Ultrasound (US) imaging is a critical tool in emergency and military medicine because of its portability and immediate nature. However, proper image interpretation requires skill, limiting its utility in remote applications for conditions such as pneumothorax (PTX) which requires rapid intervention. Artificial intelligence has the potential to automate ultrasound image analysis for various pathophysiological conditions. Training models require large data sets and a means of troubleshooting in real-time for ultrasound integration deployment, and they also require large animal models or clinical testing. Here, we detail the development of a dynamic synthetic tissue phantom model for PTX and its use in training image classification algorithms. The model comprises a synthetic gelatin phantom cast in a custom 3D-printed rib mold and a lung mimicking phantom. When compared to PTX images acquired in swine, images from the phantom were similar in both PTX negative and positive mimicking scenarios. We then used a deep learning image classification algorithm, which we previously developed for shrapnel detection, to accurately predict the presence of PTX in swine images by only training on phantom image sets, highlighting the utility for a tissue phantom for AI applications.

Physiological Closed-Loop Controlled systems continue to take a growing part in clinical practice, offering possibilities of providing more accurate, goal-directed care while reducing clinicians’ cognitive and task load. These systems also provide a standardized approach for the clinical management of the patient, leading to a reduction in care variability across multiple dimensions. For fluid management and administration, the advantages of closed-loop technology are clear, especially in conditions that require precise care to improve outcomes, such as peri-operative care, trauma, and acute burn care. Controller design varies from simplistic to complex designs, based on detailed physiological models and adaptive properties that account for inter-patient and intra-patient variability; their maturity level ranges from theoretical models tested in silico to commercially available, FDA-approved products. This comprehensive scoping review was conducted in order to assess the current technological landscape of this field, describe the systems currently available or under development, and suggest further advancements that may unfold in the coming years. Ten distinct systems were identified and discussed.

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.

Hemorrhage remains a leading cause of death, with early goal-directed fluid resuscitation being a pillar of mortality prevention. While closed-loop resuscitation can potentially benefit this effort, development of these systems is resource-intensive, making it a challenge to compare infusion controllers and respective hardware within a range of physiologically relevant hemorrhage scenarios. Here, we present a hardware-in-loop automated testbed for resuscitation controllers (HATRC) that provides a simple yet robust methodology to evaluate controllers. HATRC is a flow-loop benchtop system comprised of multiple PhysioVessels which mimic pressure-volume responsiveness for different resuscitation infusates. Subject variability and infusate switching were integrated for more complex testing. Further, HATRC can modulate fluidic resistance to mimic arterial resistance changes after vasopressor administration. Finally, all outflow rates are computer-controlled, with rules to dictate hemorrhage, clotting, and urine rates. Using HATRC, we evaluated a decision-table controller at two sampling rates with different hemorrhage scenarios. HATRC allows quantification of twelve performance metrics for each controller configuration and scenario, producing heterogeneous results and highlighting the need for controller evaluation with multiple hemorrhage scenarios. In conclusion, HATRC can be used to evaluate closed-loop controllers through user-defined hemorrhage scenarios while rating their performance. Extensive controller troubleshooting using HATRC can accelerate product development and subsequent translation.

Uncontrolled hemorrhage is a leading cause of death in trauma situations. Developing solutions to automate hemorrhagic shock resuscitation may improve the outcomes for trauma patients. However, testing and development of automated solutions to address critical care interventions, oftentimes require extensive large animal studies for even initial troubleshooting. The use of accurate laboratory or in-silico models may provide a way to reduce the need for large animal datasets. Here, a tabletop model, for use in the development of fluid resuscitation with physiologically relevant pressure-volume responsiveness for high throughput testing, is presented. The design approach shown can be applied to any pressure-volume dataset through a process of curve-fitting, 3D modeling, and fabrication of a fluid reservoir shaped to the precise curve fit. Two case studies are presented here based on different resuscitation fluids: whole blood and crystalloid resuscitation. Both scenarios were derived from data acquired during porcine hemorrhage studies, used a pressure-volume curve to design and fabricate a 3D model, and evaluated to show that the test platform mimics the physiological data. The vessels produced based on data collected from pigs infused with whole blood and crystalloid were able to reproduce normalized pressure-volume curves within one standard deviation of the porcine data with mean residual differences of 0.018 and 0.016, respectively. This design process is useful for developing closed-loop algorithms for resuscitation and can simplify initial testing of technologies for this life-saving medical intervention.

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.