Repeatability Study of Local Vascular Stiffness Measurement Using Carotid Surface Acceleration Plethysmogram

We have developed an accelerometric system with a custom-designed patch probe and signal acquisition hardware to acquire the carotid wall displacement from the soft tissue surface for arterial stiffness evaluation. A subject-specific calibration model was developed to estimate the morphology of accurate carotid diameter waveform, using a standard ultrasound B-mode imaging system as the reference. Following the one-time calibration, the accelerometric system continuously acquired a non-invasive carotid lumen diameter waveform. The capability of the accelerometric system to measure the carotid stiffness index (β) in-vivo was experimentally validated by performing measurements on 8 normotensive subjects in the supine position. The repeatability and reproducibility of the results were investigated and were found to be comparable to those provided by ultrasound imaging systems. Further, the variation of arterial stiffness index measurements on different days was studied to verify the ability of the system to give a stable measure of stiffness. The accuracy of the observed results was confirmed with the state-of-art B-mode ultrasound imaging system. The results were found to be stable over a day, indicating the utility of the system for a reliable measure of non-invasive carotid arterial stiffness.

Cuffless Blood Pressure Estimation Using Features Extracted from Carotid Dual-Diameter Waveforms

The major challenges in deep learning approaches to cuffless blood pressure estimation is selecting the most appropriate representative of the blood pulse waveform and extraction of relevant features for data collection. This paper performs an analysis of a novel dataset consisting of 71 features from the carotid dual-diameter waveforms and 4 blood pressure parameters. In particular, the analysis uses gradient boosting and graph-theoretic algorithms to determine (1) features with high predictive power and (2) potential to be pruned. Identifying such features and understanding their physiological significance is important for building blood pressure estimation models using machine learning that is robust across diverse clinical environments and patient sets.

Automated measurement of compression-decompression in arterial diameter and wall thickness by image-free ultrasound

BACKGROUND AND OBJECTIVE

The manual measurement of arterial diameter and wall thickness using imaging modalities demand expertise, and the state-of-art automated or semi-automated measurement features are seldom available in the entry-level systems. The advanced ultrasound modalities are expensive, non-scalable, and less favorable for field and resource-constrained settings. In this work, we present a novel method to measure arterial diameter (D), surrogate intima-media thickness (sIMT), and with them their intra-cardiac cycle changes by employing an affordable image-free ultrasound technology.

METHODS

The functionality of the method was systematically validated on a simulation testbed, phantoms and, 40 human subjects. The accuracy, agreement, inter-beat, and inter-operator variabilities were quantified. The in-vivo measurement performance of the method was compared against two reference B-mode tools - Carotid Studio and CAROLAB.

RESULTS

Simulations revealed that for the A-mode frames with SNR > 10 dB, the proposed method identifies the desired arterial wall interfaces with an RMSE < 20 μm. The RMSE for the diameter and wall thickness measurements from the static phantom were 111 μm and 14 μm, and for the dynamic phantom were 117 μm and 18 μm, respectively. Strong agreement was seen between the in-vivo measurements of the proposed method and the two reference tools. The mean absolute errors against the two references and the inter-beat variability were smaller than 0.18 mm for D and smaller than 36 μm for sIMT measurements. Likewise, the respective inter-observer variabilities were 0.16 ± 0.23 mm and 43 ± 25 μm.

CONCLUSION

Acceptable accuracy and repeatability were observed during the validation, that were on a par with the recently reported B-mode techniques in the literature. The technology being real-time, automated, and relatively inexpensive, is promising for field and low-resource settings.

Semantic segmentation of microscopic neuroanatomical data by combining topological priors with encoder-decoder deep networks

Understanding of neuronal circuitry at cellular resolution within the brain has relied on neuron tracing methods which involve careful observation and interpretation by experienced neuroscientists. With recent developments in imaging and digitization, this approach is no longer feasible with the large scale (terabyte to petabyte range) images. Machine learning based techniques, using deep networks, provide an efficient alternative to the problem. However, these methods rely on very large volumes of annotated images for training and have error rates that are too high for scientific data analysis, and thus requires a significant volume of human-in-the-loop proofreading. Here we introduce a hybrid architecture combining prior structure in the form of topological data analysis methods, based on discrete Morse theory, with the best-in-class deep-net architectures for the neuronal connectivity analysis. We show significant performance gains using our hybrid architecture on detection of topological structure (e.g. connectivity of neuronal processes and local intensity maxima on axons corresponding to synaptic swellings) with precision/recall close to 90% compared with human observers. We have adapted our architecture to a high performance pipeline capable of semantic segmentation of light microscopic whole-brain image data into a hierarchy of neuronal compartments. We expect that the hybrid architecture incorporating discrete Morse techniques into deep nets will generalize to other data domains.

Artificial intelligence in detection and segmentation of internal auditory canal and its nerves using deep learning techniques

PURPOSE

Artificial intelligence (AI) in medical imaging is a burgeoning topic that involves the interpretation of complex image structures. The recent advancements in deep learning techniques increase the computational powers to extract vital features without human intervention. The automatic detection and segmentation of subtle tissue such as the internal auditory canal (IAC) and its nerves is a challenging task, and it can be improved using deep learning techniques.

METHODS

The main scope of this research is to present an automatic method to detect and segment the IAC and its nerves like the facial nerve, cochlear nerve, inferior vestibular nerve, and superior vestibular nerve. To address this issue, we propose a Mask R-CNN approach driven with U-net to detect and segment the IAC and its nerves. The Mask R-CNN with its backbone network of the RESNET50 model learns a background-based localization policy to produce an actual bounding box of the IAC. Furthermore, the U-net segments the structure related information of IAC and its nerves by learning its features.

RESULTS

The proposed method was experimented on clinical datasets of 50 different patients including adults and children. The localization of IAC using Mask R-CNN was evaluated using Intersection of Union (IoU), and segmentation of IAC and its nerves was evaluated using Dice similarity coefficient.

CONCLUSIONS

The localization result shows that mean IoU of RESNET50, RESNET101 are 0.79 and 0.74, respectively. The Dice similarity coefficient of IAC and its nerves using region growing, PSO and U-net method scored 92%, 94%, and 96%, respectively. The result shows that the proposed method outperform better in localization and segmentation of IAC and its nerves. Thus, AI aids the radiologists in making the right decisions as the localization and segmentation of IAC is accurate.

iQuant Auto: Automated Rapid Test Platform for Immunodiagnostics

Point-of-care diagnostic devices aid in the early and rapid detection of immunological markers leading to better medical outcomes. Lateral flow immunoassays (LFIA) are fast assays that provide both qualitative and semi-quantitative results on site. Sample preparation for LFIA tests is usually done manually with multiple mixing steps and is prone to errors. The iQuant Auto is an entirely automated system that can handle sample preparation, effective transfer to lateral flow test membrane, and subsequent result estimation. The system uses a pneumatic system for fluid handling and sample preparation, and an image-based fluorescence reader for reaction visualization. The device works with test specific milli-fluidic lateral flow kit called iQPrep Kit, which has integrated reagent storage areas and valves for fluid control. The test kit can be manufactured using standard manufacturing techniques and can be produced at scale cheaply. The iQPrep Kit can be modified to test for various markers like HbA1c, Vitamin D, and TSH, while the hardware for sample preparation and the fluorescence reader remains the same. The device has a minimalist and intelligible graphical interface aiding smooth operation by less skilled people at resource-limited settings. Standard reference cartridges of different volume ratios were used to validate the functionality of the instrument. The intra- instrument coefficient of variation (CoV) of the mobile kit reader was found to be less than 0.62%. The positional accuracy of the system to ensure precise kit engagement with the other auxiliary systems was checked, and the CoV was 0.16%. The fluid handling capabilities were tested, and it was found that an average fluid loss of 10 µl results due to the liquid adherence to fluid channel walls and valve interfaces. The iQuant Auto is an easily operable, total analysis system for immunodiagnostics.

High-Throughput Vascular Screening by ARTSENS Pen During a Medical Camp for Early-Stage Detection of Chronic Kidney Disease

Intervention in the early stages of cardiovascular and kidney diseases is proven to be more effective in preventing disease progression. Large artery stiffness measurement can be a potential early predictor of future risks. The purpose of the study reported in this work was to demonstrate the feasibility of our ARTSENS^® Pen device as a high-throughput vascular screening tool for risk assessment. The study was performed during a medical camp conducted for awareness and early-stage detection of kidney diseases. Screening procedures included biosample tests and blood pressure measurements. Alongside, various clinically relevant measures of the arterial stiffness were evaluated using the ARTSENS^® Pen, by measuring vessel wall dynamics via our proprietary image-free ultrasound algorithms. Stiffness measurement from the left common carotid artery on 85 participants could be completed within 4 hours, employing two units of ARTSENS^® Pen; this also includes time taken for all the procedures enlisted in the study protocol. The associations of carotid stiffness indices with age-, gender-, and risk factor-dependent variations were established.

Non-contact sensing of neonatal pulse rate using camera-based imaging: a clinical feasibility study

OBJECTIVE

Neonates and infants are patients who would benefit from less invasive vital sign sensing, especially from fewer cables and the avoidance of adhesive electrodes. Photoplethysmography imaging (PPGI) has been studied for medical applications in recent years: it is possible to assess various vital signs remotely, non-invasively, and without contact by using video cameras and light. However, studies on infants and especially on neonates in clinical settings are still rare. Hence, we conducted a single-center study to assess heart activity by estimating the pulse rate (PR) of 19 neonates.

APPROACH

Time series were generated from tracked regions of interest (ROIs) and PR was estimated via a joint time-frequency analysis using a short-time Fourier transform. Artifacts, for example, induced by movement, were detected and flagged by applying a signal quality index in the frequency domain.

MAIN RESULTS

The feasibility of PR estimation was demonstrated using visible light and near-infrared light at 850 nm and 940 nm, respectively: the estimated PR was as close as 3 heartbeats per minute in artifact-free time segments. Furthermore, an improvement could be shown when selecting the best performing ROI compared to the ROI containing the whole body. The main challenges are artifacts from motion, light sources, medical devices, and the detection and tracking of suitable regions for signal retrieval. Nonetheless, the PR extracted was found to be comparable to the contact-based photoplethysmography reference and is, therefore, a viable replacement if robust signal retrieval is ensured.

SIGNIFICANCE

Neonates are seldom measured by PPGI and studies reporting measurements on darker skin tones are rare. In this work, not only a single camera was used, but a synchronized camera setup using multiple wavelengths. Various ROIs were used for signal extraction to examine the capabilities of PPGI. In addition, qualitative observations regarding camera parameters and noise sources were reported and discussed.

ARTSENS® Pen-portable easy-to-use device for carotid stiffness measurement: technology validation and clinical-utility assessment

OBJECTIVE

The conventional medical imaging modalities used for arterial stiffness measurement are non-scalable and unviable for field-level vascular screening. The need for an affordable, easy-to-operate automated non-invasive technologies remains unmet. To address this need, we present a portable image-free ultrasound device-ARTSENS^® Pen, that uses a single-element ultrasound transducer for carotid stiffness evaluation.

APPROACH

The performance of the device was clinically validated on a cohort of 523 subjects. A clinical-grade B-mode ultrasound imaging system (ALOKA eTracking) was used as the reference. Carotid stiffness measurements were taken using the ARTSENS^® Pen in sitting posture emulating field scenarios.

MAIN RESULTS

A statistically significant correlation (r > 0.80, p < 0.0001) with a non-significant bias was observed between the measurements obtained from the two devices. The ARTSENS^® Pen device could perform highly repeatable measurements (with variation smaller than 10%) on a relatively larger percentage of the population when compared to the ALOKA system. The study results also revealed the sensitivity of ARTSENS^® Pen to detect changes in arterial stiffness with age.

SIGNIFICANCE

The easy-to-use technology and the automated algorithms of the ARTSENS^® Pen make it suitable for cardiovascular risk assessment in resource-constrained settings.

Novel Geometric Representation for One-Dimensional Model of Arterial Blood Pulse Wave Propagation

This paper proposes a novel one-dimensional graphical representation to model the phenomenon of blood pulse wave propagation in major arteries. In particular, a tree data structure, as opposed to the existing purely linear structures, is used to accommodate arterial branching. The model is qualitatively validated and its demonstrated reliability by evaluating the phenomenon of wave reflection and pulse pressure amplification with a sample in-vivo arterial segment length measurements.

Machine Learning based SpO2 Computation Using Reflectance Pulse Oximetry

Continuous monitoring of blood oxygen saturation level (SpO₂) is crucial for patients with cardiac and pulmonary disorders and those undergoing surgeries. SpO₂ monitoring is widely used in a clinical setting to evaluate the effectiveness of lung medication and ventilator support. Owing to its high levels of accuracy and stability, transmittance pulse oximeters are widely used in the clinical community to compute SpO₂. Transmittance pulse oximeters are limited to measure SpO₂ only from peripheral sites. Reflectance pulse oximeters, however, can be used at various measurement sites like finger, wrist, chest, forehead, and are immune to faulty measurements due to vasoconstriction and perfusion changes. Reflectance pulse oximeters are not widely adopted in clinical environments due to faulty measurements and inaccurate R-value based calibration methods. In this paper, we present the analysis and observations made using a machine learning model for SpO₂ computation using reflectance Photoplethysmogram (PPG) signals acquired from the finger using the custom data acquisition platform. The proposed model overcomes the limitations imposed by the traditional R-value based calibration method through the use of a machine learning model using various time and frequency domain features. The model was trained and tested using the clinical data collected from 95 subjects with SpO₂ levels varying from 81-100% using the custom SpO₂ data acquisition platform along with reference measures. The proposed model has an absolute mean error of 0.5% with an accuracy of 96 ± 2% error band for SpO₂ values ranging from 81-100%.

Continuous Assessment of Carotid Diameter using an Accelerometer Patch Probe for Ambulatory Arterial Stiffness Monitoring

We present a system with an accelerometer patch probe design for non-invasive evaluation of carotid arterial stiffness. The proposed system could continuously measure the acceleration signal derived due to the propagation of blood pulse wave through the left carotid artery, double integrating and scaling it to estimate the accelerometer-derived carotid wall displacement. This functional principle was proved by comparing the accelerometer-derived carotid wall displacement with the carotid distension signal from the reference system ARTSENS® (ARTerial Stiffness Evaluation for Noninvasive Screening device) for all the recruited human subjects. Assuming the relationship to be linear, a one-time subject-specific calibration was performed with the simultaneously acquired reference distension signal and the accelerometer-derived carotid displacement signals on its anachrotic limbs data points (at systolic phases) for each subject. This calibration equation was tested with latterly acquired accelerometer signals and results in the measurement of accelerometer-derived carotid distension and lumen-diameter values. The ability of the accelerometer system to measure real-time carotid distension and lumen diameter in a repeatable beat-by-beat manner for arterial stiffness index evaluation was validated in-vivo. The accuracy of the obtained results was studied with our clinically validated reference system. The experimental validation study results exhibit the feasibility of using the developed accelerometer system for continuous carotid distension and lumen diameter measurements, whereby the estimation of carotid arterial stiffness.

Image-Free Technique for Flow Mediated Dilation Using ARTSENS® Pen

Flow mediated dilation (FMD) is a clinically accepted non-invasive tool for assessing endothelial dysfunction. FMD is conventionally performed with B-mode ultrasound systems that involve recording of the image sequences as DICOM files or video-graphic files and processing them offline. Sometimes the examinations may have to be rejected due to poor or unstable image sequences resulting non-reliable diameter estimates. We had earlier developed and extensively validated an image-free ultrasound technology, ARTSENS^®, for the measurement of carotid artery wall dynamics and arterial stiffness metrics. In this work, we evaluate the feasibility of using the technology for continuous real-time diameter measurement of the brachial artery and thereby FMD. To investigate the performance of the ARTSENS^® device an in-vivo study was conducted on 5 subjects as pilot. As a reference the measurements were also performed by a B-mode imaging system with a help of a commercially available clinically validated offline FMD analysis tool. The brachial artery diameter and FMD measurements performed by the ARTSENS^® device were consistent with the earlier reported literature. The beat-to-beat repeatability of the baseline diameter measurements was acceptable with a CoV <; 4% for all the subjects. The diameter measurements performed by the two devices exhibited a significant correlation (r-square = 0.81, p <; 0.05). The RMSE for the diameter and FMD% measurements was 0.32 mm and 0.63% respectively, illustrating the measurement accuracy. The study demonstrated that the ARTSENS^® can be reliably employed for performing FMD measurements and assessing endothelial dysfunction. This would help realize a field deployable solution for real-time automated FMD measurement and consequently for the acceleration of large population studies in this research area.

Multimodal Image-Free Ultrasound Technique for Evaluation of Arterial Viscoelastic Properties: A Feasibility Study

In this article, we have presented a multimodal system and a novel probe design that was built around an image-free ultrasound technology, ARTSENS®, for measurement of arterial viscoelastic properties. ARTSENS® was extensively validated over the years, for performing measurements of arterial wall dynamics and stiffness with an accuracy that meets clinical standards. Concerning this work, several enhancements were incorporated to this basic technology that allowed high frame rate A-scan imaging (1 kHz) and integration of a pressure measuring module for automated measurements of the viscoelastic parameter (elastic index, viscous index and wall buffering function). The functionality of the developed multimodal system and probe were investigated by conducting an in-vivo on 8 young subjects (both normotensive and hypertensive were included). The beat-to-beat measurements of the viscoelastic parameters exhibited acceptable repeatability with a variability <; 6.5%. It was observed that the group average for viscosity index and the wall buffering function were higher for hypertensive subjects as compared to normotensive subjects. The study observations were consistent with the reported literature. The proposed system addresses several issues associated with the traditional image-based systems and offers huge advantage of field amenability thus making it favorable for large population screening and studies.

PPGnet: Deep Network for Device Independent Heart Rate Estimation from Photoplethysmogram

Photoplethysmogram (PPG) is increasingly used to provide monitoring of the cardiovascular system under ambulatory conditions. Wearable devices like smartwatches use PPG to allow long-term unobtrusive monitoring of heart rate in free-living conditions. PPG based heart rate measurement is unfortunately highly susceptible to motion artifacts, particularly when measured from the wrist. Traditional machine learning and deep learning approaches rely on tri-axial accelerometer data along with PPG to perform heart rate estimation. The conventional learning based approaches have not addressed the need for device-specific modeling due to differences in hardware design among PPG devices. In this paper, we propose a novel end-to-end deep learning model to perform heart rate estimation using 8-second length input PPG signal. We evaluate the proposed model on the IEEE SPC 2015 dataset, achieving a mean absolute error of 3.36±4.1BPM for HR estimation on 12 subjects without requiring patient-specific training. We also studied the feasibility of applying transfer learning along with sparse retraining from a comprehensive in-house PPG dataset for heart rate estimation across PPG devices with different hardware design.

Effectiveness of a continuous patient position monitoring system in improving hospital turn protocol compliance in an ICU: A multiphase multisite study in India

Purpose

Hospital-acquired pressure ulcers are a significant cause of morbidity and consume considerable financial resources. Turn protocols (repositioning patients at regular intervals) are utilized to reduce incidence of pressure ulcers. Adherence to turn protocols is particularly challenging for nursing teams, given the high number of interventions in intensive care unit, and lack of widely available tools to monitor patient position and generate alerts. We decided to develop and evaluate usefulness of a continuous patient position monitoring system to assist nurses in improving turn protocol compliance.

Methods

We conducted a prospective, non-randomized, multiphase, multicentre trial. In Phase I (control group), the function of the device was not revealed to nurses so as to observe their baseline adherence to turn protocol, while Phase II (intervention group) used continuous patient position monitoring system to generate alerts, when non-compliant with the turn protocol. All consecutive patients admitted to one of the two intensive care units during the study period were screened for enrolment. Patients at risk of acquiring pressure ulcers (Braden score < 18) were considered for the study (Phase I (N = 22), Phase II (N = 25)).

Results

We analysed over 1450 h of patient position data collected from 40 patients (Phase I (N = 20), Phase II (N = 20)). Turn protocol compliance was significantly higher in Phase II (80.15 ± 8.97%) compared to the Phase I (24.36 ± 12.67%); p < 0.001.

Conclusion

Using a continuous patient position monitoring system to provide alerts significantly improved compliance with hospital turn protocol. Nurses found the system to be useful in providing automated turn reminders and prioritising tasks.

Clinical Validation of a Wearable Respiratory Rate Device for Neonatal Monitoring

Respiratory rate monitoring is of paramount importance in neonatal care. Manual counting of expansions and contractions of the abdomen or diaphragm of the neonate is still the widely accepted measure of respiratory rate in most clinical settings. A practical, affordable, easy-to-use technology to continuously measure respiratory rate in neonates is essential to recognize the signs and symptoms of respiratory disorders. Clinical validation of a system for continuous and long term respiratory rate monitoring of neonates, in a wearable form factor with the capability of remote monitoring is presented in this paper. The respiratory rate monitor was validated in clinical settings on 10 premature babies with various disease conditions and respiratory rates varying from 25 to 90 breaths per minute. Results show a high degree of correlation between the respiratory rate measured by the device and reference measurements. An intelligent algorithm which can remove motion corruption from the accelerometer data and provide reliable results is essential for large-scale adoption of the technology for both clinical as well as home monitoring. The technical details of implementation, results and analysis of the clinical study and observations made during clinical study regarding the feasibility of integrating the device in neonatal care are covered in this paper.

Validation of a Customized Algorithm for the Detection of Diabetic Retinopathy from Single-Field Fundus Photographs in a Tertiary Eye Care Hospital

The study was done to validate the real time efficacy of a customised algorithm in detecting diabetic retinopathy (DR) among diabetic patients being examined at the vitreo retinal outpatient department (VR OPD) of a tertiary care hospital, Diabetic Retinopathy algorithm showed sensitivity of 79% and specificity of 57% which is an acceptable methodology to diagnose diabetic retinopathy and avoid unnecessary referrals.

Local Pulse Wave Velocity: Theory, Methods, Advancements, and Clinical Applications

Local pulse wave velocity (PWV) is evolving as one of the important determinants of arterial hemodynamics, localized vessel stiffening associated with several pathologies, and a host of other cardiovascular events. Although PWV was introduced over a century ago, only in recent decades, due to various technological advancements, has emphasis been directed toward its measurement from a single arterial section or from piecewise segments of a target arterial section. This emerging worldwide trend in the exploration of instrumental solutions for local PWV measurement has produced several invasive and noninvasive methods. As of yet, however, a univocal opinion on the ideal measurement method has not emerged. Neither have there been extensive comparative studies on the accuracy of the available methods. Recognizing this reality, makes apparent the need to establish guideline-recommended standards for the measurement methods and reference values, without which clinical application cannot be pursued. This paper enumerates all major local PWV measurement methods while pinpointing their salient methodological considerations and emphasizing the necessity of global standardization. Further, a summary of the advancements in measuring modalities and clinical applications is provided. Additionally, a detailed discussion on the minimally explored concept of incremental local PWV is presented along with suggestions of future research questions.

Polyp Segmentation using Generative Adversarial Network

Colorectal cancer is one of the highest causes of cancer-related death and the patient's survival rate depends on the stage at which polyps are detected. Polyp segmentation is a challenging research task due to variations in the size and shape of polyps leading to necessitate robust approaches for diagnosis. This paper studies the deep generative convolutional framework for the task of polyp segmentation. Here, the analysis of polyp segmentation has been explored with the pix2pix conditional generative adversarial network. On CVC- Clinic dataset, the proposed network achieves Jaccard index of 81.27% and Dice index of 88.48%.

Pre-surgery Stress Monitoring Using Heart Rate Variability Measures

Pre-surgery stress is common in patients hospitalized for undergoing surgeries. High levels of stress could prolong post-operative recovery time, increasing the duration of hospitalization. Abnormally high stress levels could sometimes have irreversible impacts, leading to post-operative physiological and psychological disorders. Continuous monitoring of patients during the pre-operative period could help in taking necessary measures to control the stress levels. Electrocardiogram (ECG) is one of the signals which is usually monitored continuously for patients in clinical settings. The usability of ECG for Heart Rate Variability (HRV) based stress detection has been explored in this study. HRV features derived from ECG data acquired from 51 patients admitted in the surgical ward during their pre-operative phase were studied. The trend of the features showed similarity in pre-surgery stress experienced by the patients. Using chest leads connected by wires to a wrist wearable for collecting ECG was obtrusive to patients and resulted in loss of more than 50% of the data. Unobtrusive data collection using chest patches can make HRV based stress detection feasible for clinical use. However, an additional monitoring system would require additional responsibility on the part of the healthcare staff involved in patient care. Integrating the HRV based stress detection into the patient monitors already being used in these clinical settings could therefore make the monitoring of stress feasible.

RespNet: A deep learning model for extraction of respiration from photoplethysmogram

Respiratory ailments afflict a wide range of people and manifests itself through conditions like asthma and sleep apnea. Continuous monitoring of chronic respiratory ailments is seldom used outside the intensive care ward due to the large size and cost of the monitoring system. While Electrocardiogram (ECG) based respiration extraction is a validated approach, its adoption is limited by access to a suitable continuous ECG monitor. Recently, due to the widespread adoption of wearable smartwatches with in-built Photoplethysmogram (PPG) sensor, it is being considered as a viable candidate for continuous and unobtrusive respiration monitoring. Research in this domain, however, has been predominantly focussed on estimating respiration rate from PPG. In this work, a novel end-to-end deep learning network called RespNet is proposed to perform the task of extracting the respiration signal from a given input PPG as opposed to extracting respiration rate. The proposed network was trained and tested on two different datasets utilizing different modalities of reference respiration signal recordings. Also, the similarity and performance of the proposed network against two conventional signal processing approaches for extracting respiration signal were studied. The proposed method was tested on two independent datasets with a Mean Squared Error of 0.262 and 0.145. The cross-correlation coefficient of the respective datasets were found to be 0.933 and 0.931. The reported errors and similarity was found to be better than conventional approaches. The proposed approach would aid clinicians to provide comprehensive evaluation of sleep-related respiratory conditions and chronic respiratory ailments while being comfortable and inexpensive for the patient.

Multi-cartridge Fluorescence Reader for Quantitative Immunoassays

Lateral flow immunoassays (LFIA) play a significant role in point-of-care (POC) diagnostics, facilitating early diagnosis of medical conditions. With simpler infrastructure requirements, POC diagnostics can be easily adopted in remote areas as well as for end-user level monitoring. As part of the current work, we present a camera based multi-cartridge fluorescence reader. The proposed system can carry out simultaneous analysis of four LFIA test cartridges. It forms a simple, rugged system requiring minimal human intervention and the average time taken for tests is lower as compared to the available LFIA readers. The hardware architecture of the system along with the software algorithms utilized is described in this paper. To validate the system performance, tests were conducted using HbA1C samples. The designed system comprises of four test-slots accommodating four test cartridges in a single go. The correlation of the obtained results with reference sample concentrations was determined and system calibration equations were as well obtained. Repeatability across the slots in terms of % coefficient of variation was calculated and was found to be less than 6%. The obtained results along with challenges in the current system and future modifications are also discussed.