Automatic Liver Viability Scoring with Deep Learning and Hyperspectral Imaging

Diagnostics

Manuel Barberio¹  Didier Mutter²  Emanuele Felli²  Andrea Baiocchini³  Veronique Lindner⁴  Jordi Gracia-Sancho⁵  Eric Felli⁵  Cindy Vincent⁶  Catherine Schuster⁷  Bernard Geny⁸  Sylvain Gioux⁹  Michele Diana^1,10  Mahdi Al-Taher^1,10  Jacques Marescaux^1,10  Toby Collins^1,10  Richard Nkusi^1,10  Alexandre Hostettler^1,10  Giuseppe Maria Ettorre^1,11 

[1] Department of General Surgery, Cardinale Giovanni Panico Hospital, 73039 Tricase, Italy;Department of General, Digestive, and Endocrine Surgery, University Hospital of Strasbourg, 67000 Strasbourg, France;Department of Pathology, San Camillo Forlanini Hospital, 00152 Rome, Italy;Department of Pathology, University Hospital of Strasbourg, 67000 Strasbourg, France;Hepatology, Department of Biomedical Research, Inselspital, University of Bern, 3008 Bern, Switzerland;IHU-Strasbourg, Institute of Image-Guided Surgery, 67000 Strasbourg, France;INSERM, Institute of Viral and Liver Disease, U1110, 67000 Strasbourg, France;Institute of Physiology, EA3072 Mitochondria Respiration and Oxidative Stress, University of Strasbourg, 67000 Strasbourg, France;Photonics Instrumentation for Health, iCube Laboratory, University of Strasbourg, 67000 Strasbourg, France;Research Institute against Digestive Cancer (IRCAD), 67000 Strasbourg, France;San Camillo Forlanini Hospital, Department of Transplantation and General Surgery, 00152 Rome, Italy;

关键词: liver viability;    artificial intelligence;    deep learning;    convolutional networks;    CNNs;    hyperspectral imaging;   

DOI  :  10.3390/diagnostics11091527

来源: DOAJ

【 摘 要 】

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, p = 0.0320) and Suzuki’s score (r = −0.96, p = 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.

【 授权许可】

Unknown