Cargando…

Automatic Prediction of Ischemia-Reperfusion Injury of Small Intestine Using Convolutional Neural Networks: A Pilot Study

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 viabilit...

Descripción completa

Detalles Bibliográficos
Autores principales: Hou, Jie, Strand-Amundsen, Runar, Tronstad, Christian, Høgetveit, Jan Olav, Martinsen, Ørjan Grøttem, Tønnessen, Tor Inge
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8512235/
https://www.ncbi.nlm.nih.gov/pubmed/34641009
http://dx.doi.org/10.3390/s21196691
_version_ 1784582942505304064
author Hou, Jie
Strand-Amundsen, Runar
Tronstad, Christian
Høgetveit, Jan Olav
Martinsen, Ørjan Grøttem
Tønnessen, Tor Inge
author_facet Hou, Jie
Strand-Amundsen, Runar
Tronstad, Christian
Høgetveit, Jan Olav
Martinsen, Ørjan Grøttem
Tønnessen, Tor Inge
author_sort Hou, Jie
collection PubMed
description 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.
format Online
Article
Text
id pubmed-8512235
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-85122352021-10-14 Automatic Prediction of Ischemia-Reperfusion Injury of Small Intestine Using Convolutional Neural Networks: A Pilot Study Hou, Jie Strand-Amundsen, Runar Tronstad, Christian Høgetveit, Jan Olav Martinsen, Ørjan Grøttem Tønnessen, Tor Inge Sensors (Basel) Article 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. MDPI 2021-10-08 /pmc/articles/PMC8512235/ /pubmed/34641009 http://dx.doi.org/10.3390/s21196691 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Hou, Jie
Strand-Amundsen, Runar
Tronstad, Christian
Høgetveit, Jan Olav
Martinsen, Ørjan Grøttem
Tønnessen, Tor Inge
Automatic Prediction of Ischemia-Reperfusion Injury of Small Intestine Using Convolutional Neural Networks: A Pilot Study
title Automatic Prediction of Ischemia-Reperfusion Injury of Small Intestine Using Convolutional Neural Networks: A Pilot Study
title_full Automatic Prediction of Ischemia-Reperfusion Injury of Small Intestine Using Convolutional Neural Networks: A Pilot Study
title_fullStr Automatic Prediction of Ischemia-Reperfusion Injury of Small Intestine Using Convolutional Neural Networks: A Pilot Study
title_full_unstemmed Automatic Prediction of Ischemia-Reperfusion Injury of Small Intestine Using Convolutional Neural Networks: A Pilot Study
title_short Automatic Prediction of Ischemia-Reperfusion Injury of Small Intestine Using Convolutional Neural Networks: A Pilot Study
title_sort automatic prediction of ischemia-reperfusion injury of small intestine using convolutional neural networks: a pilot study
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8512235/
https://www.ncbi.nlm.nih.gov/pubmed/34641009
http://dx.doi.org/10.3390/s21196691
work_keys_str_mv AT houjie automaticpredictionofischemiareperfusioninjuryofsmallintestineusingconvolutionalneuralnetworksapilotstudy
AT strandamundsenrunar automaticpredictionofischemiareperfusioninjuryofsmallintestineusingconvolutionalneuralnetworksapilotstudy
AT tronstadchristian automaticpredictionofischemiareperfusioninjuryofsmallintestineusingconvolutionalneuralnetworksapilotstudy
AT høgetveitjanolav automaticpredictionofischemiareperfusioninjuryofsmallintestineusingconvolutionalneuralnetworksapilotstudy
AT martinsenørjangrøttem automaticpredictionofischemiareperfusioninjuryofsmallintestineusingconvolutionalneuralnetworksapilotstudy
AT tønnessentoringe automaticpredictionofischemiareperfusioninjuryofsmallintestineusingconvolutionalneuralnetworksapilotstudy