Introducing Artificial Intelligence in Interpretation of Foetal Cardiotocography: Medical Dataset Curation and Preliminary Coding-An Interdisciplinary Project.

Artificial intelligence (AI) is gaining increasing interest in the field of medicine because of its capacity to process big data and pattern recognition. Cardiotocography (CTG) is widely used for the assessment of foetal well-being and uterine contractions during pregnancy and labour. It is characterised by inter- and intraobserver variability in interpretation, which depends on the observers' experience. Artificial intelligence (AI)-assisted interpretation could improve its quality and, thus, intrapartal care. Cardiotocography (CTG) raw signals from labouring women were extracted from the database at the University Hospital of Bern between 2006 and 2019. Later, they were matched with the corresponding foetal outcomes, namely arterial umbilical cord pH and 5-min APGAR score. Excluded were deliveries where data were incomplete, as well as multiple births. Clinical data were grouped regarding foetal pH and APGAR score at 5 min after delivery. Physiological foetal pH was defined as 7.15 and above, and a 5-min APGAR score was considered physiologic when reaching ≥7. With these groups, the algorithm was trained to predict foetal hypoxia. Raw data from 19,399 CTG recordings could be exported. This was accomplished by manually searching the patient's identification numbers (PIDs) and extracting the corresponding raw data from each episode. For some patients, only one episode per pregnancy could be found, whereas for others, up to ten episodes were available. Initially, 3400 corresponding clinical outcomes were found for the 19,399 CTGs (17.52%). Due to the small size, this dataset was rejected, and a new search strategy was elaborated. After further matching and curation, 6141 (31.65%) paired data samples could be extracted (cardiotocography raw data and corresponding maternal and foetal outcomes). Of these, half will be used to train artificial intelligence (AI) algorithms, whereas the other half will be used for analysis of efficacy. Complete data could only be found for one-third of the available population. Yet, to our knowledge, this is the most exhaustive and second-largest cardiotocography database worldwide, which can be used for computer analysis and programming. A further enrichment of the database is planned.

Artificial intelligence and machine learning in cardiotocography: A scoping review.

INTRODUCTION: Artificial intelligence (AI) is gaining more interest in the field of medicine due to its capacity to learn patterns directly from data. This becomes interesting for the field of cardiotocography (CTG) interpretation, since it promises to remove existing biases and improve the well-known issues of inter- and intra-observer variability. MATERIAL AND METHODS: The objective of this study was to map current knowledge in AI-assisted interpretation of CTG tracings and thus, to present different approaches with their strengths, gaps, and limitations. The search was performed on Ovid Medline and PubMed databases. The Preferred Reporting Items for Systematic Reviews and meta-Analysis for Scoping Reviews (PRISMA-ScR) guidelines were followed. RESULTS: We summarized 40 different studies investigating at least one algorithm or system to classify CTG tracings. In addition, the Oxford Sonicaid system is presented because of its wide use in clinical practice. CONCLUSIONS: There are several promising approaches in this area, but none of them has gained big acceptance in clinical practice. Further investigation and refinement of the algorithms and features are needed to achieve a validated decision-support system. For this purpose, larger quantities of curated and labeled data may be necessary.

Evaluation of a Wearable System for Fetal ECG Monitoring Using Cooperative Sensors.

Fetal electrocardiography (fECG) has gotten widespread interest in the last years as technology for fetal monitoring. Compared to cardiotocography (CTG), the current state of the art, it can be designed in smaller formfactor and is thus suited for long-term and unsupervised monitoring. In the present study we evaluated a wearable system which is based on CSEM's cooperative sensors, a versatile technology that allows for the measurement of multiple biosignals and an easy integration into a garment or patch. The system was tested on 25 patients with singleton pregnancies and an age of gestation ≥ 37 weeks. To reject unreliable fetal heart rate (fHR) estimations, the signal processing algorithm provides a signal quality index. In 12 out of 21 patients available for analysis, a good performance of fHR estimations was obtained with a mean absolute error < 5 bpm and an acceptance rate >70%. However, the remaining 9 patients showed low acceptance rates and high errors. Besides investigating the source of these high errors, future work includes the investigating improved signal processing algorithms, different body positions and the use of dry electrodes. Clinical Relevance - The aim of this work is to develop a wearable system that can be offered in hospitals as an alternative to cardiotocography, or as a home monitoring tool for at risk fetuses, in the era of evolving telemedicine.

Atrial Fibrillation Detection on Low-Power Wearables using Knowledge Distillation.

The increasing complexity and memory requirements of neural networks have been slowing down the adoption of AI in low-power wearable devices, which impose important restrictions in computational power and memory footprint. These low-power systems are the key to obtain 24/7 monitoring systems necessary for the current personalized healthcare trend since they do not require constant charging. In this work, we apply Knowledge Distillation to our previously published convolutional-recurrent neural network for cardiac arrhythmia detection and classification. We show that the resulting network halves the memory footprint (138 K parameters) and the number of operations (1.84 MOp) compared to the baseline. By using Knowledge Distillation, this network also achieves significantly higher accuracy after quantization (increase in overall F1 score from 0.779 to 0.828) and is capable of running into a nRF52832 System-on-Chip from Nordic Semiconductors. This promising result lays the groundwork for deployment on resource-constrained embedded platforms such as micro-controllers of the ARM Cortex-M family, thus potentially enabling continuous detection of cardiac arrhythmias in low-power wearable devices.

Ultra-low-power Physical Activity Classifier for Wearables: From Generic MCUs to ASICs.

In the era of Internet of Things (IoT), an increasing amount of sensors is being integrated into intelligent wearable devices. These sensors have the potential to produce a large quantity of physiological data streams to be analyzed in order to produce meaningful and actionable information. An important part of this processing is usually located in the device itself and takes the form of embedded algorithms which are executed into the onboard microcontroller (MCU). As data processing algorithms have become more complex due to, in part, the disruption of machine learning, they are taking an increasing part of MCU time becoming one of the main driving factors in the energy budget of the overall embedded system. We propose to integrate such algorithms into dedicated low-power circuits making the power consumption of the processing part negligible to the overall system. We provide the results of several implementations of a pre-trained physical activity classifier used in smartwatches and wristbands. The algorithm combines signal processing for feature extraction and machine learning in the form of decision trees for physical activity classification. We show how an in-silicon implementation decreases up to 0.1 µW the power consumption compared to 73 µW on a general-purpose ARM's Cortex-M0 MCU.

Artificial Intelligence for Hospital Health Care: Application Cases and Answers to Challenges in European Hospitals.

The development and implementation of artificial intelligence (AI) applications in health care contexts is a concurrent research and management question. Especially for hospitals, the expectations regarding improved efficiency and effectiveness by the introduction of novel AI applications are huge. However, experiences with real-life AI use cases are still scarce. As a first step towards structuring and comparing such experiences, this paper is presenting a comparative approach from nine European hospitals and eleven different use cases with possible application areas and benefits of hospital AI technologies. This is structured as a current review and opinion article from a diverse range of researchers and health care professionals. This contributes to important improvement options also for pandemic crises challenges, e.g., the current COVID-19 situation. The expected advantages as well as challenges regarding data protection, privacy, or human acceptance are reported. Altogether, the diversity of application cases is a core characteristic of AI applications in hospitals, and this requires a specific approach for successful implementation in the health care sector. This can include specialized solutions for hospitals regarding human-computer interaction, data management, and communication in AI implementation projects.

Lung Nodule Malignancy Prediction in Sequential CT Scans: Summary of ISBI 2018 Challenge.

Lung cancer is by far the leading cause of cancer death in the US. Recent studies have demonstrated the effectiveness of screening using low dose CT (LDCT) in reducing lung cancer related mortality. While lung nodules are detected with a high rate of sensitivity, this exam has a low specificity rate and it is still difficult to separate benign and malignant lesions. The ISBI 2018 Lung Nodule Malignancy Prediction Challenge, developed by a team from the Quantitative Imaging Network of the National Cancer Institute, was focused on the prediction of lung nodule malignancy from two sequential LDCT screening exams using automated (non-manual) algorithms. We curated a cohort of 100 subjects who participated in the National Lung Screening Trial and had established pathological diagnoses. Data from 30 subjects were randomly selected for training and the remaining was used for testing. Participants were evaluated based on the area under the receiver operating characteristic curve (AUC) of nodule-wise malignancy scores generated by their algorithms on the test set. The challenge had 17 participants, with 11 teams submitting reports with method description, mandated by the challenge rules. Participants used quantitative methods, resulting in a reporting test AUC ranging from 0.698 to 0.913. The top five contestants used deep learning approaches, reporting an AUC between 0.87 - 0.91. The team's predictor did not achieve significant differences from each other nor from a volume change estimate (p =.05 with Bonferroni-Holm's correction).

MQT-TZ: Secure MQTT Broker for Biomedical Signal Processing on the Edge.

Physical health records belong to healthcare providers, but the information contained within belongs to each patient. In an increasing manner, more health-related data is being acquired by wearables and other IoT devices following the ever-increasing trend of the Quantified Self. Even though data protection regulations (e.g., GDPR) encourage the usage of privacy-preserving processing techniques, most of the current IoT infrastructure was not originally conceived for such purposes. One of the most used communication protocols, MQTT, is a lightweight publish-subscribe protocol commonly used in the Edge and IoT applications. In MQTT, the broker must process data on clear text, hence exposing a large attack surface for a malicious agent to steal/tamper with this health-related data. In this paper, we introduce MQT-TZ, a secure MQTT broker leveraging Arm TRUSTZONE, a popular Trusted Execution Environment (TEE). We define a mutual TLS-based handshake and a two-layer encryption for end-to-end security using the TEE as a trusted proxy. We provide quantitative evaluation of our open-source PoC on streaming ECGs in real time and highlight the trade-offs.

Secure Stream Processing for Medical Data.

Medical data belongs to whom it produces it. In an increasing manner, this data is usually processed in unauthorized third-party clouds that should never have the opportunity to access it. Moreover, recent data protection regulations (e.g., GDPR) pave the way towards the development of privacy-preserving processing techniques. In this paper, we present a proof of concept of a streaming IoT architecture that securely processes cardiac data in the cloud combining trusted hardware and Spark. The additional security guarantees come with no changes to the application's code in the server. We tested the system with a database containing ECGs from wearable devices comprised of 8 healthy males performing a standardized range of in-lab physical activities (e.g., run, walk, bike). We show that, when compared with standard Spark Streaming, the addition of privacy comes at the cost of doubling the execution time.

Respiratory and cardiac monitoring at night using a wrist wearable optical system.

Sleep monitoring provides valuable insights into the general health of an individual and helps in the diagnostic of sleep-derived illnesses. Polysomnography, is considered the gold standard for such task. However, it is very unwieldy and therefore not suitable for long-term analysis. Here, we present a non-intrusive wearable system that, by using photoplethysmography, it can estimate beat-to-beat intervals, pulse rate, and breathing rate reliably during the night. The performance of the proposed approach was evaluated empirically in the Department of Psychology at the University of Fribourg. Each participant was wearing two smart-bracelets from Ava as well as a complete polysomnographic setup as reference. The resulting mean absolute errors are 17.4ms (MAPE 1.8%) for the beat-to-beat intervals, 0.13beats-per-minute (MAPE 0.20%) for the pulse rate, and 0.9breaths-per-minute (MAPE 6.7%) for the breath rate.

FlyLimbTracker: An active contour based approach for leg segment tracking in unmarked, freely behaving Drosophila.

Understanding the biological underpinnings of movement and action requires the development of tools for quantitative measurements of animal behavior. Drosophila melanogaster provides an ideal model for developing such tools: the fly has unparalleled genetic accessibility and depends on a relatively compact nervous system to generate sophisticated limbed behaviors including walking, reaching, grooming, courtship, and boxing. Here we describe a method that uses active contours to semi-automatically track body and leg segments from video image sequences of unmarked, freely behaving D. melanogaster. We show that this approach yields a more than 6-fold reduction in user intervention when compared with fully manual annotation and can be used to annotate videos with low spatial or temporal resolution for a variety of locomotor and grooming behaviors. FlyLimbTracker, the software implementation of this method, is open-source and our approach is generalizable. This opens up the possibility of tracking leg movements in other species by modifications of underlying active contour models.

Towards 24/7 continuous heart rate monitoring.

Heart rate (HR) and HR variability (HRV) carry rich information about physical activity, mental and physical load, physiological status, and health of an individual. When combined with activity monitoring and personalized physiological modelling, HR/HRV monitoring may be used for monitoring of complex behaviors and impact of behaviors and external factors on the current physiological status of an individual. Optical HR monitoring (OHR) from wrist provides a comfortable and unobtrusive method for HR/HRV monitoring and is better adhered by users than traditional ECG electrodes or chest straps. However, OHR power consumption is significantly higher than that for ECG based methods due to the measurement principle based on optical illumination of the tissue. We developed an algorithmic approach to reduce power consumption of the OHR in 24/7 HR trending. We use continuous activity monitoring and a fast converging frequency domain algorithm to derive a reliable HR estimate in 7.1s (during outdoor sports, in average) to 10.0s (during daily life). The method allows >80% reduction in power consumption in 24/7 OHR monitoring when average HR monitoring is targeted, without significant reduction in tracking accuracy.

Efficient Shape Priors for Spline-Based Snakes.

Parametric active contours are an attractive approach for image segmentation, thanks to their computational efficiency. They are driven by application-dependent energies that reflect the prior knowledge on the object to be segmented. We propose an energy involving shape priors acting in a regularization-like manner. Thereby, the shape of the snake is orthogonally projected onto the space that spans the affine transformations of a given shape prior. The formulation of the curves is continuous, which provides computational benefits when compared with landmark-based (discrete) methods. We show that this approach improves the robustness and quality of spline-based segmentation algorithms, while its computational overhead is negligible. An interactive and ready-to-use implementation of the proposed algorithm is available and was successfully tested on real data in order to segment Drosophila flies and yeast cells in microscopic images.

Clinical validation of LTMS-S: A wearable system for vital signs monitoring.

LTMS-S is a new wearable system for the monitoring of several physiological signals--including a two-lead electrocardiogram (ECG)--and parameters, such as the heart rate, the breathing rate, the peripheral oxygen saturation (SpO2), the core body temperature (CBT), and the physical activity. All signals are measured using only three sensors embedded within a vest. The sensors are standalone with their own rechargeable battery, memory, wireless communication and with an autonomy exceeding 24 hours. This paper presents the results of the clinical validation of the LTMS-S system.

Evaluation of the beat-to-beat detection accuracy of PulseOn wearable optical heart rate monitor.

Heart rate variability (HRV) provides significant information about the health status of an individual. Optical heart rate monitoring is a comfortable alternative to ECG based heart rate monitoring. However, most available optical heart rate monitoring devices do not supply beat-to-beat detection accuracy required by proper HRV analysis. We evaluate the beat-to-beat detection accuracy of a recent wrist-worn optical heart rate monitoring device, PulseOn (PO). Ten subjects (8 male and 2 female; 35.9±10.3 years old) participated in the study. HRV was recorded with PO and Firstbeat Bodyguard 2 (BG2) device, which was used as an ECG based reference. HRV was recorded during sleep. As compared to BG2, PO detected on average 99.57% of the heartbeats (0.43% of beats missed) and had 0.72% extra beat detection rate, with 5.94 ms mean absolute error (MAE) in beat-to-beat intervals (RRI) as compared to the ECG based RRI BG2. Mean RMSSD difference between PO and BG2 derived HRV was 3.1 ms. Therefore, PO provides an accurate method for long term HRV monitoring during sleep.

Evaluation of accuracy and reliability of PulseOn optical heart rate monitoring device.

PulseOn is a wrist-worn optical heart rate (HR) monitor based on photoplethysmography. It utilizes multi-wavelength technology and optimized sensor geometry to monitor blood flow at different depths of skin tissue, and it dynamically adapts to an optimal measurement depth in different conditions. Movement artefacts are reduced by adaptive movement-cancellation algorithms and optimized mechanics, which stabilize the sensor-to-skin contact. In this paper, we evaluated the accuracy and reliability of PulseOn technology against ECG-derived HR in laboratory conditions during a wide range of physical activities and also during outdoor sports. In addition, we compared the performance to another on-the-shelf wrist-worn consumer product Mio LINK(®). The results showed PulseOn reliability (% of time with error <;10bpm) of 94.5% with accuracy (100% - mean absolute percentage error) 96.6% as compared to ECG (vs 86.6% and 94.4% for Mio LINK(®), correspondingly) during laboratory protocol. Similar or better reliability and accuracy was seen during normal outdoor sports activities. The results show that PulseOn provides reliability and accuracy similar to traditional chest strap ECG HR monitors during cardiovascular exercise.

Anillin regulates cell-cell junction integrity by organizing junctional accumulation of Rho-GTP and actomyosin.

Anillin is a scaffolding protein that organizes and stabilizes actomyosin contractile rings and was previously thought to function primarily in cytokinesis [1-10]. Using Xenopus laevis embryos as a model system to examine Anillin's role in the intact vertebrate epithelium, we find that a population of Anillin surprisingly localizes to epithelial cell-cell junctions throughout the cell cycle, whereas it was previously thought to be nuclear during interphase [5, 11]. Furthermore, we show that Anillin plays a critical role in regulating cell-cell junction integrity. Both tight junctions and adherens junctions are disrupted when Anillin is knocked down, leading to altered cell shape and increased intercellular spaces. Anillin interacts with Rho, F-actin, and myosin II [3, 8, 9], all of which regulate cell-cell junction structure and function. When Anillin is knocked down, active Rho (Rho-guanosine triphosphate [GTP]), F-actin, and myosin II are misregulated at junctions. Indeed, increased dynamic "flares" of Rho-GTP are observed at cell-cell junctions, whereas overall junctional F-actin and myosin II accumulation is reduced when Anillin is depleted. We propose that Anillin is required for proper Rho-GTP distribution at cell-cell junctions and for maintenance of a robust apical actomyosin belt, which is required for cell-cell junction integrity. These results reveal a novel role for Anillin in regulating epithelial cell-cell junctions.

A chemostat array enables the spatio-temporal analysis of the yeast proteome.

Observing cellular responses to perturbations is central to generating and testing hypotheses in biology. We developed a massively parallel microchemostat array capable of growing and observing 1,152 yeast-GFP strains on the single-cell level with 20 min time resolution. We measured protein abundance and localization changes in 4,085 GFP-tagged strains in response to methyl methanesulfonate and analyzed 576 GFP strains in five additional conditions for a total of more than 10,000 unique experiments, providing a systematic view of the yeast proteome in flux. We observed that processing bodies formed rapidly and synchronously in response to UV irradiation, and in conjunction with 506 deletion-GFP strains, identified four gene disruptions leading to abnormal ribonucleotide-diphosphate reductase (Rnr4) localization. Our microchemostat platform enables the large-scale interrogation of proteomes in flux and permits the concurrent observation of protein abundance, localization, cell size, and growth parameters on the single-cell level for thousands of microbial cultures in one experiment.

Spline-based deforming ellipsoids for interactive 3D bioimage segmentation.

We present a new fast active-contour model (a.k.a. snake) for image segmentation in 3D microscopy. We introduce a parametric design that relies on exponential B-spline bases and allows us to build snakes that are able to reproduce ellipsoids. We design our bases to have the shortest-possible support, subject to some constraints. Thus, computational efficiency is maximized. The proposed 3D snake can approximate blob-like objects with good accuracy and can perfectly reproduce spheres and ellipsoids, irrespective of their position and orientation. The optimization process is remarkably fast due to the use of Gauss' theorem within our energy computation scheme. Our technique yields successful segmentation results, even for challenging data where object contours are not well defined. This is due to our parametric approach that allows one to favor prior shapes. In addition, this paper provides a software that gives full control over the snakes via an intuitive manipulation of few control points.

Snakes with an ellipse-reproducing property.

We present a new class of continuously defined parametric snakes using a special kind of exponential splines as basis functions. We have enforced our bases to have the shortest possible support subject to some design constraints to maximize efficiency. While the resulting snakes are versatile enough to provide a good approximation of any closed curve in the plane, their most important feature is the fact that they admit ellipses within their span. Thus, they can perfectly generate circular and elliptical shapes. These features are appropriate to delineate cross sections of cylindrical-like conduits and to outline bloblike objects. We address the implementation details and illustrate the capabilities of our snake with synthetic and real data.