Worldwide implementation of liver-graft pool using marginal livers (such as grafts which carry a high risk of technical complications and impaired function, or a risk of transmitting infection or malignancy to the recipient) has led to a growing interest in developing methods for accurate evaluation of graft quality. Liver steatosis is associated with a higher risk of primary nonfunction (PNF), early graft dysfunction (EAD), poor graft survival rate. The present study aimed to analyze the value of artificial intelligence (AI) in the assessment of liver steatosis during procurement compared to liver biopsy evaluation. One hundred and seventeen consecutive brain-deceased donors' liver grafts were included and classified in 2 cohorts: > vs < 30% hepatic steatosis. AI analysis required the presence of an intraoperative smartphone liver picture, as well as a graft biopsy and donor's data. Firstly, a new algorithm, arising from current visual recognition methods was developed, trained and validated to obtain automatic liver-graft segmentation from smartphone images. Secondly, a fully automated texture analysis and classification of the liver graft was performed by machine learning algorithms. Automatic liver-graft segmentation from smartphone images achieved an accuracy of 98% while the analysis of the liver graft features (cropped picture and donor's data) showed an accuracy of 89% in graft classification (> vs < 30%). This study demonstrates that AI has the potential to assess steatosis in a handy and non-invasive way to reliably identify potential non-transplantable liver grafts and avoid improper grafts utilization.
Use of artificial intelligence as innovative method for liver graft macrosteatosis assessment / Cesaretti, M; Brustia, R; Goumard, C; Cauchy, F; Poté, N; Dondero, F; Paugam-Burtz, C; Durand, F; Paradis, V; Diaspro, A; Mattos, L; Scatton, O; Soubrane, O; Moccia, S. - In: LIVER TRANSPLANTATION. - ISSN 1527-6465. - (2020). [10.1002/lt.25801]
Use of artificial intelligence as innovative method for liver graft macrosteatosis assessment
Moccia, S
2020-01-01
Abstract
Worldwide implementation of liver-graft pool using marginal livers (such as grafts which carry a high risk of technical complications and impaired function, or a risk of transmitting infection or malignancy to the recipient) has led to a growing interest in developing methods for accurate evaluation of graft quality. Liver steatosis is associated with a higher risk of primary nonfunction (PNF), early graft dysfunction (EAD), poor graft survival rate. The present study aimed to analyze the value of artificial intelligence (AI) in the assessment of liver steatosis during procurement compared to liver biopsy evaluation. One hundred and seventeen consecutive brain-deceased donors' liver grafts were included and classified in 2 cohorts: > vs < 30% hepatic steatosis. AI analysis required the presence of an intraoperative smartphone liver picture, as well as a graft biopsy and donor's data. Firstly, a new algorithm, arising from current visual recognition methods was developed, trained and validated to obtain automatic liver-graft segmentation from smartphone images. Secondly, a fully automated texture analysis and classification of the liver graft was performed by machine learning algorithms. Automatic liver-graft segmentation from smartphone images achieved an accuracy of 98% while the analysis of the liver graft features (cropped picture and donor's data) showed an accuracy of 89% in graft classification (> vs < 30%). This study demonstrates that AI has the potential to assess steatosis in a handy and non-invasive way to reliably identify potential non-transplantable liver grafts and avoid improper grafts utilization.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.