Development of a graphical user interface for automatic separation of human voice from Doppler ultrasound audio in diving experiments.

Doppler ultrasound (DU) is used in decompression research to detect venous gas emboli in the precordium or subclavian vein, as a marker of decompression stress. This is of relevance to scuba divers, compressed air workers and astronauts to prevent decompression sickness (DCS) that can be caused by these bubbles upon or after a sudden reduction in ambient pressure. Doppler ultrasound data is graded by expert raters on the Kisman-Masurel or Spencer scales that are associated to DCS risk. Meta-analyses, as well as efforts to computer-automate DU grading, both necessitate access to large databases of well-curated and graded data. Leveraging previously collected data is especially important due to the difficulty of repeating large-scale extreme military pressure exposures that were conducted in the 70-90s in austere environments. Historically, DU data (Non-speech) were often captured on cassettes in one-channel audio with superimposed human speech describing the experiment (Speech). Digitizing and separating these audio files is currently a lengthy, manual task. In this paper, we develop a graphical user interface (GUI) to perform automatic speech recognition and aid in Non-speech and Speech separation. This constitutes the first study incorporating speech processing technology in the field of diving research. If successful, it has the potential to significantly accelerate the reuse of previously-acquired datasets. The recognition task incorporates the Google speech recognizer to detect the presence of human voice activity together with corresponding timestamps. The detected human speech is then separated from the audio Doppler ultrasound within the developed GUI. Several experiments were conducted on recently digitized audio Doppler recordings to corroborate the effectiveness of the developed GUI in recognition and separations tasks, and these are compared to manual labels for Speech timestamps. The following metrics are used to evaluate performance: the average absolute differences between the reference and detected Speech starting points, as well as the percentage of detected Speech over the total duration of the reference Speech. Results have shown the efficacy of the developed GUI in Speech/Non-speech component separation.

Relative hypoxemia at depth during breath-hold diving investigated through arterial blood gas analysis and lung ultrasound.

Pulmonary gas exchange in breath-hold diving (BHD) consists of a progressive increase in arterial partial pressures of oxygen ([Formula: see text]) and carbon dioxide ([Formula: see text]) during descent. However, recent findings have demonstrated that [Formula: see text] does not consistently rise in all subjects. This study aimed at verifying and explaining [Formula: see text] derangements during BHD analyzing arterial blood gases and searching for pulmonary alterations with lung ultrasound. After ethical approval, 14 fit breath-hold divers were included. Experiments were performed in warm water (temperature: 31°C). We analyzed arterial blood gases immediately before, at depth, and immediately after a breath-hold dive to -15 m of fresh water (mfw) and -42 mfw. Signs of lung interstitial edema and atelectasis were searched simultaneously with a marinized lung ultrasound. In five subjects (-15 mfw) and four subjects (-42 mfw), the [Formula: see text] at depth seems to decrease instead of increasing. [Formula: see text] and lactate showed slight variations. At depth, no lung ultrasound alterations were seen except in one subject (hypoxemia and B-lines at -15 mfw; B-lines at the surface). Lung interstitial edema was detected in 3 and 12 subjects after resurfacing from -15 to -42 mfw, respectively. Two subjects developed hypoxemia at depth and a small lung atelectasis (a focal pleural irregularity of triangular shape, surrounded by thickened B-lines) after resurfacing from -42 mfw. Current experiments confirmed that some BH divers can experience hypoxemia at depth. The hypothesized explanation for such a discrepancy is lung atelectasis, which could not be detected in all subjects probably due to limited time available at depth.NEW & NOTEWORTHY During breath-hold diving, arterial partial pressure of oxygen ([Formula: see text]) and arterial partial pressure of carbon dioxide ([Formula: see text]) are believed to increase progressively during descent, as explained by theory, previous end-tidal alveolar gas measurements, and arterial blood gas analysis in hyperbaric chambers. Recent experiments in real underwater environment found a paradoxical [Formula: see text] drop at depth in some divers. This work confirms that some breath-hold divers can experience hypoxemia at depth. The hypothesized explanation for such a discrepancy is lung atelectasis, as suggested by lung ultrasound findings.

Effect of Anesthetic Carrier Gas on In Vivo Circulation Times of Intravenously Administered Phospholipid Oxygen Microbubbles in Rats.

OBJECTIVE: For the treatment of tumor hypoxia, microbubbles comprising oxygen as a majority component of the gas core with a stabilizing shell may be used to deliver and release oxygen locally at the tumor site through ultrasound destruction. Previous work has revealed differences in circulation half-life in vivo for perfluorocarbon-filled microbubbles, typically used as ultrasound imaging contrast agents, as a function of anesthetic carrier gas. These differences in circulation time in vivo were likely due to gas diffusion as a function of anesthetic carrier gas, among other variables. This work has motivated studies to evaluate the effect of anesthetic carrier gas on oxygen microbubble circulation dynamics. METHODS: Circulation time for oxygen microbubbles was derived from ultrasound image intensity obtained during longitudinal kidney imaging. Studies were constructed for rats anesthetized on inhaled isoflurane with either pure oxygen or medical air as the anesthetic carrier gas. RESULTS: Results indicated that oxygen microbubbles were highly visible via contrast-specific imaging. Marked signal enhancement and duration differences were observed between animals breathing air and oxygen. Perhaps counterintuitively, oxygen microbubbles disappeared from circulation significantly faster when the animals were breathing pure oxygen compared with medical air. This may be explained by nitrogen counterdiffusion from blood into the bubble, effectively changing the gas composition of the core, as has been observed in perfluorocarbon core microbubbles. CONCLUSION: Our findings suggest that the apparent longevity and persistence of oxygen microbubbles in circulation may not be reflective of oxygen delivery when the animal is anesthetized breathing air.

An open-source framework for synthetic post-dive Doppler ultrasound audio generation.

Doppler ultrasound (DU) measurements are used to detect and evaluate venous gas emboli (VGE) formed after decompression. Automated methodologies for assessing VGE presence using signal processing have been developed on varying real-world datasets of limited size and without ground truth values preventing objective evaluation. We develop and report a method to generate synthetic post-dive data using DU signals collected in both precordium and subclavian vein with varying degrees of bubbling matching field-standard grading metrics. This method is adaptable, modifiable, and reproducible, allowing for researchers to tune the produced dataset for their desired purpose. We provide the baseline Doppler recordings and code required to generate synthetic data for researchers to reproduce our work and improve upon it. We also provide a set of pre-made synthetic post-dive DU data spanning six scenarios representing the Spencer and Kisman-Masurel (KM) grading scales as well as precordial and subclavian DU recordings. By providing a method for synthetic post-dive DU data generation, we aim to improve and accelerate the development of signal processing techniques for VGE analysis in Doppler ultrasound.

Volume 50: The UHM Journal celebrates a milestone with the publication of this issue.

As the UHMS observes the distinguished anniversary of the publication of 50 volumes of the Undersea and Hyperbaric Medicine Journal, two of our past editors take a look at the evolution of our flagship publications.

Deep Learning-Based Venous Gas Emboli Grade Classification in Doppler Ultrasound Audio Recordings.

OBJECTIVE: Doppler ultrasound (DU) is used to detect venous gas emboli (VGE) post dive as a marker of decompression stress for diving physiology research as well as new decompression procedure validation to minimize decompression sickness risk. In this article, we propose the first deep learning model for VGE grading in DU audio recordings. METHODS: A database of real-world data was assembled and labeled for the purpose of developing the algorithm, totaling 274 recordings comprising both subclavian and precordial measurements. Synthetic data was also generated by acquiring baseline DU signals from human volunteers and superimposing laboratory-acquired DU signals of bubbles flowing in a tissue mimicking material. A novel squeeze-and-excitation deep learning model was designed to effectively classify recordings on the 5-class Spencer scoring system used by trained human raters. RESULTS: On the real-data test set, we show that synthetic data pretraining achieves average ordinal accuracy of 84.9% for precordial and 90.4% for subclavian DU which is a 24.6% and 26.2% increase over training with real-data and time-series augmentation only. The weighted kappa coefficients of agreement between the model and human ground truth were 0.74 and 0.69 for precordial and subclavian respectively, indicating substantial agreement similar to human inter-rater agreement for this type of data. CONCLUSION: The present work demonstrates the first application of deep-learning for DU VGE grading using a combination of synthetic and real-world data. SIGNIFICANCE: The proposed method can contribute to accelerating DU analysis for decompression research.

Effects of high-intensity interval training with hyperbaric oxygen.

Hyperbaric Oxygen (HBO2) has been proposed as a pre-conditioning method to enhance exercise performance. Most prior studies testing this effect have been limited by inadequate methodologies. Its potential efficacy and mechanism of action remain unknown. We hypothesized that HBO2 could enhance aerobic capacity by inducing mitochondrial biogenesis via redox signaling in skeletal muscle. HBO2 was administered in combination with high-intensity interval training (HIIT), a potent redox stimulus known to induce mitochondrial biogenesis. Aerobic capacity was tested during acute hypobaric hypoxia seeking to shift the limiting site of whole body V̇O2 from convection to diffusion, more closely isolating any effect of improved oxidative capacity. Healthy volunteers were screened with sea-level (SL) V̇O2peak testing. Seventeen subjects were enrolled (10 men, 7 women, ages 26.5±1.3 years, BMI 24.6±0.6 kg m-2, V̇O2peak SL = 43.4±2.1). Each completed 6 HIIT sessions over 2 weeks randomized to breathing normobaric air, "HIIT+Air" (PiO2 = 0.21 ATM) or HBO2 (PiO2 = 1.4 ATM) during training, "HIIT+HBO2" group. Training workloads were individualized based on V̇O2peak SL test. Vastus Lateralis (VL) muscle biopsies were performed before and after HIIT in both groups. Baseline and post-training V̇O2peak tests were conducted in a hypobaric chamber at PiO2 = 0.12 ATM. HIIT significantly increased V̇O2peak in both groups: HIIT+HBO2 31.4±1.5 to 35.2±1.2 ml kg-1·min-1 and HIIT+Air 29.0±3.1 to 33.2±2.5 ml kg-1·min-1 (p = 0.005) without an additional effect of HBO2 (p = 0.9 for interaction of HIIT x HBO2). Subjects randomized to HIIT+HBO2 displayed higher skeletal muscle mRNA levels of PPARGC1A, a regulator of mitochondrial biogenesis, and HK2 and SLC2A4, regulators of glucose utilization and storage. All other tested markers of mitochondrial biogenesis showed no additional effect of HBO2 to HIIT. When combined with HIIT, short-term modest HBO2 (1.4 ATA) has does not increase whole-body V̇O2peak during acute hypobaric hypoxia. (ClinicalTrials.gov Identifier: NCT02356900; https://clinicaltrials.gov/ct2/show/NCT02356900).

Safety evaluation of carbon tetrafluoride as an inert hyperbaric breathing gas in Sprague-Dawley rats.

Carbon tetrafluoride (CF4) is an inert gas with higher molecular weight and lower water solubility than commonly used hyperbaric breathing gases. These inert gas properties decrease time required to decompress and avoid decompression sickness after deep dives. To assess CF4 toxicity, Sprague-Dawley rats were exposed to 8 atm absolute (ATA) air (10 males, 10 females) or 8 ATA 79% CF4/21% O2 (25 males, 25 females). Exposures were 30 min daily for 5 days. Rat behavior was normal throughout the testing period. There were no gross or microscopic pathology abnormalities following repeat dose exposure. Male body weight trends were similar between groups. Female body weight trends were 0.5 ± 0.8% day-1 for hyperbaric air exposure and - 0.2 ± 0.8% day-1 for hyperbaric CF4 exposure (P = 0.01) but remained within literature cited norms. Organ weights and hematologic indices remained within or near literature normal ranges. Clinical chemistry panels showed no signs of toxicity in renal or hepatic biomarkers. Polychromatic erythrocyte micronucleus frequency showed no chromosomal damage. Comet assay showed no DNA damage in lung tissue. Females exposed to CF4 had 2.5 times greater percent tail DNA in liver tissue than controls (P = 0.009). However this result remained within the normal range of local negative controls. A bacterial reverse mutation assay with exposure to 1 ATA 79% CF4/21% O2 for 72 h was nonmutagenic in four strains of Salmonella typhimurium and one strain of Escherichia coli. Overall, there was no evidence that CF4 caused organ toxicity or genetic toxicity.

Immersion-Induced Mitral Regurgitation: A Novel Risk Factor for Swimming-Induced Pulmonary Edema.

Immersion pulmonary edema, more commonly referred to as swimming-induced pulmonary edema (SIPE), is a well-documented condition believed to be a result of immersion physiologic condition that is characterized by a peripheral-to-central redistribution of blood volume. It disproportionally affects young, healthy athletes with no clinically overt cardiovascular or pulmonary conditions. We present four cases of healthy athletes with previously documented SIPE, who participated in Institutional Review Board-approved clinical studies that examined the pathophysiologic condition and prevention of SIPE. During standard recumbent echocardiography, trivial mitral regurgitation was observed in all four individuals. Acute exacerbation of their mitral regurgitation was observed during immersion with both immersed resting and immersed exercise echocardiography, contributing to the development of SIPE. These observations demonstrate that the occurrence of subclinical or trivial mitral valve regurgitation during dry rest is a novel risk factor for SIPE. We propose the use of immersion echocardiography as a useful investigative tool for otherwise healthy individuals with SIPE and no previously explainable cause.

The Dewey Monitor: Pulse Oximetry can Warn of Hypoxia in an Immersed Rebreather Diver in Multiple Scenarios.

Divers who wish to prolong their time underwater while carrying less equipment often use devices called rebreathers, which recycle the gas expired after each breath instead of discarding it as bubbles. However, rebreathers' need to replace oxygen used by breathing creates a failure mechanism that can and frequently does lead to hypoxia, loss of consciousness, and death. The purpose of this study was to determine whether a pulse oximeter could provide a useful amount of warning time to a diver with a rebreather after failure of the oxygen addition mechanism. Twenty-eight volunteer human subjects breathed on a mixed-gas rebreather in which the oxygen addition system had been disabled. The subjects were immersed in water in four separate environmental scenarios, including cold and warm water, and monitored using pulse oximeters placed at multiple locations. Pulse oximeters placed on the forehead and clipped on the nasal ala provided a mean of 32 s (±10 s SD) of warning time to divers with falling oxygen levels, prior to risk of loss of consciousness. These devices, if configured for underwater use, could provide a practical and inexpensive alarm system to warn of impending loss of consciousness in a manner that is redundant to the rebreather.

Blood gas analyses in hyperbaric and underwater environments: a systematic review.

Pulmonary gas exchange during diving or in a dry hyperbaric environment is affected by increased breathing gas density and possibly water immersion. During free diving, there is also the effect of apnea. Few studies have published blood gas data in underwater or hyperbaric environments: this review summarizes the available literature and was used to test the hypothesis that arterial Po2 under hyperbaric conditions can be predicted from blood gas measurement at 1 atmosphere assuming a constant arterial/alveolar Po2 ratio (a:A). A systematic search was performed on traditional sources including arterial blood gases obtained on humans in hyperbaric or underwater environments. The a:A was calculated at 1 atmosphere absolute (ATA). For each condition, predicted arterial partial pressure of oxygen ([Formula: see text]) at pressure was calculated using the 1 ATA a:A, and the measured [Formula: see text] was plotted against the predicted value with Spearman correlation coefficients. Of 3,640 records reviewed, 30 studies were included: 25 were reports describing values obtained in hyperbaric chambers, and the remaining were collected while underwater. Increased inspired O2 at pressure resulted in increased [Formula: see text], although underlying lung disease in patients treated with hyperbaric oxygen attenuated the rise. [Formula: see text] generally increased only slightly. In breath-hold divers, hyperoxemia generally occurred at maximum depth, with hypoxemia after surfacing. The a:A adequately predicted the [Formula: see text] under various conditions: dry (r = 0.993, P < 0.0001), rest versus exercise (r = 0.999, P < 0.0001), and breathing mixtures (r = 0.995, P < 0.0001). In conclusion, pulmonary oxygenation under hyperbaric conditions can be reliably and accurately predicted from 1 ATA a:A measurements.

Hyperbaric oxygen for decompression sickness.

Decompression sickness (DCS, "bends") is caused by formation of bubbles in tissues and/or blood when the sum of dissolved gas pressures exceeds ambient pressure (supersaturation). This may occur when ambient pressure is reduced during any of the following: ascent from a dive; depressurization of a hyperbaric chamber; rapid ascent to altitude in an unpressurized aircraft or hypobaric chamber; loss of cabin pressure in an aircraft; and during space walks.

Physiologic and biochemical rationale for treating COVID-19 patients with hyperbaric oxygen.

The SARS-Cov-2 (COVID-19) pandemic remains a major worldwide public health issue. Initially, improved supportive and anti-inflammatory intervention, often employing known drugs or technologies, provided measurable improvement in management. We have recently seen advances in specific therapeutic interventions and in vaccines. Nevertheless, it will be months before most of the world's population can be vaccinated to achieve herd immunity. In the interim, hyperbaric oxygen (HBO2) treatment offers several potentially beneficial therapeutic effects. Three small published series, one with a propensity-score-matched control group, have demonstrated safety and initial efficacy. Additional anecdotal reports are consistent with these publications. HBO2 delivers oxygen in extreme conditions of hypoxemia and tissue hypoxia, even in the presence of lung pathology. It provides anti-inflammatory and anti-proinflammatory effects likely to ameliorate the overexuberant immune response common to COVID-19. Unlike steroids, it exerts these effects without immune suppression. One study suggests HBO2 may reduce the hypercoagulability seen in COVID patients. Also, hyperbaric oxygen offers a likely successful intervention to address the oxygen debt expected to arise from a prolonged period of hypoxemia and tissue hypoxia. To date, 11 studies designed to investigate the impact of HBO2 on patients infected with SARS-Cov-2 have been posted on clinicaltrials.gov. This paper describes the promising physiologic and biochemical effects of hyperbaric oxygen in COVID-19 and potentially in other disorders with similar pathologic mechanisms.

Ultrasound in decompression research: fundamentals, considerations, and future technologies.

It is widely accepted that bubbles are a necessary but insufficient condition for the development of decompression sickness. However, open questions remain regarding the precise formation and behavior of these bubbles after an ambient pressure reduction (decompression), primarily due to the inherent difficulty of directly observing this phenomenon in vivo. In decompression research, information about these bubbles after a decompression is gathered via means of ultrasound acquisitions. The ability to draw conclusions regarding decompression research using ultrasound is highly influenced by the variability of the methodologies and equipment utilized by different research groups. These differences play a significant role in the quality of the data and thus the interpretation of the results. The purpose of this review is to provide a technical overview of the use of ultrasound in decompression research, particularly Doppler and brightness (B)-mode ultrasound. Further, we will discuss the strengths and limitations of these technologies and how new advancements are improving our ability to understand bubble behavior post-decompression.

Hyperbaric oxygen for intracranial abscess.

The term "intracranial abscess" (ICA) includes cerebral abscess, subdural empyema, and epidural empyema, which share many diagnostic and therapeutic similarities and, frequently, very similar etiologies. Infection may occur and spread from a contiguous infection such as sinusitis, otitis, mastoiditis, or dental infection; hematogenous seeding; or cranial trauma. In view of the high morbidity and mortality of ICA and the fact that hyperbaric oxygen therapy (HBO2) is relatively non-invasive and carries a low complication rate, the risk-benefit ratio favors adjunct use of HBO2 therapy in selected patients with intracranial abscess.

A fully automated method for late ventricular diastole frame selection in post-dive echocardiography without ECG gating.

Venous gas emboli (VGE) are often quantified as a marker of decompression stress on echocardiograms. Bubble-counting has been proposed as an easy to learn method, but remains time-consuming, rendering large dataset analysis impractical. Computer automation of VGE counting following this method has therefore been suggested as a means to eliminate rater bias and save time. A necessary step for this automation relies on the selection of a frame during late ventricular diastole (LVD) for each cardiac cycle of the recording. Since electrocardiograms (ECG) are not always recorded in field experiments, here we propose a fully automated method for LVD frame selection based on regional intensity minimization. The algorithm is tested on 20 previously acquired echocardiography recordings (from the original bubble-counting publication), half of which were acquired at rest (Rest) and the other half after leg flexions (Flex). From the 7,140 frames analyzed, sensitivity was found to be 0.913 [95% CI: 0.875-0.940] and specificity 0.997 [95% CI: 0.996-0.998]. The method's performance is also compared to that of random chance selection and found to perform significantly better (p≺0.0001). No trend in algorithm performance was found with respect to VGE counts, and no significant difference was found between Flex and Rest (p>0.05). In conclusion, full automation of LVD frame selection for the purpose of bubble counting in post-dive echocardiography has been established with excellent accuracy, although we caution that high quality acquisitions remain paramount in retaining high reliability.