Detection and localization of peripheral vascular bleeding using Doppler ultrasound

Automatic Hemorrhage Detection From Color Doppler Ultrasound Using a Generative Adversarial Network (GAN)-Based Anomaly Detection Method

Hemorrhage control has been identified as a priority focus area both for civilian and military populations in the United States because exsanguination is the most common cause of preventable death in hemorrhagic injury. Non-compressible torso hemorrhage (NCTH) has high mortality rate and there are currently no broadly available therapies for NCTH outside of a surgical room environment. Novel therapies, which include High Intensity Focused Ultrasound (HIFU) have emerged as promising methods for hemorrhage control as they can non-invasively cauterize bleeding tissue deep within the body without injuring uninvolved regions. A major challenge in the application of HIFU with color Doppler US guidance is the interpretation and optimization of the blood flow images in real-time to identify the hemorrhagic focus. Today, this task requires an expert sonographer, limiting the utility of this therapy in non-clinical environments. In this work, we investigated the feasibility of an automated hemorrhage detection method using a Generative Adversarial Network (GAN) for anomaly detection that learns a manifold of normal blood flow variability and subsequently identifies anomalous flow patterns that fall outside the learned manifold. As an initial feasibility study, we collected ultrasound color Doppler images of femoral arteries in an animal model of vascular injury (N = 11 pigs). Velocity information of the blood flow were extracted from the color Doppler images that were used for training and testing the anomaly detection network. Normotensive images from 8 pigs were used for training, and testing was performed on normotensive, immediately after injury, 10 minutes post-injury and 30 minutes post-injury images from 3 other pigs. The residual images or the reconstructed error maps show promise in detecting hemorrhages with an AUC of 0.90, 0.87, 0.62 immediately, 10 minutes post-injury and 30 minutes post-injury respectively with an overall AUC of 0.83.

Clinical implications of fracture-associated vascular damage in extremity and pelvic trauma

BACKGROUND

Vascular damage in polytrauma patients is associated with high mortality and morbidity. Therefore, specific clinical implications of vascular damage with fractures in major trauma patients are reassessed.

METHODS

This comprehensive nine-year retrospective single center cohort study analyzed demography, laboratory, treatment and outcome data from 3689 patients, 64 patients with fracture-associated vascular injuries were identified and were compared to a control group.

RESULTS

Vascular damage occurred in 7% of patients with upper and lower limb and pelvic fractures admitted to the trauma room. Overall survival was 80% in pelvic fracture and 97% in extremity fracture patients and comparable to non-vascular trauma patients. Additional arterial damage required substantial fluid administration and was visible as significantly anemia and disturbed coagulation tests upon admission. Open procedures were done in over 80% of peripheral extremity vascular damage. Endovascular procedures were predominant (87%) in pelvic injury.

CONCLUSION

Vascular damage is associated with high mortality rates especially in combination with pelvic fractures. Initial anemia, disturbed coagulation tests and the need for extensive pre-clinical fluid substitution were observed in the cohort with vascular damage. Therefore, fast diagnosis and early interventional and surgical procedures are necessary to optimize patient-specific outcome.

A System for Simple Real-Time Anastomotic Failure Detection and Wireless Blood Flow Monitoring in the Lower Limbs

Current totally implantable wireless blood flow monitors are large and cannot operate alongside nearby monitors. To alleviate the problems with the current monitors, we developed a system to monitor blood flow wirelessly, with a simple and easily interpretable real-time output. To the best of our knowledge, the implanted electronics are the smallest in reported literature, which reduces bio-burden. Calibration was performed across realistic physiological flow ranges using a syringe pump. The device's sensors connected directly to the bilateral femoral veins of swine. For each 1 min, blood flow was monitored, then, an occlusion was introduced, and then, the occlusion was removed to resume flow. Each vein of four pigs was monitored four times, totaling 32 data collections. The implant measured 1.70 cm3 without battery/encapsulation. Across its calibrated range, including equipment tolerances, the relative error is less than ±5% above 8 mL/min and between -0.8% and +1.2% at its largest calibrated flow rate, which to the best of our knowledge is the lowest reported in the literature across the measured calibration range. The average standard deviation of the flow waveform amplitude was three times greater than that of no-flow. Establishing the relative amplitude for the flow and no-flow waveforms was found necessary, particularly for noise modulated Doppler signals. Its size and accuracy, compared with other microcontroller-equipped totally implantable monitors, make it a good candidate for future tether-free free flap monitoring studies.