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.

A fully automated algorithm for heart rate detection in post-dive precordial Doppler ultrasound.

Background: Doppler ultrasound is used currently in decompression research for the evaluation of venous gas emboli (VGE). Estimation of heart rate from post-dive Doppler ultrasound recordings can provide a tool for the evaluation of physiological changes from decompression stress, as well as aid in the development of automated VGE detection algorithms that relate VGE presence to cardiac activity. Method: An algorithm based on short-term autocorrelation was developed in MATLAB to estimate the heart rate in post-dive precordial Doppler ultrasound. The algorithm was evaluated on 21 previously acquired and labeled precordial recordings spanning Kisman-Masurel (KM) codes of 111-444 (KM I-IV) with manually derived instantaneous heart rates. Results: A window size of at least two seconds was necessary for robust and accurate instantaneous heart rate estimation with a mean error of 1.56 ± 7.10 bpm. Larger window sizes improved the algorithm performance, at the cost of beat-to-beat heart rate estimates. We also found that our algorithm provides good results for low KM grade Doppler recordings with and without flexion, and high KM grades without flexion. High KM grades observed after movement produced the greatest mean absolute error of 6.12 ± 8.40 bpm. Conclusion: We have developed a fully automated algorithm for the estimation of heart rate in post-dive precordial Doppler ultrasound recordings.

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.

Perspective on ultrasound bioeffects and possible implications for continuous post-dive monitoring safety.

Ultrasound monitoring, both in the form of Doppler and 2D echocardiography, has been used post-dive to detect decompression bubbles circulating in the bloodstream. With large variability in both bubble time course and loads, it has been hypothesised that shorter periods between imaging, or even continuous imaging, could provide more accurate post-dive assessments. However, while considering applications of ultrasound imaging post-decompression, it may also be prudent to consider the possibility of ultrasound-induced bioeffects. Clinical ultrasound studies using microbubble contrast agents have shown bioeffect generation with acoustic powers much lower than those used in post-dive monitoring. However, to date no studies have specifically investigated potential bioeffect generation from continuous post-dive echocardiography. This review discusses what can be drawn from the current ultrasound and diving literature on the safety of bubble sonication and highlights areas where more studies are needed. An overview of the ultrasound-bubble mechanisms that lead to bioeffects and analyses of ultrasound contrast agent studies on bioeffect generation in the pulmonary and cardiovascular systems are provided to illustrate how bubbles under ultrasound can cause damage within the body. Along with clinical ultrasound studies, studies investigating the effects of decompression bubbles under ultrasound are analysed and open questions regarding continuous post-dive monitoring safety are discussed.

Effect of Acoustic Parameters and Microbubble Concentration on the Likelihood of Encapsulated Microbubble Coalescence.

Microbubble contrast agents are commonly used for therapeutic and diagnostic imaging applications. Under certain conditions, these contrast agents can coalesce on ultrasound application and form larger bubbles than the initial population. The formation of large microbubbles potentially influences therapeutic outcomes and imaging quality. We studied clinically relevant ultrasound parameters related to low-pressure therapy and contrast-enhanced ultrasound imaging to determine their effect on microbubble coalescence and subsequent changes in microbubble size distributions in vitro. Results indicate that therapeutic ultrasound at low frequencies, moderate pressures and high duty cycles are capable of forming bubbles greater than two times larger than the initial bubble distribution. Furthermore, acoustic parameters related to contrast-enhanced ultrasound imaging that are at higher frequency, low-pressure and low-duty cycle exhibit no statistically significant changes in bubble diameter, suggesting that standard contrast ultrasound imaging does not cause coalescence. Overall, this work suggests that the microbubble coalescence phenomenon can readily occur at acoustic parameters used in therapeutic ultrasound, generating bubbles much larger than those found in commercial contrast agents, although coalescence is unlikely to be significant in diagnostic contrast-enhanced ultrasound imaging. This observation warrants further expansion of parameter ranges and investigation of resulting effects.

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.

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.