Automatic Liver Viability Scoring with Deep Learning and Hyperspectral Imaging
Hyperspectral imaging (HSI) is a non-invasive imaging modality already applied to evaluate hepatic oxygenation and to discriminate different models of hepatic ischemia. Nevertheless, the ability of HSI to detect and predict the reperfusion damage intraoperatively was not yet assessed. Hypoxia caused...
Main Authors: | , , , , , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-08-01
|
Series: | Diagnostics |
Subjects: | |
Online Access: | https://www.mdpi.com/2075-4418/11/9/1527 |
id |
doaj-cbaef29cc9d84f9c9316f1f1e57e4be9 |
---|---|
record_format |
Article |
spelling |
doaj-cbaef29cc9d84f9c9316f1f1e57e4be92021-09-25T23:58:42ZengMDPI AGDiagnostics2075-44182021-08-01111527152710.3390/diagnostics11091527Automatic Liver Viability Scoring with Deep Learning and Hyperspectral ImagingEric Felli0Mahdi Al-Taher1Toby Collins2Richard Nkusi3Emanuele Felli4Andrea Baiocchini5Veronique Lindner6Cindy Vincent7Manuel Barberio8Bernard Geny9Giuseppe Maria Ettorre10Alexandre Hostettler11Didier Mutter12Sylvain Gioux13Catherine Schuster14Jacques Marescaux15Jordi Gracia-Sancho16Michele Diana17Hepatology, Department of Biomedical Research, Inselspital, University of Bern, 3008 Bern, SwitzerlandResearch Institute against Digestive Cancer (IRCAD), 67000 Strasbourg, FranceResearch Institute against Digestive Cancer (IRCAD), 67000 Strasbourg, FranceResearch Institute against Digestive Cancer (IRCAD), 67000 Strasbourg, FranceDepartment of General, Digestive, and Endocrine Surgery, University Hospital of Strasbourg, 67000 Strasbourg, FranceDepartment of Pathology, San Camillo Forlanini Hospital, 00152 Rome, ItalyDepartment of Pathology, University Hospital of Strasbourg, 67000 Strasbourg, FranceIHU-Strasbourg, Institute of Image-Guided Surgery, 67000 Strasbourg, FranceDepartment of General Surgery, Cardinale Giovanni Panico Hospital, 73039 Tricase, ItalyInstitute of Physiology, EA3072 Mitochondria Respiration and Oxidative Stress, University of Strasbourg, 67000 Strasbourg, FranceSan Camillo Forlanini Hospital, Department of Transplantation and General Surgery, 00152 Rome, ItalyResearch Institute against Digestive Cancer (IRCAD), 67000 Strasbourg, FranceDepartment of General, Digestive, and Endocrine Surgery, University Hospital of Strasbourg, 67000 Strasbourg, FrancePhotonics Instrumentation for Health, iCube Laboratory, University of Strasbourg, 67000 Strasbourg, FranceINSERM, Institute of Viral and Liver Disease, U1110, 67000 Strasbourg, FranceResearch Institute against Digestive Cancer (IRCAD), 67000 Strasbourg, FranceHepatology, Department of Biomedical Research, Inselspital, University of Bern, 3008 Bern, SwitzerlandResearch Institute against Digestive Cancer (IRCAD), 67000 Strasbourg, FranceHyperspectral imaging (HSI) is a non-invasive imaging modality already applied to evaluate hepatic oxygenation and to discriminate different models of hepatic ischemia. Nevertheless, the ability of HSI to detect and predict the reperfusion damage intraoperatively was not yet assessed. Hypoxia caused by hepatic artery occlusion (HAO) in the liver brings about dreadful vascular complications known as ischemia-reperfusion injury (IRI). Here, we show the evaluation of liver viability in an HAO model with an artificial intelligence-based analysis of HSI. We have combined the potential of HSI to extract quantitative optical tissue properties with a deep learning-based model using convolutional neural networks. The artificial intelligence (AI) score of liver viability showed a significant correlation with capillary lactate from the liver surface (r = −0.78, <i>p</i> = 0.0320) and Suzuki’s score (r = −0.96, <i>p</i> = 0.0012). CD31 immunostaining confirmed the microvascular damage accordingly with the AI score. Our results ultimately show the potential of an HSI-AI-based analysis to predict liver viability, thereby prompting for intraoperative tool development to explore its application in a clinical setting.https://www.mdpi.com/2075-4418/11/9/1527liver viabilityartificial intelligencedeep learningconvolutional networksCNNshyperspectral imaging |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Eric Felli Mahdi Al-Taher Toby Collins Richard Nkusi Emanuele Felli Andrea Baiocchini Veronique Lindner Cindy Vincent Manuel Barberio Bernard Geny Giuseppe Maria Ettorre Alexandre Hostettler Didier Mutter Sylvain Gioux Catherine Schuster Jacques Marescaux Jordi Gracia-Sancho Michele Diana |
spellingShingle |
Eric Felli Mahdi Al-Taher Toby Collins Richard Nkusi Emanuele Felli Andrea Baiocchini Veronique Lindner Cindy Vincent Manuel Barberio Bernard Geny Giuseppe Maria Ettorre Alexandre Hostettler Didier Mutter Sylvain Gioux Catherine Schuster Jacques Marescaux Jordi Gracia-Sancho Michele Diana Automatic Liver Viability Scoring with Deep Learning and Hyperspectral Imaging Diagnostics liver viability artificial intelligence deep learning convolutional networks CNNs hyperspectral imaging |
author_facet |
Eric Felli Mahdi Al-Taher Toby Collins Richard Nkusi Emanuele Felli Andrea Baiocchini Veronique Lindner Cindy Vincent Manuel Barberio Bernard Geny Giuseppe Maria Ettorre Alexandre Hostettler Didier Mutter Sylvain Gioux Catherine Schuster Jacques Marescaux Jordi Gracia-Sancho Michele Diana |
author_sort |
Eric Felli |
title |
Automatic Liver Viability Scoring with Deep Learning and Hyperspectral Imaging |
title_short |
Automatic Liver Viability Scoring with Deep Learning and Hyperspectral Imaging |
title_full |
Automatic Liver Viability Scoring with Deep Learning and Hyperspectral Imaging |
title_fullStr |
Automatic Liver Viability Scoring with Deep Learning and Hyperspectral Imaging |
title_full_unstemmed |
Automatic Liver Viability Scoring with Deep Learning and Hyperspectral Imaging |
title_sort |
automatic liver viability scoring with deep learning and hyperspectral imaging |
publisher |
MDPI AG |
series |
Diagnostics |
issn |
2075-4418 |
publishDate |
2021-08-01 |
description |
Hyperspectral imaging (HSI) is a non-invasive imaging modality already applied to evaluate hepatic oxygenation and to discriminate different models of hepatic ischemia. Nevertheless, the ability of HSI to detect and predict the reperfusion damage intraoperatively was not yet assessed. Hypoxia caused by hepatic artery occlusion (HAO) in the liver brings about dreadful vascular complications known as ischemia-reperfusion injury (IRI). Here, we show the evaluation of liver viability in an HAO model with an artificial intelligence-based analysis of HSI. We have combined the potential of HSI to extract quantitative optical tissue properties with a deep learning-based model using convolutional neural networks. The artificial intelligence (AI) score of liver viability showed a significant correlation with capillary lactate from the liver surface (r = −0.78, <i>p</i> = 0.0320) and Suzuki’s score (r = −0.96, <i>p</i> = 0.0012). CD31 immunostaining confirmed the microvascular damage accordingly with the AI score. Our results ultimately show the potential of an HSI-AI-based analysis to predict liver viability, thereby prompting for intraoperative tool development to explore its application in a clinical setting. |
topic |
liver viability artificial intelligence deep learning convolutional networks CNNs hyperspectral imaging |
url |
https://www.mdpi.com/2075-4418/11/9/1527 |
work_keys_str_mv |
AT ericfelli automaticliverviabilityscoringwithdeeplearningandhyperspectralimaging AT mahdialtaher automaticliverviabilityscoringwithdeeplearningandhyperspectralimaging AT tobycollins automaticliverviabilityscoringwithdeeplearningandhyperspectralimaging AT richardnkusi automaticliverviabilityscoringwithdeeplearningandhyperspectralimaging AT emanuelefelli automaticliverviabilityscoringwithdeeplearningandhyperspectralimaging AT andreabaiocchini automaticliverviabilityscoringwithdeeplearningandhyperspectralimaging AT veroniquelindner automaticliverviabilityscoringwithdeeplearningandhyperspectralimaging AT cindyvincent automaticliverviabilityscoringwithdeeplearningandhyperspectralimaging AT manuelbarberio automaticliverviabilityscoringwithdeeplearningandhyperspectralimaging AT bernardgeny automaticliverviabilityscoringwithdeeplearningandhyperspectralimaging AT giuseppemariaettorre automaticliverviabilityscoringwithdeeplearningandhyperspectralimaging AT alexandrehostettler automaticliverviabilityscoringwithdeeplearningandhyperspectralimaging AT didiermutter automaticliverviabilityscoringwithdeeplearningandhyperspectralimaging AT sylvaingioux automaticliverviabilityscoringwithdeeplearningandhyperspectralimaging AT catherineschuster automaticliverviabilityscoringwithdeeplearningandhyperspectralimaging AT jacquesmarescaux automaticliverviabilityscoringwithdeeplearningandhyperspectralimaging AT jordigraciasancho automaticliverviabilityscoringwithdeeplearningandhyperspectralimaging AT michelediana automaticliverviabilityscoringwithdeeplearningandhyperspectralimaging |
_version_ |
1717367416351096832 |