Enhanced Artificial Intelligence Methods for Liver Steatosis Assessment Using Machine Learning and Color Image Processing: Liver Color Project.


Journal

Clinical transplantation
ISSN: 1399-0012
Titre abrégé: Clin Transplant
Pays: Denmark
ID NLM: 8710240

Informations de publication

Date de publication:
Oct 2024
Historique:
revised: 02 08 2024
received: 25 01 2024
accepted: 08 09 2024
medline: 9 10 2024
pubmed: 9 10 2024
entrez: 9 10 2024
Statut: ppublish

Résumé

The use of livers with significant steatosis is associated with worse transplantation outcomes. Brain death donor liver acceptance is mostly based on subjective surgeon assessment of liver appearance, since steatotic livers acquire a yellowish tone. The aim of this study was to develop a rapid, robust, accurate, and cost-effective method to assess liver steatosis. From June 1, 2018, to November 30, 2023, photographs and tru-cut needle biopsies were taken from adult brain death donor livers at a single university hospital for the study. All the liver photographs were taken by smartphones then color calibrated, segmented, and divided into patches. Color and texture features were then extracted and used as input, and the machine learning method was applied. This is a collaborative project between Vall d'Hebron University Hospital and Barcelona MedTech, Pompeu Fabra University, and is referred to as LiverColor. A total of 192 livers (362 photographs and 7240 patches) were included. When setting a macrosteatosis threshold of 30%, the best results were obtained using the random forest classifier, achieving an AUROC = 0.74, with 85% accuracy. Machine learning coupled with liver texture and color analysis of photographs taken with smartphones provides excellent accuracy for determining liver steatosis.

Sections du résumé

BACKGROUND BACKGROUND
The use of livers with significant steatosis is associated with worse transplantation outcomes. Brain death donor liver acceptance is mostly based on subjective surgeon assessment of liver appearance, since steatotic livers acquire a yellowish tone. The aim of this study was to develop a rapid, robust, accurate, and cost-effective method to assess liver steatosis.
METHODS METHODS
From June 1, 2018, to November 30, 2023, photographs and tru-cut needle biopsies were taken from adult brain death donor livers at a single university hospital for the study. All the liver photographs were taken by smartphones then color calibrated, segmented, and divided into patches. Color and texture features were then extracted and used as input, and the machine learning method was applied. This is a collaborative project between Vall d'Hebron University Hospital and Barcelona MedTech, Pompeu Fabra University, and is referred to as LiverColor.
RESULTS RESULTS
A total of 192 livers (362 photographs and 7240 patches) were included. When setting a macrosteatosis threshold of 30%, the best results were obtained using the random forest classifier, achieving an AUROC = 0.74, with 85% accuracy.
CONCLUSION CONCLUSIONS
Machine learning coupled with liver texture and color analysis of photographs taken with smartphones provides excellent accuracy for determining liver steatosis.

Identifiants

pubmed: 39382065
doi: 10.1111/ctr.15465
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

e15465

Subventions

Organisme : Fundación Mutua Madrileña
Organisme : Instituto de Salud Carlos III
Organisme : "La Caixa" Foundation
Organisme : European Union's Horizon 2020 research and innovation programme
ID : CI21-00064
Organisme : UPF INNOValora programme

Informations de copyright

© 2024 The Author(s). Clinical Transplantation published by Wiley Periodicals LLC.

Références

ONT. No Title. Doss la Organ Nac Traspl. (2023)., http://www.ont.es/links/Paginas/Publicaciones.aspx.
A. W. C. Kow, “Hepatic Metastasis From Colorectal Cancer,” Journal of Gastrointestinal Oncology 10, no. 6 (2019): 1274–1298.
M. Hagness, A. Foss, T. S. Egge, and S. Dueland, “Patterns of Recurrence After Liver Transplantation for Nonresectable Liver Metastases From Colorectal Cancer,” Annals of Surgical Oncology 21, no. 4 (2014): 1323–1329.
M. Hagness, A. Foss, P.‐D. Line, et al., “Liver Transplantation for Nonresectable Liver Metastases From Colorectal Cancer,” Annals of Surgery 257, no. 5 (2013): 800–806.
S. Dueland, T. Syversveen, J. M. Solheim, et al., “Survival Following Liver Transplantation for Patients With Nonresectable Liver‐Only Colorectal Metastases,” Annals of Surgery 271, no. 2 (2020): 212–218.
C. D. Williams, J. Stengel, M. I. Asike, et al., “Prevalence of Nonalcoholic Fatty Liver Disease and Nonalcoholic Steatohepatitis Among a Largely Middle‐Aged Population Utilizing Ultrasound and Liver Biopsy: A Prospective Study,” Gastroenterology 140, no. 1 (2011): 124–131.
N. Chalasani, Z. Younossi, J. E. Lavine, et al., “The Diagnosis and Management of Non‐Alcoholic Fatty Liver Disease: Practice Guideline by the American Gastroenterological Association, American Association for the Study of Liver Diseases, and American College of Gastroenterology,” Gastroenterology 142, no. 7 (2012): 1592–1609.
H. M. Noujaim, J. de Ville de Goyet, E. F. S. Montero, et al., “Expanding Postmortem Donor Pool Using Steatotic Liver Grafts: A New Look,” Transplantation 87, no. 6 (2009): 919–925.
S. Todo, A. J. Demetris, L. Makowka, et al., “Primary Nonfunction of Hepatic Allografts With Preexisting Fatty Infiltration,” Transplantation 47, no. 5 (1989): 903–905.
S. Moosburner, J. Gassner, M. Nösser, et al., “Prevalence of Steatosis Hepatis in the Eurotransplant Region: Impact on Graft Acceptance Rates,” HPB Surgery 2018 (2018): 1–9.
P. Dutkowski, A. Schlegel, K. Slankamenac, et al., “The Use of Fatty Liver Grafts in Modern Allocation Systems,” Annals of Surgery 256, no. 5 (2012): 861–869.
J. M. Kim, S. Y. Ha, J.‐W. Joh, et al., “Predicting Hepatic Steatosis in Living Liver Donors via Noninvasive Methods,” Medicine 95, no. 7 (2016): e2718.
G.‐W. Song and S.‐G. Lee, “Living Donor Liver Transplantation,” Current Opinions in Organ Transplantation 19, no. 3 (2014): 217–222.
H. Yersiz, C. Lee, F. M. Kaldas, et al., “Assessment of Hepatic Steatosis by Transplant Surgeon and Expert Pathologist: A Prospective, Double‐Blind Evaluation of 201 Donor Livers,” Liver Transplantation 19, no. 4 (2013): 437–449.
R. G. Rodriguez, J. Vazquez‐Corral, and M. Bertalmio, “Color Matching Images With Unknown Non‐Linear Encodings,” IEEE Transactions on Image Processing 29 (2020): 4435–4444.
J. Vazquez‐Corral and M. Bertalmío, “Color Stabilization Along Time and Across Shots of the Same Scene, for One or Several Cameras of Unknown Specifications,” IEEE Transactions on Image Processing 23, no. 10 (2014): 4564–4575.
P. Bedossa and T. Poynard, “An Algorithm for the Grading of Activity in Chronic Hepatitis C. The METAVIR Cooperative Study Group,” Hepatology 24, no. 2 (1996): 289–293.
E. M. Brunt, C. G. Janney, A. M. Di Bisceglie, B. A. Neuschwander‐Tetri, and B. R. Bacon, “Nonalcoholic Steatohepatitis: A Proposal for Grading and Staging the Histological Lesions,” American Journal of Gastroenterology 94, no. 9 (1999): 2467–2474.
V. N. Vapnik, The Nature of Statistical Learning Theory (New York, NY: Springer New York, 2000).
L. Breiman, “Random Forests,” Machine Learning 45, no. 1 (2001): 5–32.
K. P. Croome, D. D. Lee, S. Croome, et al., “The Impact of Postreperfusion Syndrome During Liver Transplantation Using Livers With Significant Macrosteatosis,” American Journal of Transplantation 19, no. 9 (2019): 2550–2559.
T. M. Fishbein, M. I. Fiel, S. Emre, et al., “Use of Livers With Microvesicular Fat Safely Expands the Donor Pool,” Transplantation 64, no. 2 (1997): 248–251.
K. P. Croome, D. D. Lee, S. Croome, et al., “Does Donor Allograft Microsteatosis Matter? Comparison of Outcomes in Liver Transplantation With a Propensity‐Matched Cohort,” Liver Transplantation 25, no. 10 (2019): 1533–1540.
A. L. Spitzer, O. B. Lao, A. A. S. Dick, et al., “The Biopsied Donor Liver: Incorporating Macrosteatosis Into High‐Risk Donor Assessment,” Liver Transplantation 16, no. 7 (2010): 874–884.
V. J. Lozanovski, E. Khajeh, H. Fonouni, et al., “The Impact of Major Extended Donor Criteria on Graft Failure and Patient Mortality After Liver Transplantation,” Langenbeck's Archives of Surgery 403, no. 6 (2018): 719–731.
R. Adam, M. Reynes, M. Johann, et al., “The Outcome of Steatotic Grafts in Liver Transplantation,” Transplantation Proceedings 23 (1991): 1538–1540. Pt 2.
Spanish National Transplant Organization. Annual Reports. ONT., http://www.ont.es/infesp/Paginas/Memorias.aspx.
M. Cesaretti, N. Poté, F. Cauchy, et al., “Noninvasive Assessment of Liver Steatosis in Deceased Donors: A Pilot Study,” Liver Transplantation 24, no. 4 (2018): 551–556.
N. Golse, C. Cosse, M.‐A. Allard, et al., “Evaluation of a Micro‐Spectrometer for the Real‐Time Assessment of Liver Graft With Mild‐to‐Moderate Macrosteatosis: A Proof of Concept Study,” Journal of Hepatology 70, no. 3 (2019): 423–430.
A. Lawal, S. Florman, M. I. Fiel, R. Gordon, J. Bromberg, and T. D. Schiano, “Identification of Ultrastructural Changes in Liver Allografts of Patients Experiencing Primary Nonfunction,” Transplantation Proceedings 37 (2005): 4339–4342.
A. Spann, A. Yasodhara, J. Kang, et al., “Applying Machine Learning in Liver Disease and Transplantation: A Comprehensive Review,” Hepatology 71, no. 3 (2020): 1093–1105.
M. D. Ayllón, R. Ciria, M. Cruz‐Ramírez, et al., “Validation of Artificial Neural Networks as a Methodology for Donor‐Recipient Matching for Liver Transplantation,” Liver Transplantation 24, no. 2 (2018): 192–203.
V. Cherchi, M. V. Della, G. Terrosu, et al., “Assessment of Hepatic Steatosis Based on Needle Biopsy Images From Deceased Donor Livers,” Clinical Transplantation (2021).
M. Cesaretti, R. Brustia, C. Goumard, et al., “Use of Artificial Intelligence as an Innovative Method for Liver Graft Macrosteatosis Assessment,” Liver Transplantation 26, no. 10 (2020): 1224–1232.
M. Rodríguez‐Perálvarez, M. A. Gómez‐Bravo, G. Sánchez‐Antolín, et al., “Expanding Indications of Liver Transplantation in Spain: Consensus Statement and Recommendations by the Spanish Society of Liver Transplantation,” Transplantation 105, no. 3 (2021): 602–607.
M. Ivanics, D. Wallace, M. Claasen, et al., “Low Utilization of Adult‐to‐Adult LDLT in Western Countries Despite Excellent Outcomes: International Multicenter Analysis of the US, the UK, and Canada,” Journal of Hepatology 77, no. 6 (2022): 1607–1618.
M. Rodríguez‐Perálvarez, M. A. Gómez‐Bravo, G. Sánchez‐Antolín, et al., “Expanding Indications of Liver Transplantation in Spain: Consensus Statement and Recommendations by the Spanish Society of Liver Transplantation,” Transplantation 105, no. 3 (2021): 602–607.
A. Webb, E. Lester, A. M. J. Shapiro, D. Eurich, and D. L. Bigam, “Cost‐Utility Analysis of Normothermic Machine Perfusion Compared to Static Cold Storage in Liver Transplantation in the Canadian Setting,” American Journal of Transplantation 22, no. 2 (2022): 541–551.

Auteurs

Concepción Gómez-Gavara (C)

Barcelona Autonoma University, Universitat Autónoma de Barcelona, Barcelona, Spain.
Servicio de Cirugía HBP y Trasplante, Hospital Universitari Vall d´Hebron, Vall d´Hebron Institute of Research (VHIR), Barcelona, Spain.

Itxarone Bilbao (I)

Barcelona Autonoma University, Universitat Autónoma de Barcelona, Barcelona, Spain.
Servicio de Cirugía HBP y Trasplante, Hospital Universitari Vall d´Hebron, Vall d´Hebron Institute of Research (VHIR), Barcelona, Spain.

Gemma Piella (G)

Barcelona MedTech, Universidad Pompeu Fabra, Barcelona, Spain.

Javier Vazquez-Corral (J)

Computer Vision Center and Computer Sciences Department, Universitat Autònoma de Barcelona, Barcelona, Spain.

Berta Benet-Cugat (B)

Barcelona MedTech, Universidad Pompeu Fabra, Barcelona, Spain.

Elizabeth Pando (E)

Barcelona Autonoma University, Universitat Autónoma de Barcelona, Barcelona, Spain.
Servicio de Cirugía HBP y Trasplante, Hospital Universitari Vall d´Hebron, Vall d´Hebron Institute of Research (VHIR), Barcelona, Spain.

José Andrés Molino (JA)

Servicio de Cirugía Pediátrica, Hospital Universitari Vall d´Hebron, Barcelona, Spain.

María Teresa Salcedo (MT)

Servicio de Anatomía Patológica, Hospital Universitari Vall d´Hebron, Barcelona, Spain.

Mar Dalmau (M)

Barcelona Autonoma University, Universitat Autónoma de Barcelona, Barcelona, Spain.
Servicio de Cirugía HBP y Trasplante, Hospital Universitari Vall d´Hebron, Vall d´Hebron Institute of Research (VHIR), Barcelona, Spain.

Laura Vidal (L)

Barcelona Autonoma University, Universitat Autónoma de Barcelona, Barcelona, Spain.
Servicio de Cirugía HBP y Trasplante, Hospital Universitari Vall d´Hebron, Vall d´Hebron Institute of Research (VHIR), Barcelona, Spain.

Daniel Esono (D)

Barcelona MedTech, Universidad Pompeu Fabra, Barcelona, Spain.

Miguel Ángel Cordobés (MÁ)

Barcelona MedTech, Universidad Pompeu Fabra, Barcelona, Spain.

Ángela Bilbao (Á)

Barcelona Autonoma University, Universitat Autónoma de Barcelona, Barcelona, Spain.

Josa Prats (J)

Barcelona MedTech, Universidad Pompeu Fabra, Barcelona, Spain.

Mar Moya (M)

Barcelona MedTech, Universidad Pompeu Fabra, Barcelona, Spain.

Cristina Dopazo (C)

Barcelona Autonoma University, Universitat Autónoma de Barcelona, Barcelona, Spain.
Servicio de Cirugía HBP y Trasplante, Hospital Universitari Vall d´Hebron, Vall d´Hebron Institute of Research (VHIR), Barcelona, Spain.

Christopher Mazo (C)

Coordinación de Trasplantes, Hospital Universitari Vall d´Hebron, Barcelona, Spain.

Mireia Caralt (M)

Servicio de Cirugía HBP y Trasplante, Hospital Universitari Vall d´Hebron, Vall d´Hebron Institute of Research (VHIR), Barcelona, Spain.

Ernest Hidalgo (E)

Servicio de Cirugía HBP y Trasplante, Hospital Universitari Vall d´Hebron, Vall d´Hebron Institute of Research (VHIR), Barcelona, Spain.

Ramon Charco (R)

Servicio de Cirugía HBP y Trasplante, Hospital Universitari Vall d´Hebron, Vall d´Hebron Institute of Research (VHIR), Barcelona, Spain.

Articles similaires

[Redispensing of expensive oral anticancer medicines: a practical application].

Lisanne N van Merendonk, Kübra Akgöl, Bastiaan Nuijen
1.00
Humans Antineoplastic Agents Administration, Oral Drug Costs Counterfeit Drugs

Smoking Cessation and Incident Cardiovascular Disease.

Jun Hwan Cho, Seung Yong Shin, Hoseob Kim et al.
1.00
Humans Male Smoking Cessation Cardiovascular Diseases Female
Humans United States Aged Cross-Sectional Studies Medicare Part C
1.00
Humans Yoga Low Back Pain Female Male

Classifications MeSH