Assessment of hepatic steatosis based on needle biopsy images from deceased donor livers.
artificial intelligence
liver graft biopsy
liver steatosis
liver transplantation
machine learning
macrovesicular steatosis
Journal
Clinical transplantation
ISSN: 1399-0012
Titre abrégé: Clin Transplant
Pays: Denmark
ID NLM: 8710240
Informations de publication
Date de publication:
03 2022
03 2022
Historique:
revised:
25
11
2021
received:
14
08
2021
accepted:
03
12
2021
pubmed:
11
12
2021
medline:
26
4
2022
entrez:
10
12
2021
Statut:
ppublish
Résumé
Assessment of hepatic steatosis (HS) before transplantation requires the pathologist to read a graft biopsy. A simple method based on the evaluation of images from tissue samples with a smartphone could expedite and facilitate the liver selection. This study aims to assess the degree of HS by analysing photographic images from liver needle biopsy samples. Thirty-three biopsy-images were acquired with a smartphone. Image processing was carried out using ImageJ: background subtraction, conversion to HSB colour space, segmentation of the biopsy area, and evaluation of statistical features of Hue, Saturation, Brightness, Red, Green, and Blue channels on the biopsy area. After feature extraction, correlations were made with gold standard HS percentage assessed at two levels (frozen-section vs glass-slide). Sensitivity, specificity, and accuracy were calculated for each feature. Correlations were found for H, S, R. The sensitivity, specificity, and accuracy of the final classifier based on the K* algorithm were 94%, 92%, 94%. Accuracy assessment was performed considering macrovesicular steatosis on specimens with mostly < 30% HS. The steatosis assessment based on needle biopsy images, proved to be an effective and promising method. Deep learning approaches could also be experimented with a larger set of images.
Sections du résumé
BACKGROUND
Assessment of hepatic steatosis (HS) before transplantation requires the pathologist to read a graft biopsy. A simple method based on the evaluation of images from tissue samples with a smartphone could expedite and facilitate the liver selection. This study aims to assess the degree of HS by analysing photographic images from liver needle biopsy samples.
METHODS
Thirty-three biopsy-images were acquired with a smartphone. Image processing was carried out using ImageJ: background subtraction, conversion to HSB colour space, segmentation of the biopsy area, and evaluation of statistical features of Hue, Saturation, Brightness, Red, Green, and Blue channels on the biopsy area. After feature extraction, correlations were made with gold standard HS percentage assessed at two levels (frozen-section vs glass-slide). Sensitivity, specificity, and accuracy were calculated for each feature.
RESULTS
Correlations were found for H, S, R. The sensitivity, specificity, and accuracy of the final classifier based on the K* algorithm were 94%, 92%, 94%.
LIMITATIONS
Accuracy assessment was performed considering macrovesicular steatosis on specimens with mostly < 30% HS.
CONCLUSIONS
The steatosis assessment based on needle biopsy images, proved to be an effective and promising method. Deep learning approaches could also be experimented with a larger set of images.
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
e14557Informations de copyright
© 2021 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.
Références
European Association for the Study of the Liver. Electronic address: EASL Clinical Practice Guidelines: Liver transplantation. J Hepatol. 2016;64(2):433-485.
Routh D, Sharma S, Naidu CS, Rao PP, Sharma AK, Ranjan P. Comparison of outcomes in ideal donor and extended criteria donor in deceased donor liver transplant: a prospective study. Int J Surg. 2014;12(8):774-7.
Dutkowski P, Schlegel A, Slankamenac K, Oberkofler CE, Adam R, Burroughs AK, et al. The use of fatty liver grafts in modern allocation systems: risk assessment by the balance of risk (BAR) score. Ann Surg. 2012;256:861-868, Discussion 8-9.
Croome KP, Mathur AK, Mao S, et al. Perioperative and long-term outcomes of utilizing donation after circulatory death liver grafts with macrosteatosis: A multicenter analysis. Am J Transplant. 2020;20(9):2449-2456.
Biesterfeld S, Knapp J, Bittinger F, Götte H, Schramm M, Otto G. Frozen section diagnosis in donor liver biopsies: observer variation of semiquantitative and quantitative steatosis assessment. Virchows Arch. 2012;461:177-183.
Schindelin J, Arganda-Carreras I, Frise E, et al. (2012), “Fiji: an open-source platform for biological-image analysis”. Nature methods 9(7): 676-682.
Sternberg. “Biomedical Image Processing”, IEEE Computer. 1983.
Andert A, Ulmer TF, Schöning W, et al. Grade of donor liver microvesicular steatosis does not affect the postoperative outcome after liver transplantation. Hepatobiliary Pancreat Dis Int. 2017 Dec 15;16(6):617-623.
Nocito A, El-Badry AM, Clavien P-A. When is steatosis too much for transplantation? J Hepatol. 2006;45(4):494-9.
Frank E, Hall MA, Witten IH (2016). The WEKA Workbench. Online Appendix for “Data Mining: Practical Machine Learning Tools and Techniques”, Morgan Kaufmann, Fourth Edition, 2016.
Cesaretti M, Brustia R, Goumard C, et al. Use of Artificial Intelligence as an Innovative Method for Liver Graft Macrosteatosis Assessment. Liver Transpl. 2020;26(10):1224-1232.
Weka 3: Machine Learning Software in Java. https://www.cs.waikato.ac.nz/ml/weka/.
[John GH, Langley P: Estimating Continuous Distributions in Bayesian Classifiers. In: Eleventh Conference on Uncertainty in Artificial Intelligence, San Mateo, 338-345, 1995.
Haykin S (1998). Neural Networks: A Comprehensive Foundation (2 ed.). Prentice Hall. ISBN 0-13-273350-1.
Cleary JG, Leonard E. Trigg: K*: An Instance-based Learner Using an Entropic Distance Measure. In: 12th International Conference on Machine Learning, 108-114, 1995.
Quinlan R (1993). C4.5: Programs for Machine Learning. Morgan Kaufmann Publishers, San Mateo, CA.
Breiman L (2001). Random Forests. Machine Learning. 45(1):5-32.
Marsman H, Matsushita T, Dierkhising R, Kremers W, Rosen C, Burgart L, Nyberg SL. Assessment of donor liver steatosis: pathologist or automated software? Hum Pathol. 2004;35(4):430-5.
Moccia S, Mattos LS, Patrini I, et al. Computer-assisted liver graft steatosis assessment via learning-based texture analysis. Int J Comput Assist Radiol Surg. 2018;13(9):1357-1367.