Decellularized tissue is an important source for biological tissue engineering. Evaluation of the quality of decellularized tissue is performed using scanned images of hematoxylin-eosin stained (H&E) tissue sections and is usually dependent on the observer. The first step in creating a tool for the assessment of the quality of the liver scaffold without observer bias is the automatic segmentation of the whole slide image into three classes: the background, intralobular area, and extralobular area. Such segmentation enables to perform the texture analysis in the intralobular area of the liver scaffold, which is crucial part in the recellularization procedure. Existing semi-automatic methods for general segmentation (i.e., thresholding, watershed, etc.) do not meet the quality requirements. Moreover, there are no methods available to solve this task automatically. Given the low amount of training data, we proposed a two-stage method. The first stage is based on classification of simple hand-crafted descriptors of the pixels and their neighborhoods. This method is trained on partially annotated data. Its outputs are used for training of the second-stage approach, which is based on a convolutional neural network (CNN). Our architecture inspired by U-Net reaches very promising results, despite a very low amount of the training data. We provide qualitative and quantitative data for both stages. With the best training setup, we reach 90.70% recognition accuracy.

Biomedical Center Faculty of Medicine in Pilsen Charles University 323 00 Pilsen Czech Republic

Department of Surgery University Hospital and Faculty of Medicine in Pilsen Charles University 323 00 Pilsen Czech Republic

Experimental Transplantation Surgery Department Universitätsklinikum Jena 07743 Jena Germany

NTIS New Technologies for the Information Society Faculty of Applied Sciences University of West Bohemia 301 00 Pilsen Czech Republic

Zobrazit více v PubMed

Hussey G.S., Dziki J.L., Badylak S.F. Extracellular matrix-based materials for regenerative medicine. Nat. Rev. Mater. 2018;3:159–173. doi: 10.1038/s41578-018-0023-x. DOI

Porzionato A., Stocco E., Barbon S., Grandi F., Macchi V., De Caro R. Tissue-engineered grafts from human decellularized extracellular matrices: A systematic review and future perspectives. Int. J. Mol. Sci. 2018;19:4117. doi: 10.3390/ijms19124117. PubMed DOI PMC

Mazza G., Al-Akkad W., Rombouts K., Pinzani M. Liver tissue engineering: From implantable tissue to whole organ engineering. Hepatol. Commun. 2018;2:131–141. doi: 10.1002/hep4.1136. PubMed DOI PMC

Zhang Q., Johnson J.A., Dunne L.W., Chen Y., Iyyanki T., Wu Y., Chang E.I., Branch-Brooks C.D., Robb G.L., Butler C.E. Decellularized skin/adipose tissue flap matrix for engineering vascularized composite soft tissue flaps. Acta Biomater. 2016;35:166–184. doi: 10.1016/j.actbio.2016.02.017. PubMed DOI PMC

Atala A., Kurtis Kasper F., Mikos A.G. Engineering complex tissues. Sci. Transl. Med. 2012;4:1–11. doi: 10.1126/scitranslmed.3004890. PubMed DOI

Wuensch A., Baehr A., Bongoni A.K., Kemter E., Blutke A., Baars W., Haertle S., Zakhartchenko V., Kurome M., Kessler B., et al. Regulatory Sequences of the Porcine THBD Gene Facilitate Endothelial-Specific Expression of Bioactive Human Thrombomodulin in Single- and Multitransgenic Pigs. Transplantation. 2014;97:138–147. doi: 10.1097/TP.0b013e3182a95cbc. PubMed DOI

Poornejad N., Momtahan N., Salehi A.S., Scott D.R., Fronk C.A., Roeder B.L., Reynolds P.R., Bundy B.C., Cook A.D. Efficient decellularization of whole porcine kidneys improves reseeded cell behavior. Biomed. Mater. 2016;11:025003. doi: 10.1088/1748-6041/11/2/025003. PubMed DOI

Moulisová V., Jiřík M., Schindler C., Červenková L., Pálek R., Rosendorf J., Arlt J., Bolek L., Šůsová S., Nietzsche S., et al. Novel morphological multi-scale evaluation system for quality assessment of decellularized liver scaffolds. J. Tissue Eng. 2020;11 doi: 10.1177/2041731420921121. PubMed DOI PMC

Crapo P.M., Gilbert T.W., Badylak S.F. An overview of tissue and whole organ decellularization processes. Biomaterials. 2011;32:3233–3243. doi: 10.1016/j.biomaterials.2011.01.057. PubMed DOI PMC

Wang Y., Nicolas C.T., Chen H.S., Ross J.J., De Lorenzo S.B., Nyberg S.L. Recent Advances in Decellularization and Recellularization for Tissue-Engineered Liver Grafts. Cells Tissues Organs. 2017;204:125–136. doi: 10.1159/000479597. PubMed DOI

Amin A., Mahmoud-Ghoneim D. Texture analysis of liver fibrosis microscopic images: A study on the effect of biomarkers. Acta Biochim. Biophys. Sin. 2011;43:193–203. doi: 10.1093/abbs/gmq129. PubMed DOI

Haralick R.M. Statistical and structural approaches to texture. Proc. IEEE. 1979;67:786–804. doi: 10.1109/PROC.1979.11328. DOI

Kang H.K., Kim K.H., Ahn J.S., Kim H.B., Yi J.H., Kim H.S. A simple segmentation and quantification method for numerical quantitative analysis of cells and tissues. Technol. Health Care. 2020;28:S401–S410. doi: 10.3233/THC-209041. PubMed DOI PMC

LeCun Y., Boser B., Denker J.S., Henderson D., Howard R.E., Hubbard W., Jackel L.D. Backpropagation applied to handwritten zip code recognition. Neural Comput. 1989;1:541–551. doi: 10.1162/neco.1989.1.4.541. DOI

LeCun Y., Bottou L., Bengio Y., Haffner P. Gradient-Based Learning Applied to Document Recognition. Proc. IEEE. 1998;86:2278–2324. doi: 10.1109/5.726791. DOI

Vu Q.D., Graham S., Kurc T., To M.N.N., Shaban M., Qaiser T., Koohbanani N.A., Khurram S.A., Kalpathy-Cramer J., Zhao T., et al. Methods for segmentation and classification of digital microscopy tissue images. Front. Bioeng. Biotechnol. 2019;7:53. doi: 10.3389/fbioe.2019.00053. PubMed DOI PMC

John G.H., Langley P. Proceedings of the Eleventh Conference on Uncertainty in Artificial Intelligence. Morgan Kaufmann Publishers Inc.; San Francisco, CA, USA: 1995. Estimating Continuous Distributions in Bayesian Classifiers; pp. 338–345.

Blinchikoff H.J., Zverev A.I. Filtering in the Time and Frequency Domains. Wiley; New York, NY, USA: 1976. p. 12.

Duda R.O., Hart P.E. Pattern Classification and Scene Analysis. Volume 3 Wiley; New York, NY, USA: 1973.

Lee E.P., Lee E.P., Lozeille J., Soldán P., Daire S.E., Dyke J.M., Wright T.G. An empirical study of the naive Bayes classifier. Phys. Chem. Chem. Phys. 2001;3:4863–4869. doi: 10.1039/b104835j. DOI

Zhang H. Exploring conditions for the optimality of naïve bayes. Int. J. Pattern Recognit. Artif. Intell. 2005;19:183–198. doi: 10.1142/S0218001405003983. DOI

Pedregosa F., Varoquaux G., Gramfort A., Michel V., Thirion B., Grisel O., Blondel M., Prettenhofer P., Weiss R., Dubourg V., et al. Scikit-learn: Machine Learning in Python. J. Mach. Learn. Res. 2011;12:2825–2830.

Noh H., Hong S., Han B. Learning deconvolution network for semantic segmentation; Proceedings of the IEEE International Conference on Computer Vision; Santiago, Chile. 7–13 December 2015; pp. 1520–1528.

Ronneberger O., Fischer P., Brox T. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany, 5–9 October 2015. Springer; Cham, Switzerland: U-net: Convolutional networks for biomedical image segmentation; pp. 234–241.

Badrinarayanan V., Kendall A., Cipolla R. Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 2017;39:2481–2495. doi: 10.1109/TPAMI.2016.2644615. PubMed DOI

Bureš L., Gruber I., Neduchal P., Hlaváč M., Hrúz M. Semantic text segmentation from synthetic images of full-text documents. SPIIRAS Proc. 2019;18:1381–1406. doi: 10.15622/sp.2019.18.6.1381-1406. DOI

Tokui S., Oono K., Hido S., Clayton J. Chainer: A next-generation open source framework for deep learning; Proceedings of the Workshop on Machine Learning Systems (LearningSys) in the Twenty-Ninth Annual Conference on Neural Information Processing Systems (NIPS); Montreal, Canada. 11–12 December 2015; pp. 1–6.

Akiba T., Fukuda K., Suzuki S. ChainerMN: Scalable distributed deep learning framework. arXiv. 20171710.11351

Kingma D.P., Ba J. Adam: A method for stochastic optimization. arXiv. 20141412.6980

Maghsoudlou P., Georgiades F., Smith H., Milan A., Shangaris P., Urbani L., Loukogeorgakis S.P., Lombardi B., Mazza G., Hagen C., et al. Optimization of Liver Decellularization Maintains Extracellular Matrix Micro-Architecture and Composition Predisposing to Effective Cell Seeding. PLoS ONE. 2016;11:e0155324. doi: 10.1371/journal.pone.0155324. PubMed DOI PMC

Mirmalek-Sani S.H., Sullivan D.C., Zimmerman C., Shupe T.D., Petersen B.E. Immunogenicity of decellularized porcine liver for bioengineered hepatic tissue. Am. J. Pathol. 2013;183:558–565. doi: 10.1016/j.ajpath.2013.05.002. PubMed DOI PMC

Struecker B., Hillebrandt K.H., Voitl R., Butter A., Schmuck R.B., Reutzel-Selke A., Geisel D., Joehrens K., Pickerodt P.A., Raschzok N., et al. Porcine liver decellularization under oscillating pressure conditions: A technical refinement to improve the homogeneity of the decellularization process. Tissue Eng. Part C Methods. 2015;21:303–313. doi: 10.1089/ten.tec.2014.0321. PubMed DOI