TY - JOUR
T1 - Enhanced Artificial Intelligence Methods for Liver Steatosis Assessment Using Machine Learning and Color Image Processing
T2 - Liver Color Project
AU - Gómez-Gavara, Concepción
AU - Bilbao, Itxarone
AU - Piella, Gemma
AU - Vazquez-Corral, Javier
AU - Benet-Cugat, Berta
AU - Pando, Elizabeth
AU - Molino, José Andrés
AU - Salcedo, María Teresa
AU - Dalmau, Mar
AU - Vidal, Laura
AU - Esono, Daniel
AU - Cordobés, Miguel Ángel
AU - Bilbao, Ángela
AU - Prats, Josa
AU - Moya, Mar
AU - Dopazo, Cristina
AU - Mazo, Christopher
AU - Caralt, Mireia
AU - Hidalgo, Ernest
AU - Charco, Ramon
N1 - Publisher Copyright:
© 2024 The Author(s). Clinical Transplantation published by Wiley Periodicals LLC.
PY - 2024/10/9
Y1 - 2024/10/9
N2 - 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: 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: 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: Machine learning coupled with liver texture and color analysis of photographs taken with smartphones provides excellent accuracy for determining liver steatosis.
AB - 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: 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: 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: Machine learning coupled with liver texture and color analysis of photographs taken with smartphones provides excellent accuracy for determining liver steatosis.
KW - Adult
KW - Artificial Intelligence
KW - Color
KW - Fatty Liver/pathology
KW - Female
KW - Follow-Up Studies
KW - Humans
KW - Image Processing, Computer-Assisted/methods
KW - Liver Transplantation
KW - Liver/pathology
KW - Machine Learning
KW - Male
KW - Middle Aged
KW - Prognosis
KW - Tissue Donors/supply & distribution
KW - Transplantation
KW - Metastases
KW - Allografts
KW - Grafts
UR - http://www.scopus.com/inward/record.url?scp=85206055848&partnerID=8YFLogxK
UR - https://www.mendeley.com/catalogue/8893253f-d830-3b77-a498-74a9d7e1ea23/
UR - https://portalrecerca.uab.cat/en/publications/212ae0b0-42f3-4e3a-aeb9-ed9b09c502ef
U2 - 10.1111/ctr.15465
DO - 10.1111/ctr.15465
M3 - Article
C2 - 39382065
AN - SCOPUS:85206055848
SN - 0902-0063
VL - 38
JO - Clinical Transplantation
JF - Clinical Transplantation
IS - 10
M1 - e15465
ER -