15 years, the segmentation of vessels in retinal images has become an intensively researched problem in medical imaging, with hundreds of algorithms published. One of the de facto benchmarking data sets of vessel segmentation techniques is the DRIVE data set. Since DRIVE contains a predefined split of training and test images, the published performance results of the various segmentation techniques should provide a reliable ranking of the algorithms. Including more than 100 papers in the study, we performed a detailed numerical analysis of the coherence of the published performance scores. We found inconsistencies in the reported scores related to the use of the field of view (FoV), which has a significant impact on the performance scores. We attempted to eliminate the biases using numerical techniques to provide a more realistic picture of the state of the art. Based on the results, we have formulated several findings, most notably: despite the well-defined test set of DRIVE, most rankings in published papers are based on non-comparable figures; in contrast to the near-perfect accuracy scores reported in the literature, the highest accuracy score achieved to date is 0.9582 in the FoV region, which is 1% higher than that of human annotators. The methods we have developed for identifying and eliminating the evaluation biases can be easily applied to other domains where similar problems may arise.

Understanding the impact of a publication by using bibliometric indices becomes an essential activity not only for universities and research institutes but also for individual academicians. This paper aims to provide a brief review of the current bibliometric tools used by authors and editors and proposes an algorithm to assess the relevance of the most common bibliometric tools to help the researchers select the fittest journal and know the trends of published submissions by using self-evaluation. We present a narrative review answering at least two related consecutive questions triggered by the topics mentioned above. How prestigious is a journal based on its most recent bibliometrics, so authors may choose it to submit their next manuscript? And, how can they self-evaluate/understand the impact of their whole publishing scientific life? We presented the main relevant definitions of each bibliometrics and grouped them in those oriented to evaluated journals or individuals. Also, we share with our readers our algorithm to assess journals before manuscript submission. Since there is a journal performance market and an article performance market, each one with its patterns, an integrative use of these metrics, rather than just the impact factor alone, might represent the fairest and most legitimate approach to assess the influence and importance of an acceptable research issue, and not only a sound journal in their respective disciplines.

Many complex physical systems exhibit a rich variety of discrete behavioural modes. Often, the system complexity limits the applicability of standard modelling tools. Hence, understanding the underlying physics of different behaviours and distinguishing between them is challenging. Although traditional machine learning techniques could predict and classify behaviour well, typically they do not provide any meaningful insight into the underlying physics of the system. In this paper we present a novel method for extracting physically meaningful clusters of discrete behaviour from limited experimental observations. This method obtains a set of physically plausible functions that both facilitate behavioural clustering and aid in system understanding. We demonstrate the approach on the V-shaped falling paper system, a new falling paper type system that exhibits four distinct behavioural modes depending on a few morphological parameters. Using just 49 experimental observations, the method discovered a set of candidate functions that distinguish behaviours with an error of 2.04%, while also aiding insight into the physical phenomena driving each behaviour. © 2019 Howison et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Efficient and safe detection of Bacillus anthracis spores (BAS) is a challenging task especially in bio-terror scenarios where the agent is concealed. We provide a proof-of-concept for the identification of concealed BAS inside mail envelopes using short-wave infrared hyperspectral imaging (SWIR-HSI). The spores and two other benign materials are identified according to their typical absorption spectrum. The identification process is based on the removal of the envelope signal using a new automatic new algorithm. This method may serve as a fast screening tool prior to using classical bioanalytical techniques.

Electrocardiography (ECG) is essential in many heart diseases. However, some ECGs are recorded by paper, which can be highly noisy. Digitizing the paper-based ECG records into a high-quality signal is critical for further analysis. We formulated the digitization problem as a segmentation problem and proposed a deep learning method to digitize highly noisy ECG scans. Our method extracts the ECG signal in an end-to-end manner and can handle different paper record layouts. In the experiment, our model clearly extracted the ECG waveform with a Dice coefficient of 0.85 and accurately measured the common ECG parameters with more than 0.90 Pearson's correlation. We showed that the end-to-end approach with deep learning can be powerful in ECG digitization. To the best of our knowledge, we provide the first approach to digitize the least informative noisy binary ECG scans and potentially be generalized to digitize various ECG records.

In recent years, there has been a dramatic increase in research papers about machine learning (ML) and artificial intelligence in radiology. With so many papers around, it is of paramount importance to make a proper scientific quality assessment as to their validity, reliability, effectiveness, and clinical applicability. Due to methodological complexity, the papers on ML in radiology are often hard to evaluate, requiring a good understanding of key methodological issues. In this review, we aimed to guide the radiology community about key methodological aspects of ML to improve their academic reading and peer-review experience. Key aspects of ML pipeline were presented within four broad categories: study design, data handling, modelling, and reporting. Sixteen key methodological items and related common pitfalls were reviewed with a fresh perspective: database size, robustness of reference standard, information leakage, feature scaling, reliability of features, high dimensionality, perturbations in feature selection, class balance, bias-variance trade-off, hyperparameter tuning, performance metrics, generalisability, clinical utility, comparison with traditional tools, data sharing, and transparent reporting.Key Points• Machine learning is new and rather complex for the radiology community.• Validity, reliability, effectiveness, and clinical applicability of studies on machine learning can be evaluated with a proper understanding of key methodological concepts about study design, data handling, modelling, and reporting.• Understanding key methodological concepts will provide a better academic reading and peer-review experience for the radiology community.

Author summary Conferences are great venues for disseminating algorithmic bioinformatics results, but they unfortunately do not offer an opportunity to make major revisions in the way that journals do. As a result, it is not possible for authors to fix mistakes that might be easily correctable but nevertheless can cause the paper to be rejected. As a reviewer, I wish that I had the opportunity to tell the authors, “Hey, you forgot to do this really important thing, without which it is hard to accept the paper, but if you could go back and fix it, you might have a great paper for the conference.” This lack of a back and forth can be especially problematic for first-time submitters or those from outside the field, e.g., biologists. In this article, I outline Ten Simple Rules to follow when writing an algorithmic bioinformatics conference paper to avoid having it rejected.

Background and Objective Cardiotocography (CTG) is the most popular prenatal diagnostic examination, which includes continuous monitoring of foetal heart rate (FHR, bpm) and uterine contraction (UC, mmHg) signals. Compared with CTG paper reports, digitized reports have better storage, transmission and retrieval capabilities, in addition to being able to assess foetal health. However, most of the existing digitization methods extract signals from paper reports with colour background grids, and they cannot extract signals completely from paper reports with binary background grids, which are widely used in clinical CTG monitoring. Moreover, the existing digitization algorithms often neglect the image distortion caused by the imaging equipment. Methods To overcome the above drawbacks, a digitization method for CTG paper reports with binary background grids taken by smartphones is proposed in this paper. In the stage of removing the grid background, a region merger based on super-pixels and an improved binary line mask removal are designed. Then, signal extraction is performed separately according to the different states of the image column. Through a projection map used to synchronize the signal, the distortion effect of the mobile phone is removed. Results The experimental results show that the average correlation coefficient (ρ) between the recovery signal obtained by the proposed method and the reference signal is 0.9855±0.0108 for FHR and 0.9866 ± 0.1020 for UC, and the root mean square errors (RMSE) of FHR and UC processed by the proposed method are 1.0366 ± 0.4953 and 2.0355 ± 1.0246, and the mean absolute errors (MAE) of FHR and UC processed by the proposed method are 0.8735 ± 0.0684 and 1.4991 ± 0.2837, which are higher than those of the existing digitization methods. Compared with clinical signals, no significant difference is found in the feature of digitization CTG. Conclusion The proposed digitization method is a promising useful tool to realize the electronization of CTG signal.

Background After several neutral telehealth trials, the positive findings and subsequent Food and Drug Administration approval of an implantable pulmonary arterial pressure monitor (PAPM) led to renewed interest in remote patient monitoring (RPM). Here we seek to provide contemporary guidance on the appropriate use of RPM technology. Results Although early trials of external RPM devices suggested benefit, subsequent multicenter trials failed to demonstrate improved outcomes. Monitoring features of cardiac implantable electronic devices (CIEDs) also did not deliver improved HF outcomes, newer, multisensor algorithms may be better. Earlier technologies using direct pressure measurement via implanted devices failed to show benefit owing to complications or failure. Recently, 1 PAPM showed benefit in a randomized controlled trial. Although not showing cost reduction, cost-benefit analysis of that device suggests that it may meet acceptable standards. Additional research is warranted and is in progress. Consumer-owned electronic devices are becoming more pervasive and hold hope for future benefit in HF management. Practical aspects around RPM technology include targeting of risk populations, having mechanisms to ensure patient adherence to monitoring, and health care team structures that act on the data. Conclusions Based on available evidence, routine use of external RPM devices is not recommended. Implanted devices that monitor pulmonary arterial pressure and/or other parameters may be beneficial in selected patients or when used in structured programs, but the value of these devices in routine care requires further study. Future research is also warranted to better understand the cost-effectiveness of these devices.

Medicine has entered the digital era, driven by data from new modalities, especially genomics and imaging, as well as new sources such as wearables and Internet of Things. As we gain a deeper understanding of the disease biology and how diseases affect an individual, we are developing targeted therapies to personalize treatments. There is a need for technologies like Artificial Intelligence (AI) to be able to support predictions for personalized treatments. In order to mainstream AI in healthcare we will need to address issues such as explainability, liability and privacy. Developing explainable algorithms and including AI training in medical education are many of the solutions that can help alleviate these concerns.

Adsorption isotherms of 3 selected paper-based packaging materials, that is, vegetable parchment (VP) paper, Kraft paper, and solid-bleached-sulfate (SBS) paperboard, were determined at 3 different temperatures (25, 40, and 50 degrees C). The GAB isotherm model was found to fit adequately for describing experimental adsorption isotherm data for the paper samples. The monolayer moisture content of the paper samples decreased with increase in temperature, which is in the range of 0.0345 to 0.0246, 0.0301 to 0.0238, and 0.0318 to 0.0243 g water/g solid for the MG paper, the Kraft paper, and the SBS paperboard, respectively. The net isosteric heats of sorption (q(st)) for the paper samples decreased exponentially with increase in moisture content after reaching the maximum values of 18.51, 27.39, and 26.80 kJ/mol for the VP paper, the Kraft paper, and the SBS paperboard, respectively, at low-moisture content. The differential enthalpy and entropy of 3 paper samples showed compensation phenomenon with the isokinetic temperature of 399.7 K indicating that water vapor had been adsorbed onto the paper samples with the same mechanism. Depending on the paper material, tensile strength of paper samples was affected by moisture content.

Interferon (IFN)-γ release assays (IGRAs) are probably the most accurate tests for the detection of latent Mycobacterium tuberculosis infection, but IGRAs are labour intensive and the transport of samples over longer distances is difficult. IFN-γ-induced protein (IP)-10 is expressed at 100-fold higher levels than IFN-γ, and IP-10 release assays have comparable performance to IGRAs. The aim of this study was to explore the diagnostic potential of a novel IP-10 release assay based on dried plasma spots (DPS). The presence of IP-10 and IFN-γ was determined in plasma and in DPS by ELISA. Diagnostic algorithms for plasma and DPS tests for IP-10 were developed on a training cohort comprising 60 tuberculosis (TB) patients and 59 healthy controls. Diagnostic accuracy was assessed in a validation cohort comprising 78 TB patients and 98 healthy controls. Plasma was measured in Spain and DPS samples were sent to Denmark using the conventional postal service for analysis. IP-10 was readily detectable in both plasma and DPS, and correlation was excellent (r2 = 0.95). QuantiFERON-TB Gold In-Tube (QFT-TB) and IP-10 in DPS and plasma rendered comparable sensitivity (78%, 82% and 84%, respectively), specificity (100%, 97% and 97%, respectively) and indeterminate rates (p>0.55). The DPS-based IP-10 test has comparable diagnostic accuracy to the QFT-TB and samples can be sent via conventional mail over long distances for analysis without affecting the results.

The use of continuous intravenous regular human insulin (RHI) infusion is often necessary to achieve glycemic control in critically ill patients. Because insulin is a high-risk medication owing to the potential for severe hypoglycemia, it is imperative that insulin infusion algorithms are designed to be safe, effective, and instructionally clear. The safety and efficacy of our intravenous RHI infusion algorithm protocol has been previously established (Nutrition 2008;24:536-45); however, the protocol violations by nursing personnel were not examined. The objective of this study was to assess nursing adherence to our RHI infusion algorithm.Continuous RHI infusion algorithm violations were retrospectively evaluated in adult patients admitted to a trauma intensive care unit who received concurrent continuous enteral and/or parenteral nutrition therapy and our algorithm for at least 3 d. Blood glucose (BG) monitoring was done every 1 to 2 h with the target BG at 70 to 149 mg/dL (3.9 to 8.3 mmol/L). Nursing adherence to the RHI infusion protocol was evaluated for each patient by comparing the adjustments in insulin infusion rates documented by the nursing personnel with the prescribed adjustments per our graduated continuous intravenous RHI infusion algorithm.A total of 4150 BG measurements necessitating the determination of the appropriate RHI dosage rate by nursing personnel in 40 patients occurred during the observational period. The target BG was achieved for a mean of 20 h/d and none of the patients had an episode of severe hypoglycemia (BG40 mg/dL or 2.2 mmol/L). The overall rate of algorithm violations was 12.1%. The algorithm violations accounted for a single episode of mild to moderate hypoglycemia (BG 40 to 60 mg/dL or 2.2 to 3.3 mmol/L) in 4 patients and 65 total episodes of hyperglycemia (BG ≥150 mg/dL or 8.3 mmol/L) in 18 patients.An adherence rate of nearly 90% is indicative of excellent nursing adherence compared with other published paper-based algorithms that examined protocol adherence. These data, combined with our previously published glycemic control data, indicate that this RHI infusion algorithm is an effective one for hyperglycemic trauma patients receiving continuous enteral and/or parenteral nutritional therapy.

The application of big data, radiomics, machine learning, and artificial intelligence (AI) algorithms in radiology requires access to large data sets containing personal health information. Because machine learning projects often require collaboration between different sites or data transfer to a third party, precautions are required to safeguard patient privacy. Safety measures are required to prevent inadvertent access to and transfer of identifiable information. The Canadian Association of Radiologists (CAR) is the national voice of radiology committed to promoting the highest standards in patient-centered imaging, lifelong learning, and research. The CAR has created an AI Ethical and Legal standing committee with the mandate to guide the medical imaging community in terms of best practices in data management, access to health care data, de-identification, and accountability practices. Part 1 of this article will inform CAR members on principles of de-identification, pseudonymization, encryption, direct and indirect identifiers, k-anonymization, risks of reidentification, implementations, data set release models, and validation of AI algorithms, with a view to developing appropriate standards to safeguard patient information effectively.

I review my scientific career in terms of eight areas and 16 papers. The first two areas are associated with childhood. The other six are associated with residual maximum likelihood (REML), canonical transformation, inbreeding in selected populations, average information residual maximum likelihood (AIREML), the computer program ASReml and sampling-based estimation.

A facile strategy, engineered for low-cost mass production, to synthesize biomass-derived activated carbon/reduced graphene oxide composite electrodes (GBPCs) by one-pot carbonization of blotting papers containing graphene oxide (GO) and zinc chloride (ZnCl2) was proposed. Benefitting from the water absorption characteristic of blotting papers in which the voids between the celluloses can easily absorb the GO/ZnCl2 solution, the chemical activation and reduction of GO can synchronously achieve via one-step carbonization process. As a result, the GBPCs deliver a large specific surface area to accumulate charge. Simultaneously, it provides high conductivity for electron transfer. The symmetric supercapacitor assembled with the optimal GBPCs in 6 M KOH electrolyte exhibits an excellent specific capacitance of 204 F g&minus, 1 (0.2 A g&minus, 1), outstanding rate capability of 100 F g&minus, 1 (20 A g&minus, 1). Meanwhile, it still keeps 90% of the initial specific capacitance over 10,000 cycles. The readily available raw material, effective chemical activation, simple rGO additive, and resulting electrochemical properties hold out the promise of hope to achieve low-cost, green, and large-scale production of practical activated carbon composite materials for high-efficiency energy storage applications.

Pediatric empyema can be managed with a variety of modalities, and the evidence for an ideal management strategy is limited. Early or simple effusions can be treated with antibiotics alone or with drainage when respiratory distress occurs. Once fibrinopurulent empyema has developed, therapy may involve either chest tube placement with instillation of fibrinolytics or video-assisted thoracoscopic surgery with pleural decortication. In late or fibrotic empyema, an assumption persists that the fibrotic peel must be managed by decortication that can be done either thoracoscopically or through a minithoracotomy incision. This position paper is coauthored by the New Technology Committee of the American Pediatric Surgery Association. The goal is to discuss the ongoing controversies and summarize, in an evidence-based manner, the various treatment options and to suggest a reasonable therapeutic algorithm for the care of children with empyema.