Adaptive closed-loop resuscitation controllers for hemorrhagic shock resuscitation.

BACKGROUND: After hemorrhage control, fluid resuscitation is the most important intervention for hemorrhage. Even skilled providers can find resuscitation challenging to manage, especially when multiple patients require care. In the future, attention-demanding medical tasks like fluid resuscitation for hemorrhage patients may be reassigned to autonomous medical systems when availability of skilled human providers is limited, such as in austere military settings and mass casualty incidents. Central to this endeavor is the development and optimization of control architectures for physiological closed-loop control systems (PCLCs). PCLCs can take many forms, from simple table look-up methods to widely used proportional-integral-derivative or fuzzy-logic control theory. Here, we describe the design and optimization of multiple adaptive resuscitation controllers (ARCs) that we have purpose-built for the resuscitation of hemorrhaging patients. STUDY DESIGN AND METHODS: Three ARC designs were evaluated that measured pressure-volume responsiveness using different methodologies during resuscitation from which adapted infusion rates were calculated. These controllers were adaptive in that they estimated required infusion flow rates based on measured volume responsiveness. A previously developed hardware-in-loop test platform was used to evaluate the ARCs implementations across several hemorrhage scenarios. RESULTS: After optimization, we found that our purpose-built controllers outperformed traditional control system architecture as embodied in our previously developed dual-input fuzzy-logic controller. DISCUSSION: Future efforts will focus on engineering our purpose-built control systems to be robust to noise in the physiological signal coming to the controller from the patient as well as testing controller performance across a range of test scenarios and in vivo.

Development and Characterization of a Self-Tightening Tourniquet System.

Uncontrolled hemorrhage remains a leading cause of death in both emergency and military medicine. Tourniquets are essential to stopping hemorrhage in these scenarios, but they suffer from subjective, inconsistent application. Here, we demonstrate how tourniquet application can be automated using sensors and computer algorithms. The auto-tourniquet self-tightens until blood pressure oscillations are no longer registered by the pressure sensor connected to the pneumatic pressure cuff. The auto-tourniquet's performance in stopping the bleed was comparable to manual tourniquet application, but the time required to fully occlude the bleed was longer. Application of the tourniquet was significantly smoother, and less variable, for the automatic tourniquet compared to manual tourniquet application. This proof-of-concept study highlights how automated tourniquets can be integrated with sensors to provide a much more consistent application and use compared to manual application, even in controlled, low stress testing conditions. Future work will investigate different sensors and tourniquets to improve the application time and repeatability.

Supervisory Algorithm for Autonomous Hemodynamic Management Systems.

Future military conflicts will require new solutions to manage combat casualties. The use of automated medical systems can potentially address this need by streamlining and augmenting the delivery of medical care in both emergency and combat trauma environments. However, in many situations, these systems may need to operate in conjunction with other autonomous and semi-autonomous devices. Management of complex patients may require multiple automated systems operating simultaneously and potentially competing with each other. Supervisory controllers capable of harmonizing multiple closed-loop systems are thus essential before multiple automated medical systems can be deployed in managing complex medical situations. The objective for this study was to develop a Supervisory Algorithm for Casualty Management (SACM) that manages decisions and interplay between two automated systems designed for management of hemorrhage control and resuscitation: an automatic extremity tourniquet system and an adaptive resuscitation controller. SACM monitors the required physiological inputs for both systems and synchronizes each respective system as needed. We present a series of trauma experiments carried out in a physiologically relevant benchtop circulatory system in which SACM must recognize extremity or internal hemorrhage, activate the corresponding algorithm to apply a tourniquet, and then resuscitate back to the target pressure setpoint. SACM continues monitoring after the initial stabilization so that additional medical changes can be quickly identified and addressed, essential to extending automation algorithms past initial trauma resuscitation into extended monitoring. Overall, SACM is an important step in transitioning automated medical systems into emergency and combat trauma situations. Future work will address further interplay between these systems and integrate additional medical systems.

A flexible, robust microbead-based assay for quantification and normalization of target protein concentrations.

Although there are many methods for quantifying the concentration of specific proteins in samples, current techniques are technically challenging or do not easily lend themselves to normalization. Here, we describe a microbead-based assay for quantifying specific protein concentration(s) that is high-throughput, inexpensive, simple-to-use, and intrinsically incorporates normalization against the sample total protein content. This assay, termed the FRANC assay, exploits high affinity biotin-streptavidin binding to couple sample proteins to streptavidin-labelled magnetic microbeads. Proteins are then antibody-probed, followed by labeling of proteins on the microbead with fluorescent dye, and flow cytometry-based analysis. The FRANC assay demonstrates detection limits for target proteins in the femtogram range, with a linear range up to as much as 10 ng. Normalization of target protein concentrations resulted in an 80% reduction in variability as compared to non-normalized measurements. We conclude that the FRANC assay offers attractive advantages over current methods for quantifying specific protein(s) in samples.

Using AI Segmentation Models to Improve Foreign Body Detection and Triage from Ultrasound Images.

Medical imaging can be a critical tool for triaging casualties in trauma situations. In remote or military medicine scenarios, triage is essential for identifying how to use limited resources or prioritize evacuation for the most serious cases. Ultrasound imaging, while portable and often available near the point of injury, can only be used for triage if images are properly acquired, interpreted, and objectively triage scored. Here, we detail how AI segmentation models can be used for improving image interpretation and objective triage evaluation for a medical application focused on foreign bodies embedded in tissues at variable distances from critical neurovascular features. Ultrasound images previously collected in a tissue phantom with or without neurovascular features were labeled with ground truth masks. These image sets were used to train two different segmentation AI frameworks: YOLOv7 and U-Net segmentation models. Overall, both approaches were successful in identifying shrapnel in the image set, with U-Net outperforming YOLOv7 for single-class segmentation. Both segmentation models were also evaluated with a more complex image set containing shrapnel, artery, vein, and nerve features. YOLOv7 obtained higher precision scores across multiple classes whereas U-Net achieved higher recall scores. Using each AI model, a triage distance metric was adapted to measure the proximity of shrapnel to the nearest neurovascular feature, with U-Net more closely mirroring the triage distances measured from ground truth labels. Overall, the segmentation AI models were successful in detecting shrapnel in ultrasound images and could allow for improved injury triage in emergency medicine scenarios.

Refinement of machine learning arterial waveform models for predicting blood loss in canines.

Introduction: Hemorrhage remains a leading cause of death in civilian and military trauma. Hemorrhages also extend to military working dogs, who can experience injuries similar to those of the humans they work alongside. Unfortunately, current physiological monitoring is often inadequate for early detection of hemorrhage. Here, we evaluate if features extracted from the arterial waveform can allow for early hemorrhage prediction and improved intervention in canines. Methods: In this effort, we extracted more than 1,900 features from an arterial waveform in canine hemorrhage datasets prior to hemorrhage, during hemorrhage, and during a shock hold period. Different features were used as input to decision tree machine learning (ML) model architectures to track three model predictors-total blood loss volume, estimated percent blood loss, and area under the time versus hemorrhaged blood volume curve. Results: ML models were successfully developed for total and estimated percent blood loss, with the total blood loss having a higher correlation coefficient. The area predictors were unsuccessful at being directly predicted by decision tree ML models but could be calculated indirectly from the ML prediction models for blood loss. Overall, the area under the hemorrhage curve had the highest sensitivity for detecting hemorrhage at approximately 4 min after hemorrhage onset, compared to more than 45 min before detection based on mean arterial pressure. Conclusion: ML methods successfully tracked hemorrhage and provided earlier prediction in canines, potentially improving hemorrhage detection and objectifying triage for veterinary medicine. Further, its use can potentially be extended to human use with proper training datasets.

Deep learning models for interpretation of point of care ultrasound in military working dogs.

Introduction: Military working dogs (MWDs) are essential for military operations in a wide range of missions. With this pivotal role, MWDs can become casualties requiring specialized veterinary care that may not always be available far forward on the battlefield. Some injuries such as pneumothorax, hemothorax, or abdominal hemorrhage can be diagnosed using point of care ultrasound (POCUS) such as the Global FAST® exam. This presents a unique opportunity for artificial intelligence (AI) to aid in the interpretation of ultrasound images. In this article, deep learning classification neural networks were developed for POCUS assessment in MWDs. Methods: Images were collected in five MWDs under general anesthesia or deep sedation for all scan points in the Global FAST® exam. For representative injuries, a cadaver model was used from which positive and negative injury images were captured. A total of 327 ultrasound clips were captured and split across scan points for training three different AI network architectures: MobileNetV2, DarkNet-19, and ShrapML. Gradient class activation mapping (GradCAM) overlays were generated for representative images to better explain AI predictions. Results: Performance of AI models reached over 82% accuracy for all scan points. The model with the highest performance was trained with the MobileNetV2 network for the cystocolic scan point achieving 99.8% accuracy. Across all trained networks the diaphragmatic hepatorenal scan point had the best overall performance. However, GradCAM overlays showed that the models with highest accuracy, like MobileNetV2, were not always identifying relevant features. Conversely, the GradCAM heatmaps for ShrapML show general agreement with regions most indicative of fluid accumulation. Discussion: Overall, the AI models developed can automate POCUS predictions in MWDs. Preliminarily, ShrapML had the strongest performance and prediction rate paired with accurately tracking fluid accumulation sites, making it the most suitable option for eventual real-time deployment with ultrasound systems. Further integration of this technology with imaging technologies will expand use of POCUS-based triage of MWDs.

Evaluation of Deep Learning Model Architectures for Point-of-Care Ultrasound Diagnostics.

Point-of-care ultrasound imaging is a critical tool for patient triage during trauma for diagnosing injuries and prioritizing limited medical evacuation resources. Specifically, an eFAST exam evaluates if there are free fluids in the chest or abdomen but this is only possible if ultrasound scans can be accurately interpreted, a challenge in the pre-hospital setting. In this effort, we evaluated the use of artificial intelligent eFAST image interpretation models. Widely used deep learning model architectures were evaluated as well as Bayesian models optimized for six different diagnostic models: pneumothorax (i) B- or (ii) M-mode, hemothorax (iii) B- or (iv) M-mode, (v) pelvic or bladder abdominal hemorrhage and (vi) right upper quadrant abdominal hemorrhage. Models were trained using images captured in 27 swine. Using a leave-one-subject-out training approach, the MobileNetV2 and DarkNet53 models surpassed 85% accuracy for each M-mode scan site. The different B-mode models performed worse with accuracies between 68% and 74% except for the pelvic hemorrhage model, which only reached 62% accuracy for all model architectures. These results highlight which eFAST scan sites can be easily automated with image interpretation models, while other scan sites, such as the bladder hemorrhage model, will require more robust model development or data augmentation to improve performance. With these additional improvements, the skill threshold for ultrasound-based triage can be reduced, thus expanding its utility in the pre-hospital setting.

Toward Smart, Automated Junctional Tourniquets-AI Models to Interpret Vessel Occlusion at Physiological Pressure Points.

Hemorrhage is the leading cause of preventable death in both civilian and military medicine. Junctional hemorrhages are especially difficult to manage since traditional tourniquet placement is often not possible. Ultrasound can be used to visualize and guide the caretaker to apply pressure at physiological pressure points to stop hemorrhage. However, this process is technically challenging, requiring the vessel to be properly positioned over rigid boney surfaces and applying sufficient pressure to maintain proper occlusion. As a first step toward automating this life-saving intervention, we demonstrate an artificial intelligence algorithm that classifies a vessel as patent or occluded, which can guide a user to apply the appropriate pressure required to stop flow. Neural network models were trained using images captured from a custom tissue-mimicking phantom and an ex vivo swine model of the inguinal region, as pressure was applied using an ultrasound probe with and without color Doppler overlays. Using these images, we developed an image classification algorithm suitable for the determination of patency or occlusion in an ultrasound image containing color Doppler overlay. Separate AI models for both test platforms were able to accurately detect occlusion status in test-image sets to more than 93% accuracy. In conclusion, this methodology can be utilized for guiding and monitoring proper vessel occlusion, which, when combined with automated actuation and other AI models, can allow for automated junctional tourniquet application.

Design and testing of ultrasound probe adapters for a robotic imaging platform.

Medical imaging-based triage is a critical tool for emergency medicine in both civilian and military settings. Ultrasound imaging can be used to rapidly identify free fluid in abdominal and thoracic cavities which could necessitate immediate surgical intervention. However, proper ultrasound image capture requires a skilled ultrasonography technician who is likely unavailable at the point of injury where resources are limited. Instead, robotics and computer vision technology can simplify image acquisition. As a first step towards this larger goal, here, we focus on the development of prototypes for ultrasound probe securement using a robotics platform. The ability of four probe adapter technologies to precisely capture images at anatomical locations, repeatedly, and with different ultrasound transducer types were evaluated across more than five scoring criteria. Testing demonstrated two of the adapters outperformed the traditional robot gripper and manual image capture, with a compact, rotating design compatible with wireless imaging technology being most suitable for use at the point of injury. Next steps will integrate the robotic platform with computer vision and deep learning image interpretation models to automate image capture and diagnosis. This will lower the skill threshold needed for medical imaging-based triage, enabling this procedure to be available at or near the point of injury.

Using Ultrasound Image Augmentation and Ensemble Predictions to Prevent Machine-Learning Model Overfitting.

Deep learning predictive models have the potential to simplify and automate medical imaging diagnostics by lowering the skill threshold for image interpretation. However, this requires predictive models that are generalized to handle subject variability as seen clinically. Here, we highlight methods to improve test accuracy of an image classifier model for shrapnel identification using tissue phantom image sets. Using a previously developed image classifier neural network-termed ShrapML-blind test accuracy was less than 70% and was variable depending on the training/test data setup, as determined by a leave one subject out (LOSO) holdout methodology. Introduction of affine transformations for image augmentation or MixUp methodologies to generate additional training sets improved model performance and overall accuracy improved to 75%. Further improvements were made by aggregating predictions across five LOSO holdouts. This was done by bagging confidences or predictions from all LOSOs or the top-3 LOSO confidence models for each image prediction. Top-3 LOSO confidence bagging performed best, with test accuracy improved to greater than 85% accuracy for two different blind tissue phantoms. This was confirmed by gradient-weighted class activation mapping to highlight that the image classifier was tracking shrapnel in the image sets. Overall, data augmentation and ensemble prediction approaches were suitable for creating more generalized predictive models for ultrasound image analysis, a critical step for real-time diagnostic deployment.

An extended focused assessment with sonography in trauma ultrasound tissue-mimicking phantom for developing automated diagnostic technologies.

Introduction: Medical imaging-based triage is critical for ensuring medical treatment is timely and prioritized. However, without proper image collection and interpretation, triage decisions can be hard to make. While automation approaches can enhance these triage applications, tissue phantoms must be developed to train and mature these novel technologies. Here, we have developed a tissue phantom modeling the ultrasound views imaged during the enhanced focused assessment with sonography in trauma exam (eFAST). Methods: The tissue phantom utilized synthetic clear ballistic gel with carveouts in the abdomen and rib cage corresponding to the various eFAST scan points. Various approaches were taken to simulate proper physiology without injuries present or to mimic pneumothorax, hemothorax, or abdominal hemorrhage at multiple locations in the torso. Multiple ultrasound imaging systems were used to acquire ultrasound scans with or without injury present and were used to train deep learning image classification predictive models. Results: Performance of the artificial intelligent (AI) models trained in this study achieved over 97% accuracy for each eFAST scan site. We used a previously trained AI model for pneumothorax which achieved 74% accuracy in blind predictions for images collected with the novel eFAST tissue phantom. Grad-CAM heat map overlays for the predictions identified that the AI models were tracking the area of interest for each scan point in the tissue phantom. Discussion: Overall, the eFAST tissue phantom ultrasound scans resembled human images and were successful in training AI models. Tissue phantoms are critical first steps in troubleshooting and developing medical imaging automation technologies for this application that can accelerate the widespread use of ultrasound imaging for emergency triage.

Performance Comparison of Object Detection Networks for Shrapnel Identification in Ultrasound Images.

Ultrasound imaging is a critical tool for triaging and diagnosing subjects but only if images can be properly interpreted. Unfortunately, in remote or military medicine situations, the expertise to interpret images can be lacking. Machine-learning image interpretation models that are explainable to the end user and deployable in real time with ultrasound equipment have the potential to solve this problem. We have previously shown how a YOLOv3 (You Only Look Once) object detection algorithm can be used for tracking shrapnel, artery, vein, and nerve fiber bundle features in a tissue phantom. However, real-time implementation of an object detection model requires optimizing model inference time. Here, we compare the performance of five different object detection deep-learning models with varying architectures and trainable parameters to determine which model is most suitable for this shrapnel-tracking ultrasound image application. We used a dataset of more than 16,000 ultrasound images from gelatin tissue phantoms containing artery, vein, nerve fiber, and shrapnel features for training and evaluating each model. Every object detection model surpassed 0.85 mean average precision except for the detection transformer model. Overall, the YOLOv7tiny model had the higher mean average precision and quickest inference time, making it the obvious model choice for this ultrasound imaging application. Other object detection models were overfitting the data as was determined by lower testing performance compared with higher training performance. In summary, the YOLOv7tiny object detection model had the best mean average precision and inference time and was selected as optimal for this application. Next steps will implement this object detection algorithm for real-time applications, an important next step in translating AI models for emergency and military medicine.

An Explainable Machine-Learning Model for Compensatory Reserve Measurement: Methods for Feature Selection and the Effects of Subject Variability.

Tracking vital signs accurately is critical for triaging a patient and ensuring timely therapeutic intervention. The patient's status is often clouded by compensatory mechanisms that can mask injury severity. The compensatory reserve measurement (CRM) is a triaging tool derived from an arterial waveform that has been shown to allow for earlier detection of hemorrhagic shock. However, the deep-learning artificial neural networks developed for its estimation do not explain how specific arterial waveform elements lead to predicting CRM due to the large number of parameters needed to tune these models. Alternatively, we investigate how classical machine-learning models driven by specific features extracted from the arterial waveform can be used to estimate CRM. More than 50 features were extracted from human arterial blood pressure data sets collected during simulated hypovolemic shock resulting from exposure to progressive levels of lower body negative pressure. A bagged decision tree design using the ten most significant features was selected as optimal for CRM estimation. This resulted in an average root mean squared error in all test data of 0.171, similar to the error for a deep-learning CRM algorithm at 0.159. By separating the dataset into sub-groups based on the severity of simulated hypovolemic shock withstood, large subject variability was observed, and the key features identified for these sub-groups differed. This methodology could allow for the identification of unique features and machine-learning models to differentiate individuals with good compensatory mechanisms against hypovolemia from those that might be poor compensators, leading to improved triage of trauma patients and ultimately enhancing military and emergency medicine.

Verification and Validation of Lower Body Negative Pressure as a Non-Invasive Bioengineering Tool for Testing Technologies for Monitoring Human Hemorrhage.

Since hemorrhage is a leading cause of preventable death in both civilian and military settings, the development of advanced decision support monitoring capabilities is necessary to promote improved clinical outcomes. The emergence of lower body negative pressure (LBNP) has provided a bioengineering technology for inducing progressive reductions in central blood volume shown to be accurate as a model for the study of the early compensatory stages of hemorrhage. In this context, the specific aim of this study was to provide for the first time a systematic technical evaluation to meet a commonly accepted engineering standard based on the FDA-recognized Standard for Assessing Credibility of Modeling through Verification and Validation (V&V) for Medical Devices (ASME standard V&V 40) specifically highlighting LBNP as a valuable resource for the safe study of hemorrhage physiology in humans. As an experimental tool, evidence is presented that LBNP is credible, repeatable, and validated as an analog for the study of human hemorrhage physiology compared to actual blood loss. The LBNP tool can promote the testing and development of advanced monitoring algorithms and evaluating wearable sensors with the goal of improving clinical outcomes during use in emergency medical settings.

Using an Ultrasound Tissue Phantom Model for Hybrid Training of Deep Learning Models for Shrapnel Detection.

Tissue phantoms are important for medical research to reduce the use of animal or human tissue when testing or troubleshooting new devices or technology. Development of machine-learning detection tools that rely on large ultrasound imaging data sets can potentially be streamlined with high quality phantoms that closely mimic important features of biological tissue. Here, we demonstrate how an ultrasound-compliant tissue phantom comprised of multiple layers of gelatin to mimic bone, fat, and muscle tissue types can be used for machine-learning training. This tissue phantom has a heterogeneous composition to introduce tissue level complexity and subject variability in the tissue phantom. Various shrapnel types were inserted into the phantom for ultrasound imaging to supplement swine shrapnel image sets captured for applications such as deep learning algorithms. With a previously developed shrapnel detection algorithm, blind swine test image accuracy reached more than 95% accuracy when training was comprised of 75% tissue phantom images, with the rest being swine images. For comparison, a conventional MobileNetv2 deep learning model was trained with the same training image set and achieved over 90% accuracy in swine predictions. Overall, the tissue phantom demonstrated high performance for developing deep learning models for ultrasound image classification.

An image classification deep-learning algorithm for shrapnel detection from ultrasound images.

Ultrasound imaging is essential for non-invasively diagnosing injuries where advanced diagnostics may not be possible. However, image interpretation remains a challenge as proper expertise may not be available. In response, artificial intelligence algorithms are being investigated to automate image analysis and diagnosis. Here, we highlight an image classification convolutional neural network for detecting shrapnel in ultrasound images. As an initial application, different shrapnel types and sizes were embedded first in a tissue mimicking phantom and then in swine thigh tissue. The algorithm architecture was optimized stepwise by minimizing validation loss and maximizing F1 score. The final algorithm design trained on tissue phantom image sets had an F1 score of 0.95 and an area under the ROC curve of 0.95. It maintained higher than a 90% accuracy for each of 8 shrapnel types. When trained only on swine image sets, the optimized algorithm format had even higher metrics: F1 and area under the ROC curve of 0.99. Overall, the algorithm developed resulted in strong classification accuracy for both the tissue phantom and animal tissue. This framework can be applied to other trauma relevant imaging applications such as internal bleeding to further simplify trauma medicine when resources and image interpretation are scarce.

Comparison of Ultrasound Image Classifier Deep Learning Algorithms for Shrapnel Detection.

Ultrasound imaging is essential in emergency medicine and combat casualty care, oftentimes used as a critical triage tool. However, identifying injuries, such as shrapnel embedded in tissue or a pneumothorax, can be challenging without extensive ultrasonography training, which may not be available in prolonged field care or emergency medicine scenarios. Artificial intelligence can simplify this by automating image interpretation but only if it can be deployed for use in real time. We previously developed a deep learning neural network model specifically designed to identify shrapnel in ultrasound images, termed ShrapML. Here, we expand on that work to further optimize the model and compare its performance to that of conventional models trained on the ImageNet database, such as ResNet50. Through Bayesian optimization, the model's parameters were further refined, resulting in an F1 score of 0.98. We compared the proposed model to four conventional models: DarkNet-19, GoogleNet, MobileNetv2, and SqueezeNet which were down-selected based on speed and testing accuracy. Although MobileNetv2 achieved a higher accuracy than ShrapML, there was a tradeoff between accuracy and speed, with ShrapML being 10× faster than MobileNetv2. In conclusion, real-time deployment of algorithms such as ShrapML can reduce the cognitive load for medical providers in high-stress emergency or miliary medicine scenarios.

Noninvasive Monitoring of Simulated Hemorrhage and Whole Blood Resuscitation.

Hemorrhage is the leading cause of preventable death from trauma. Accurate monitoring of hemorrhage and resuscitation can significantly reduce mortality and morbidity but remains a challenge due to the low sensitivity of traditional vital signs in detecting blood loss and possible hemorrhagic shock. Vital signs are not reliable early indicators because of physiological mechanisms that compensate for blood loss and thus do not provide an accurate assessment of volume status. As an alternative, machine learning (ML) algorithms that operate on an arterial blood pressure (ABP) waveform have been shown to provide an effective early indicator. However, these ML approaches lack physiological interpretability. In this paper, we evaluate and compare the performance of ML models trained on nine ABP-derived features that provide physiological insight, using a database of 13 human subjects from a lower-body negative pressure (LBNP) model of progressive central hypovolemia and subsequent progressive restoration to normovolemia (i.e., simulated hemorrhage and whole blood resuscitation). Data were acquired at multiple repressurization rates for each subject to simulate varying resuscitation rates, resulting in 52 total LBNP collections. This work is the first to use a single ABP-based algorithm to monitor both simulated hemorrhage and resuscitation. A gradient-boosted regression tree model trained on only the half-rise to dicrotic notch (HRDN) feature achieved a root-mean-square error (RMSE) of 13%, an R2 of 0.82, and area under the receiver operating characteristic curve of 0.97 for detecting decompensation. This single-feature model's performance compares favorably to previously reported results from more-complex black box machine learning models. This model further provides physiological insight because HRDN represents an approximate measure of the delay between the ABP ejected and reflected wave and therefore is an indication of cardiac and peripheral vascular mechanisms that contribute to the compensatory response to blood loss and replacement.

Evaluation of an Object Detection Algorithm for Shrapnel and Development of a Triage Tool to Determine Injury Severity.

Emergency medicine in austere environments rely on ultrasound imaging as an essential diagnostic tool. Without extensive training, identifying abnormalities such as shrapnel embedded in tissue, is challenging. Medical professionals with appropriate expertise are limited in resource-constrained environments. Incorporating artificial intelligence models to aid the interpretation can reduce the skill gap, enabling identification of shrapnel, and its proximity to important anatomical features for improved medical treatment. Here, we apply a deep learning object detection framework, YOLOv3, for shrapnel detection in various sizes and locations with respect to a neurovascular bundle. Ultrasound images were collected in a tissue phantom containing shrapnel, vein, artery, and nerve features. The YOLOv3 framework, classifies the object types and identifies the location. In the testing dataset, the model was successful at identifying each object class, with a mean Intersection over Union and average precision of 0.73 and 0.94, respectively. Furthermore, a triage tool was developed to quantify shrapnel distance from neurovascular features that could notify the end user when a proximity threshold is surpassed, and, thus, may warrant evacuation or surgical intervention. Overall, object detection models such as this will be vital to compensate for lack of expertise in ultrasound interpretation, increasing its availability for emergency and military medicine.