Abstract
Acute intestinal ischemia is a life-threatening condition. The current gold standard, with evaluation based on visual and tactile sensation, has low specificity. In this study, we explore the feasibility of using machine learning models on images of the intestine, to assess small intestinal viability. A digital microscope was used to acquire images of the jejunum in 10 pigs. Ischemic segments were created by local clamping (approximately 30 cm in width) of small arteries and veins in the mesentery and reperfusion was initiated by releasing the clamps. A series of images were acquired once an hour on the surface of each of the segments. The convolutional neural network (CNN) has previously been used to classify medical images, while knowledge is lacking whether CNNs have potential to classify ischemia-reperfusion injury on the small intestine. We compared how different deep learning models perform for this task. Moreover, the Shapley additive explanations (SHAP) method within explainable artificial intelligence (AI) was used to identify features that the model utilizes as important in classification of different ischemic injury degrees. To be able to assess to what extent we can trust our deep learning model decisions is critical in a clinical setting. A probabilistic model Bayesian CNN was implemented to estimate the model uncertainty which provides a confidence measure of our model decisions.
Highlights
Acute intestinal ischemia is a serious condition with a high mortality rate, where rapid diagnosis and treatment are of crucial importance [1,2]
There appears to be a clear separation between classes 10–14 and classes 15–18
In this study, we investigated whether microscopic images taken from the surface of the small intestine in vivo in a pig model, combined with deep learning, can be used to assess ischemia-reperfusion injuries
Summary
Acute intestinal ischemia is a serious condition with a high mortality rate, where rapid diagnosis and treatment are of crucial importance [1,2]. The estimation of tissue state can be based on color change, presence of visible peristalsis and bleeding from cut edges [1,2,3,4,5] This method is non-specific and often unreliable. For standard clinical estimation of bowel viability, reports have been made of accuracy in the range of 78% to 89% , but this typically includes resection of viable bowel and second-look procedures [5,6]. Patients may risk short gut syndrome if resection is performed too aggressively Techniques, such as anti-mesenteric Doppler interrogation and intravenous fluorescein dye, have been used experimentally. Due to the potential inaccuracy of the early evaluation of intestinal viability following ischemia-reperfusion injury, a second-look operation, 24–48 h after the first surgery, is often required [1,2]. A quick and accurate technique for intraoperative evaluation of intestinal viability could reduce the need for second-look operations and the time needed for evaluation
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
