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

Evaluation of a Semi-Automated Ultrasound Guidance System for Central Vascular Access

Hemorrhage remains a leading cause of death in both military and civilian trauma settings. Oftentimes, the control and treatment of hemorrhage requires central vascular access and well-trained medical personnel. Automated technology is being developed that can lower the skill threshold for life-saving interventions. Here, we conduct independent evaluation testing of one such device, the Vu-Path™ Ultrasound Guidance system, or Vu-Path™. The device was designed to simplify needle insertion using a needle holder that ensures the needle is within the ultrasound field of view during its insertion into tissue, along with guidance lines shown on the user interface. We evaluated the performance of this device in a range of laboratory, animal, and human testing platforms. Overall, the device had a high success rate, achieving an 83% insertion accuracy in live animal testing across both normal and hypotensive blood pressures. Vu-Path™ was faster than manual, ultrasound-guided needle insertion and was nearly 1.5 times quicker for arterial and 2.3 times quicker for venous access. Human usability feedback highlighted that 80% of the participants would use this device for central line placement. Study users noted that the guidance lines and small form factor were useful design features. However, issues were raised regarding the needle insertion angle being too steep, with potential positioning challenges as the needle remains fixed to the ultrasound probe. Regardless, 75% of the participants believed that personnel with any level of clinical background could use the device for central vascular access. Overall, Vu-Path™ performed well across a range of testing situations, and potential design improvements were noted. With adjustments to the device, central vascular access can be made more accessible on battlefields in the future.

A Dynamic Ultrasound Phantom with Tissue-Mimicking Mechanical and Acoustic Properties

Tissue-mimicking phantoms are valuable tools that aid in improving the equipment and training available to medical professionals. However, current phantoms possess limited utility due to their inability to precisely simulate multiple physical properties simultaneously, which is crucial for achieving a system understanding of dynamic human tissues. In this work, novel materials design and fabrication processes to produce various tissue-mimicking materials (TMMs) for skin, adipose, muscle, and soft tissue at a human scale are developed. Target properties (Young's modulus, density, speed of sound, and acoustic attenuation) are first defined for each TMM based on literature. Each TMM recipe is developed, associated mechanical and acoustic properties are characterized, and the TMMs are confirmed to have comparable mechanical and acoustic properties with the corresponding human tissues. Furthermore, a novel sacrificial core to fabricate a hollow, ellipsoid-shaped bladder phantom complete with inlet and outlet tubes, which allow liquids to flow through and expand this phantom, is adopted. This dynamic bladder phantom with realistic mechanical and acoustic properties to human tissues in combination with the developed skin, soft tissue, and subcutaneous adipose tissue TMMs, culminates in a human scale torso tank and electro-mechanical system that can be systematically utilized for characterizing various medical imaging devices.

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.

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.

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.

A Reliable Approach for Fabricating Tissue-Mimicking Phantoms with Designated Dielectric Properties from 16 MHz to 3 GHz

Tissue-mimicking dielectric phantoms are widely used to mimic the relative permittivity and conductivity of human tissues in various medical applications. The artificial material combinations determine the characterization of dialectic phantoms. However, a method that reliably determined the composition of artificial materials with designed values of dielectric properties and frequency is still lacking. In this work, we propose a method that easily determine the compositions of phantom to mimic the human tissues from 16 MHz to 3 GHz.

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.