Search

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. [ABSTRACT FROM AUTHOR]

Objective: To utilize sidestream dark field video microscopic technology to evaluate the endothelium in a canine hemorrhagic shock and resuscitation model., Methods: 6 purpose-bred adult dogs were anesthetized, instrumented, and subjected to hemorrhagic shock from September 2021 through June 2022. Each dog was resuscitated with 5 resuscitation strategies in an experimental crossover design study: (1) lactated Ringer's solution (LRS) and hydroxyethyl starch (HES) solution; (2) canine chilled whole blood (CWB); (3) canine fresh frozen plasma (FFP) and packed RBCs (pRBC); (4) canine freeze-dried plasma (FDP) and hemoglobin-based oxygen carrier (HBOC); or (5) HBOC/FDP and canine lyophilized platelets. Sidestream dark field video microscopic evaluation was performed at 5 time points: commencement, after hemorrhage, after shock, after resuscitation (T135), and conclusion (T180)., Results: There was a significant difference between the perfused boundary region (PBR) measurements when comparing the LRS/HES resuscitation arm to the CWB and FFP/pRBC resuscitation arms at T180. A significant difference in PBR was appreciated in the LRS/HES arm at T135 and T180 compared to its baseline. No other significant differences in PBR were appreciated when resuscitation arms were compared longitudinally or to each other., Conclusions: Shelf-stable blood products preserved the endothelial glycocalyx similarly to CWB and pRBC/FFP as evaluated by sidestream dark field video microscopy. Lactated Ringer and HES solutions did not adequately preserve the endothelial glycocalyx compared to CWB and pRBC/FFP., Clinical Relevance: Shelf-stable blood products are a viable option to preserve the endothelial glycocalyx when used during hemorrhagic resuscitation in 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., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2024 Hernandez Torres, Holland, Edwards, Venn and Snider.)