Feasibility of intra-operative image guidance in burn excision surgery with multispectral imaging and deep learning.

BACKGROUND: Exposing a healthy wound bed for skin grafting is an important step during burn surgery to ensure graft take and maintain good functional outcomes. Currently, the removal of non-viable tissue in the burn wound bed during excision is determined by expert clinician judgment. Using a porcine model of tangential burn excision, we investigated the effectiveness of an intraoperative multispectral imaging device combined with artificial intelligence to aid clinician judgment for the excision of non-viable tissue. METHODS: Multispectral imaging data was obtained from serial tangential excisions of thermal burn injuries and used to train a deep learning algorithm to identify the presence and location of non-viable tissue in the wound bed. Following algorithm development, we studied the ability of two surgeons to estimate wound bed viability, both unaided and aided by the imaging device. RESULTS: The deep learning algorithm was 87% accurate in identifying the viability of a burn wound bed. When paired with the surgeons, this device significantly improved their abilities to determine the viability of the wound bed by 25% (p = 0.03). Each time a surgeon changed their decision after seeing the AI model output, it was always a change from an incorrect decision to excise more tissue to a correct decision to stop excision. CONCLUSION: This study provides insight into the feasibility of image-guided burn excision, its effect on surgeon decision making, and suggests further investigation of a real-time imaging system for burn surgery could reduce over-excision of burn wounds.

Contrast enhanced computed tomography of small ruminants: Caprine and ovine.

The use of small ruminants, mainly sheep and goats, is increasing in biomedical research. Small ruminants are a desirable animal model due to their human-like anatomy and physiology. However, the large variability between studies and lack of baseline data on these animals creates a barrier to further research. This knowledge gap includes a lack of computed tomography (CT) scans for healthy subjects. Full body, contrast enhanced CT scans of caprine and ovine subjects were acquired for subsequent modeling studies. Scans were acquired from an ovine specimen (male, Khatadin, 30-35 kg) and caprine specimen (female, Nubian 30-35 kg). Scans were acquired with and without contrast. Contrast enhanced scans utilized 1.7 mL/kg of contrast administered at 2 mL/s and scans were acquired 20 seconds, 80 seconds, and 5 minutes post-contrast. Scans were taken at 100 kV and 400 mA. Each scan was reconstructed using a bone window and a soft tissue window. Sixteen full body image data sets are presented (2 specimens by 4 contrast levels by 2 reconstruction windows) and are available for download through the form located at: https://redcap.link/COScanData. Scans showed that the post-contrast timing and scan reconstruction method affected structural visualization. The data are intended for further biomedical research on ruminants related to computational model development, device prototyping, comparative diagnostics, intervention planning, and other forms of translational research.