Semantic Segmentation of Intralobular and Extralobular Tissue from Liver Scaffold H&E Images

Show simple item record
dc.contributor.authorJiřík, Miroslav
dc.contributor.authorGruber, Ivan
dc.contributor.authorMoulisová, Vladimíra
dc.contributor.authorSchindler, Claudia
dc.contributor.authorČervenková, Lenka
dc.contributor.authorPálek, Richard
dc.contributor.authorRosendorf, Jáchym
dc.contributor.authorArlt, Janine
dc.contributor.authorBolek, Lukáš
dc.contributor.authorDejmek, Jiří
dc.contributor.authorDahmen, Uta
dc.contributor.authorŽelezný, Miloš
dc.contributor.authorLiška, Václav
dc.date.accessioned2021-03-01T11:00:27Z
dc.date.available2021-03-01T11:00:27Z
dc.date.issued2020
dc.description.abstract-translatedDecellularized 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.en
dc.format12 s.cs
dc.format.mimetypeapplication/pdf
dc.identifier.citationJIŘÍK, M., GRUBER, I., MOULISOVÁ, V., SCHINDLER, C., ČERVENKOVÁ, L., PÁLEK, R., ROSENDORF, J., ARLT, J., BOLEK, L., DEJMEK, J., DAHMEN, U., ŽELEZNÝ, M., LIŠKA, V. Semantic Segmentation of Intralobular and Extralobular Tissue from Liver Scaffold H&E Images. Sensors, 2020, roč. 20, č. 24. ISS: 1424-8220.cs
dc.identifier.document-number603179000001
dc.identifier.doi10.3390/s20247063
dc.identifier.issn1424-8220
dc.identifier.obd43931735
dc.identifier.uri2-s2.0-85097520340
dc.identifier.urihttp://hdl.handle.net/11025/42780
dc.language.isoenen
dc.project.IDLTARF18017/AMIR - Multimodální rozhraní založené na gestech a mluvené i znakové řeči pro ovládání asistivního mobilního informačního robotacs
dc.project.IDLO1506/PUNTIS - Podpora udržitelnosti centra NTIS - Nové technologie pro informační společnostcs
dc.project.IDLM2015042/E-infrastruktura CESNETcs
dc.project.ID90042/Velká výzkumná infrastruktura povinnost (J) - CESNET IIcs
dc.project.IDEF17_048/0007280/Aplikace moderních technologií v medicíně a průmyslucs
dc.publisherMDPIen
dc.relation.ispartofseriesSENSORSen
dc.rights© MDPIen
dc.rights.accessopenAccessen
dc.subject.translatedH&Een
dc.subject.translateddecellularizationen
dc.subject.translatedliveren
dc.subject.translatedtissue engineeringen
dc.subject.translatedsemantic segmentationen
dc.subject.translatedconvolutional neural networksen
dc.titleSemantic Segmentation of Intralobular and Extralobular Tissue from Liver Scaffold H&E Imagesen
dc.typečlánekcs
dc.typearticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen

Files

Collections

OBD
 Articles (KKY)
 Articles (NTIS)