Modification of a Conventional Deep Learning Model to Classify Simulated Breathing Patterns: A Step toward Real-Time Monitoring of Patients with Respiratory Infectious Diseases.

The emergence of the global coronavirus pandemic in 2019 (COVID-19 disease) created a need for remote methods to detect and continuously monitor patients with infectious respiratory diseases. Many different devices, including thermometers, pulse oximeters, smartwatches, and rings, were proposed to monitor the symptoms of infected individuals at home. However, these consumer-grade devices are typically not capable of automated monitoring during both day and night. This study aims to develop a method to classify and monitor breathing patterns in real-time using tissue hemodynamic responses and a deep convolutional neural network (CNN)-based classification algorithm. Tissue hemodynamic responses at the sternal manubrium were collected in 21 healthy volunteers using a wearable near-infrared spectroscopy (NIRS) device during three different breathing conditions. We developed a deep CNN-based classification algorithm to classify and monitor breathing patterns in real time. The classification method was designed by improving and modifying the pre-activation residual network (Pre-ResNet) previously developed to classify two-dimensional (2D) images. Three different one-dimensional CNN (1D-CNN) classification models based on Pre-ResNet were developed. By using these models, we were able to obtain an average classification accuracy of 88.79% (without Stage 1 (data size reducing convolutional layer)), 90.58% (with 1 × 3 Stage 1), and 91.77% (with 1 × 5 Stage 1).

Electrophysiological Evidence for Interhemispheric Connectivity and Communication in Young Human Infants.

Little is known empirically about connectivity and communication between the two hemispheres of the brain in the first year of life, and what theoretical opinion exists appears to be at variance with the meager extant anatomical evidence. To shed initial light on the question of interhemispheric connectivity and communication, this study investigated brain correlates of interhemispheric transmission of information in young human infants. We analyzed EEG data from 12 4-month-olds undergoing a face-related oddball ERP protocol. The activity in the contralateral hemisphere differed between odd-same and odd-difference trials, with the odd-different response being weaker than the response during odd-same trials. The infants' contralateral hemisphere "recognized" the odd familiar stimulus and "discriminated" the odd-different one. These findings demonstrate connectivity and communication between the two hemispheres of the brain in the first year of life and lead to a better understanding of the functional integrity of the developing human infant brain.

Optical Monitoring of Breathing Patterns and Tissue Oxygenation: A Potential Application in COVID-19 Screening and Monitoring.

The worldwide outbreak of the novel Coronavirus (COVID-19) has highlighted the need for a screening and monitoring system for infectious respiratory diseases in the acute and chronic phase. The purpose of this study was to examine the feasibility of using a wearable near-infrared spectroscopy (NIRS) sensor to collect respiratory signals and distinguish between normal and simulated pathological breathing. Twenty-one healthy adults participated in an experiment that examined five separate breathing conditions. Respiratory signals were collected with a continuous-wave NIRS sensor (PortaLite, Artinis Medical Systems) affixed over the sternal manubrium. Following a three-minute baseline, participants began five minutes of imposed difficult breathing using a respiratory trainer. After a five minute recovery period, participants began five minutes of imposed rapid and shallow breathing. The study concluded with five additional minutes of regular breathing. NIRS signals were analyzed using a machine learning model to distinguish between normal and simulated pathological breathing. Three features: breathing interval, breathing depth, and O2Hb signal amplitude were extracted from the NIRS data and, when used together, resulted in a weighted average accuracy of 0.87. This study demonstrated that a wearable NIRS sensor can monitor respiratory patterns continuously and non-invasively and we identified three respiratory features that can distinguish between normal and simulated pathological breathing.

Structured sparse multiset canonical correlation analysis of simultaneous fNIRS and EEG provides new insights into the human action-observation network.

The action observation network (AON) is a network of brain regions involved in the execution and observation of a given action. The AON has been investigated in humans using mostly electroencephalogram (EEG) and functional magnetic resonance imaging (fMRI), but shared neural correlates of action observation and action execution are still unclear due to lack of ecologically valid neuroimaging measures. In this study, we used concurrent EEG and functional Near Infrared Spectroscopy (fNIRS) to examine the AON during a live-action observation and execution paradigm. We developed structured sparse multiset canonical correlation analysis (ssmCCA) to perform EEG-fNIRS data fusion. MCCA is a generalization of CCA to more than two sets of variables and is commonly used in medical multimodal data fusion. However, mCCA suffers from multi-collinearity, high dimensionality, unimodal feature selection, and loss of spatial information in interpreting the results. A limited number of participants (small sample size) is another problem in mCCA, which leads to overfitted models. Here, we adopted graph-guided (structured) fused least absolute shrinkage and selection operator (LASSO) penalty to mCCA to conduct feature selection, incorporating structural information amongst the variables (i.e., brain regions). Benefitting from concurrent recordings of brain hemodynamic and electrophysiological responses, the proposed ssmCCA finds linear transforms of each modality such that the correlation between their projections is maximized. Our analysis of 21 right-handed participants indicated that the left inferior parietal region was active during both action execution and action observation. Our findings provide new insights into the neural correlates of AON which are more fine-tuned than the results from each individual EEG or fNIRS analysis and validate the use of ssmCCA to fuse EEG and fNIRS datasets.

Studying the Accuracy and Function of Different Thermometry Techniques for Measuring Body Temperature.

The purpose of this study was to determine which thermometry technique is the most accurate for regular measurement of body temperature. We compared seven different commercially available thermometers with a gold standard medical-grade thermometer (Welch-Allyn): four digital infrared thermometers (Wellworks, Braun, Withings, MOBI), one digital sublingual thermometer (Braun), one zero heat flux thermometer (3M), and one infrared thermal imaging camera (FLIR One). Thirty young healthy adults participated in an experiment that altered core body temperature. After baseline measurements, participants placed their feet in a cold-water bath while consuming cold water for 30 min. Subsequently, feet were removed and covered with a blanket for 30 min. Throughout the session, temperature was recorded every 10 min with all devices. The Braun tympanic thermometer (left ear) had the best agreement with the gold standard (mean error: 0.044 °C). The FLIR One thermal imaging camera was the least accurate device (mean error: -0.522 °C). A sign test demonstrated that all thermometry devices were significantly different than the gold standard except for the Braun tympanic thermometer (left ear). Our study showed that not all temperature monitoring techniques are equal, and suggested that tympanic thermometers are the most accurate commercially available system for the regular measurement of body temperature.

Non-invasive transabdominal measurement of placental oxygenation: a step toward continuous monitoring.

This study aimed to assess transabdominal placental oxygenation levels non-invasively. A wearable device was designed and tested in 12 pregnant women with an anterior placenta, 5 of whom had maternal pregnancy complications. Preliminary results revealed that the placental oxygenation level is closely related to pregnancy complications and placental pathology. Women with maternal pregnancy complications were found to have a lower placental oxygenation level (69.4% ± 6.7%) than those with uncomplicated pregnancy (75.0% ± 5.8%). This device is a step in the development of a point-of-care method designed to continuously monitor placental oxygenation and to assess maternal and fetal health.

Special Section Guest Editorial: Wearable, Implantable, Mobile, and Remote Biomedical Optics and Photonics.

Guest editors Jessica Ramella-Roman, Amir H. Gandjbakhche, Stephen C. Kanick, Babak Shadgan, and Bruce J. Tromberg introduce and summarize the articles included in the 6-part JBO Special Section on Wearable, Implantable, Mobile, and Remote Biomedical Optics Photonics.

Review of the efficacy of infrared thermography for screening infectious diseases with applications to COVID-19.

Purpose: The recent coronavirus disease 2019 (COVID-19) pandemic, which spread across the globe in a very short period of time, revealed that the transmission control of disease is a crucial step to prevent an outbreak and effective screening for viral infectious diseases is necessary. Since the severe acute respiratory syndrome (SARS) outbreak in 2003, infrared thermography (IRT) has been considered a gold standard method for screening febrile individuals at the time of pandemics. The objective of this review is to evaluate the efficacy of IRT for screening infectious diseases with specific applications to COVID-19. Approach: A literature review was performed in Google Scholar, PubMed, and ScienceDirect to search for studies evaluating IRT screening from 2002 to present using relevant keywords. Additional literature searches were done to evaluate IRT in comparison to traditional core body temperature measurements and assess the benefits of measuring additional vital signs for infectious disease screening. Results: Studies have reported on the unreliability of IRT due to poor sensitivity and specificity in detecting true core body temperature and its inability to identify asymptomatic carriers. Airport mass screening using IRT was conducted during occurrences of SARS, Dengue, Swine Flu, and Ebola with reported sensitivities as low as zero. Other studies reported that screening other vital signs such as heart and respiratory rates can lead to more robust methods for early infection detection. Conclusions: Studies evaluating IRT showed varied results in its efficacy for screening infectious diseases. This suggests the need to assess additional physiological parameters to increase the sensitivity and specificity of non-invasive biosensors.

An fNIRS Study of Brain Lateralization During Observation and Execution of a Fine Motor Task.

Brain activity in the action observation network (AON) is lateralized during action execution, with greater activation in the contralateral hemisphere to the side of the body used to perform the task. However, it is unknown whether the AON is also lateralized when watching another person perform an action. In this study, we use fNIRS to measure brain activity over the left and right cortex while participants completed actions with their left and right hands and watched an actor complete action with their left and right hands. We show that while activation is lateralized when the participants themselves are moving, brain lateralization is not affected by the side of the body when the participant is observing another person's action. In addition, we demonstrate that individual differences in hand preference and dexterity between the right and left hands are related to brain lateralization patterns.

Evaluation of the human placenta optical scattering properties using continuous wave and frequency-domain diffuse reflectance spectroscopy.

SIGNIFICANCE: Placenta is an essential organ for fetal development and successful reproduction. Placental insufficiency can lead to fetal hypoxia and, in extreme cases anoxia, leading to fetal death. Of the 145 million deliveries per year worldwide, ∼15 million neonates are small for gestational age and, therefore, at risk for antepartum and intrapartum hypoxia. Clinical methods to assess placental function largely rely on the assessment of fetal heart rate changes but do not assess placental oxygenation. Near-infrared spectroscopy (NIRS) allows non-invasive, real-time assessment of tissue oxygenation in intact organs, which can be used to assess placental oxygenation. However, tissue optical properties can affect the accuracy of methods to measure tissue oxygenation. AIM: This study was performed to estimate the scattering coefficient of the human placenta. We have computed the scattering coefficients of the human placenta for the range of 659 to 840 nm using two methods of diffuse reflectance spectroscopy (DRS). APPROACH: Measurements were performed using an in-house DRS device and a well-established frequency-domain diffuse optical spectroscopic system (DOSI). Measurements were performed in eight placentas obtained after cesarean deliveries. Placentas were perfused with normal saline to minimize the effects of absorption due to blood. Three sites per placenta were measured. Absorption and scattering coefficients were then calculated from the measured reflectance using the random walk theory for DRS and frequency-domain algorithm for DOSI. RESULTS: Average reduced scattering coefficient (µs ' ) was 0.943 ± 0.015 mm - 1 at 760 nm and 0.831 ± 0.009 mm - 1 at 840 nm, and a power function µs ' = 1.6619 (λ/500 nm) - 1.426 was derived for the human placental scattering coefficient. CONCLUSION: We report for the first time the scattering coefficient of the human placenta. This information can be used to assess baseline scattering and improve measurements of placental oxygen saturation with NIRS.

Hemodynamics of Prefrontal Cortex in Ornithine Transcarbamylase Deficiency: A Twin Case Study.

Ornithine transcarbamylase deficiency (OTCD) is the most common form of urea cycle disorder characterized by the presence of hyperammonemia (HA). In patients with OTCD, HA is known to cause impairments in domains of executive function and working memory. Monitoring OTCD progression and investigating neurocognitive biomarkers can, therefore, become critical in understanding the underlying brain function in a population with OTCD. We used functional near infrared spectroscopy (fNIRS) to examine the hemodynamics of prefrontal cortex (PFC) in a fraternal twin with and without OTCD. fNIRS is a non-invasive and wearable optical technology that can be used to assess cortical hemodynamics in a realistic clinical setting. We quantified the hemodynamic variations in total-hemoglobin as assessed by fNIRS while subjects performed the N-back working memory (WM) task. Our preliminary results showed that the sibling with OTCD had higher variation in a very low frequency band (<0.03 Hz, related to mechanism of cerebral autoregulation) compared to the control sibling. The difference between these variations was not as prominent in the higher frequency band, indicating the possible role of impaired autoregulation and cognitive function due to presence of HA. We further examined the functional connectivity in PFC, where the OTCD sibling showed lower interhemispheric functional connectivity as the task load increased. Our pilot results are the first to show the utility of fNIRS in monitoring OTCD cortical hemodynamics, indicating the possibility of inefficient neurocognitive function. This study provides a novel insight into the monitoring of OTCD focusing on the contribution of physiological process and neurocognitive function in this population.

Optical Imaging Technology: A Useful Tool to Identify Remission in Cushing Disease After Surgery.

We recently reported the use of optical imaging technology to quantify facial plethora in endogenous Cushing syndrome (CS). In the present study, we studied a larger cohort of patients with Cushing disease (CD) and examined water content fraction as well as blood volume fraction as bio-optic markers for determining the efficacy of this methodology as a predictor of lasting remission after surgery for CS. We imaged 49 patients before and after transsphenoidal surgery (TSS) for Cushing disease (CD); 22 patients were also seen at 3-6 months, and 13 patients 12 months post-operatively. On all patients, we used multi-spectral imaging (MSI) to evaluate hemodynamic distributions as well as water content at a specific area of the face. We found a decrease in blood volume fraction after vs. before surgical treatment in the tested facial area in 37 of the 40 patients, as determined with biochemical markers (p<0.001). All patients that were followed up for up to 12 months showed the same decrease from preoperative values and they remained in remission from CD. We conclude that MSI can be used for the evaluation of remission from CD, at least in the immediate post-operative period and up to one year after surgery. The use of this technology can supplement biochemical and other testing for the evaluation of the various treatment modalities available for patients with CD.

Exploring the role of task performance and learning style on prefrontal hemodynamics during a working memory task.

Existing literature outlines the quality and location of activation in the prefrontal cortex (PFC) during working memory (WM) tasks. However, the effects of individual differences on the underlying neural process of WM tasks are still unclear. In this functional near infrared spectroscopy study, we administered a visual and auditory n-back task to examine activation in the PFC while considering the influences of task performance, and preferred learning strategy (VARK score). While controlling for age, results indicated that high performance (HP) subjects (accuracy > 90%) showed task dependent lower activation compared to normal performance subjects in PFC region Specifically HP groups showed lower activation in left dorsolateral PFC (DLPFC) region during performance of auditory task whereas during visual task they showed lower activation in the right DLPFC. After accounting for learning style, we found a correlation between visual and aural VARK score and level of activation in the PFC. Subjects with higher visual VARK scores displayed lower activation during auditory task in left DLPFC, while those with higher visual scores exhibited higher activation during visual task in bilateral DLPFC. During performance of auditory task, HP subjects had higher visual VARK scores compared to NP subjects indicating an effect of learning style on the task performance and activation. The results of this study show that learning style and task performance can influence PFC activation, with applications toward neurological implications of learning style and populations with deficits in auditory or visual processing.

Using in vivo fluorescence lifetime imaging to detect HER2-positive tumors.

BACKGROUND: Assessment of the status of tumor biomarkers in individual patients would facilitate personalizing treatment strategy, and continuous monitoring of those biomarkers and their binding process to the therapeutic drugs would provide a means for early evaluation of the efficacy of therapeutic intervention. Fluorescent probes can accumulate inside the tumor region due to the leakiness of its vascularization and this can make it difficult to distinguish if the measured fluorescence intensity is from probes bound to target receptors or just accumulated unbound probes inside the tumor. In this paper, we have studied the fluorescence lifetime as a means to distinguish bound HER2 specific affibody probes to HER2 receptors. Our imaging system is a time-resolved fluorescence system using a Ti-Sapphire femtosecond pulse laser as source and Time correlated Single photon Counting (TCSPC) system as detector for calculating the lifetime of the contrast agent. HER2-specific Affibody (His6-ZHER2:GS-Cys) (Affibody, Stockholm, Sweden) conjugated with a Dylight750 fluorescent probe (Thermo-Fisher-Scientific, Waltham, Massachusetts) was used as contrast agent and six human cancer cell lines, BT-474, SKOV-3, NCI-N87, MDA-MB-361, MCF-7, and MDA-MB-468, known to express different levels of HER2/neu, are used in athymic mice xenografts. RESULTS: By comparing the lifetime of unbound contrast agent (at the contralateral site) to the fluorescence lifetime at the tumor site, our results show that the fluorescence lifetime decreases as HER2 specific Affibody probes bind to the tumor receptors. A decrease of ~15% (100ps) in tumor fluorescence lifetime was observed in tumors with mid to high HER2 expression. Smaller decreases were observed in tumors with low-level of HER2 receptors and no change was observed in the non-HER2-expressing tumors. CONCLUSIONS: Using HER2-specific Affibody conjugated with the Dylight750 fluorescent probe as contrast agent, we demonstrated in live animals that change in fluorescence lifetime of the bound contrast agent can be used to assess the high to mid-level expression of HER2 expressing tumors in-vivo in only one measurement. The rationale is that the fluorescence lifetime of our specific probe is sensitive to affinity to, and specific interaction with, other molecules.

Prefrontal Hemodynamics in Toddlers at Rest: A Pilot Study of Developmental Variability.

Functional near infrared spectroscopy (fNIRS) is a non-invasive functional neuroimaging modality. Although, it is amenable to use in infants and young children, there is a lack of fNIRS research within the toddler age range. In this study, we used fNIRS to measure cerebral hemodynamics in the prefrontal cortex (PFC) in 18-36 months old toddlers (n = 29) as part of a longitudinal study that enrolled typically-developing toddlers as well as those "at risk" for language and other delays based on presence of early language delays. In these toddlers, we explored two hemodynamic response indices during periods of rest during which time audiovisual children's programming was presented. First, we investigate Lateralization Index, based on differences in oxy-hemoglobin saturation from left and right prefrontal cortex. Then, we measure oxygenation variability (OV) index, based on variability in oxygen saturation at frequencies attributed to cerebral autoregulation. Preliminary findings show that lower cognitive (including language) abilities are associated with fNIRS measures of both lower OV index and more extreme Lateralization index values. These preliminary findings show the feasibility of using fNIRS in toddlers, including those at risk for developmental delay, and lay the groundwork for future studies.

A machine learning approach to identify functional biomarkers in human prefrontal cortex for individuals with traumatic brain injury using functional near-infrared spectroscopy.

BACKGROUND: We have explored the potential prefrontal hemodynamic biomarkers to characterize subjects with Traumatic Brain Injury (TBI) by employing the multivariate machine learning approach and introducing a novel task-related hemodynamic response detection followed by a heuristic search for optimum set of hemodynamic features. To achieve this goal, the hemodynamic response from a group of 31 healthy controls and 30 chronic TBI subjects were recorded as they performed a complexity task. METHODS: To determine the optimum hemodynamic features, we considered 11 features and their combinations in characterizing TBI subjects. We investigated the significance of the features by utilizing a machine learning classification algorithm to score all the possible combinations of features according to their predictive power. RESULTS AND CONCLUSIONS: The identified optimum feature elements resulted in classification accuracy, sensitivity, and specificity of 85%, 85%, and 84%, respectively. Classification improvement was achieved for TBI subject classification through feature combination. It signified the major advantage of the multivariate analysis over the commonly used univariate analysis suggesting that the features that are individually irrelevant in characterizing the data may become relevant when used in combination. We also conducted a spatio-temporal classification to identify regions within the prefrontal cortex (PFC) that contribute in distinguishing between TBI and healthy subjects. As expected, Brodmann areas (BA) 10 within the PFC were isolated as the region that healthy subjects (unlike subjects with TBI), showed major hemodynamic activity in response to the High Complexity task. Overall, our results indicate that identified temporal and spatio-temporal features from PFC's hemodynamic activity are promising biomarkers in classifying subjects with TBI.

Compact non-contact total emission detection for in vivo multiphoton excitation microscopy.

We describe a compact, non-contact design for a total emission detection (c-TED) system for intra-vital multiphoton imaging. To conform to a standard upright two-photon microscope design, this system uses a parabolic mirror surrounding a standard microscope objective in concert with an optical path that does not interfere with normal microscope operation. The non-contact design of this device allows for maximal light collection without disrupting the physiology of the specimen being examined. Tests were conducted on exposed tissues in live animals to examine the emission collection enhancement of the c-TED device compared to heavily optimized objective-based emission collection. The best light collection enhancement was seen from murine fat (5×-2× gains as a function of depth), whereas murine skeletal muscle and rat kidney showed gains of over two and just under twofold near the surface, respectively. Gains decreased with imaging depth (particularly in the kidney). Zebrafish imaging on a reflective substrate showed close to a twofold gain throughout the entire volume of an intact embryo (approximately 150 µm deep). Direct measurement of bleaching rates confirmed that the lower laser powers, enabled by greater light collection efficiency, yielded reduced photobleaching in vivo. The potential benefits of increased light collection in terms of speed of imaging and reduced photo-damage, as well as the applicability of this device to other multiphoton imaging methods is discussed.

In vivo assessment of HER2 receptor density in HER2-positive tumors by near-infrared imaging, using repeated injections of the fluorescent probe.

HER2 overexpression and amplification of the HER2/neu gene have been found in approximately 25% of invasive breast carcinomas. They are associated with a poor prognosis and resistance to therapy in breast cancer patients. Up to now, clinical evaluation of human epidermal growth factor receptor 2 (HER2) expression is based on ex vivo methods (immunohistochemistry (IHC) or fluorescence in situ hybridization (FISH) staining of biopsied tissue). Our goal is to realize "image and treat" paradigm using targeted fluorescent probes to evaluate expression levels of cell biomarkers responsible for cancer progression and to monitor the efficacy of corresponding monoclonal antibody treatments. We used fluorescent Affibody-based probes for in vivo analysis of HER2 receptors using near-infrared optical imaging that do not interfere with binding of the therapeutic agents to these receptors. We have analyzed two types of breast carcinoma xenografts with significant differences in HER2 expression (31 and 21 according to classification) in the mouse model. Using our kinetic model to analyze the temporal variations of the fluorescence intensity in the tumor area after two subsequent injections allowed us to assess quantitatively the difference in HER2 expression levels for two tumor types (BT-474 and MD-MBA-361). This result was substantiated by ELISA ex vivo assays of HER2 expression in the same tumors.

Monitoring LITT thermal penetration depth using real-time analysis of backscattered light.

Real-time monitoring of the thermal penetration depth (TPD) is essential in various clinical procedures, such as Laser Interstitial Thermal Therapy (LITT). MRI is commonly used to this end, though bulky and expensive. In this paper, we present an alternative novel method for an optical feedback system based on changes in the diffused reflection from the tissue during treatment. Monte-Carlo simulation was used to deduce the relations between the backscattered pattern and the TPD. Several methods of image analysis are developed for TPD estimation. Each yields a set of parameters which are linearly dependent on the TPD. In order to test these experimentally, tissue samples were monitored in-vitro during treatment at multiple wavelengths. The SNR and coefficient of determination were used to compare the various methods and wavelengths and to determine the preferred method. Such system and algorithms may be used for real-time in-vivo control during laser thermotherapy and other clinical procedures.