University of Oulu

Tiulpin A., Finnilä M., Lehenkari P., Nieminen H.J., Saarakkala S. (2020) Deep-Learning for Tidemark Segmentation in Human Osteochondral Tissues Imaged with Micro-computed Tomography. In: Blanc-Talon J., Delmas P., Philips W., Popescu D., Scheunders P. (eds) Advanced Concepts for Intelligent Vision Systems. ACIVS 2020. Lecture Notes in Computer Science, vol 12002. Springer, Cham. https://doi.org/10.1007/978-3-030-40605-9_12

Deep-learning for tidemark segmentation in human osteochondral tissues imaged with micro-computed tomography

Saved in:
Author: Tiulpin, Aleksei1,2; Finnilä, Mikko1; Lehenkari, Petri1,2;
Organizations: 1University of Oulu, Oulu, Finland
2Oulu University Hospital, Oulu, Finland
3University of Helsinki, Helsinki, Finland
4Aalto University, Espoo, Finland
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 1 MB)
Persistent link: http://urn.fi/urn:nbn:fi-fe202201199481
Language: English
Published: Springer Nature, 2020
Publish Date: 2022-01-19
Description:

Abstract

Three-dimensional (3D) semi-quantitative grading of pathological features in articular cartilage (AC) offers significant improvements in basic research of osteoarthritis (OA). We have earlier developed the 3D protocol for imaging of AC and its structures which includes staining of the sample with a contrast agent (phosphotungstic acid, PTA) and a consequent scanning with micro-computed tomography. Such a protocol was designed to provide X-ray attenuation contrast to visualize AC structure. However, at the same time, this protocol has one major disadvantage: the loss of contrast at the tidemark (calcified cartilage interface, CCI). An accurate segmentation of CCI can be very important for understanding the etiology of OA and ex-vivo evaluation of tidemark condition at early OA stages. In this paper, we present the first application of Deep Learning to PTA-stained osteochondral samples that allows to perform tidemark segmentation in a fully-automatic manner. Our method is based on U-Net trained using a combination of binary cross-entropy and soft-Jaccard loss. On cross-validation, this approach yielded intersection over the union of 0.59, 0.70, 0.79, 0.83 and 0.86 within 15 μm, 30 μm, 45 μm, 60 μm. and 75 μm padded zones around the tidemark, respectively. Our codes and the dataset that consisted of 35 PTA-stained human AC samples are made publicly available together with the segmentation masks to facilitate the development of biomedical image segmentation methods.

see all

Series: Lecture notes in computer science
ISSN: 0302-9743
ISSN-E: 1611-3349
ISSN-L: 0302-9743
ISBN: 978-3-030-40605-9
ISBN Print: 978-3-030-40604-2
Issue: 12002
Pages: 131 - 138
DOI: 10.1007/978-3-030-40605-9_12
OADOI: https://oadoi.org/10.1007/978-3-030-40605-9_12
Host publication: Advanced concepts for intelligent vision systems
Host publication editor: Blanc-Talon, Jacques
Delmas, Patrice
Philips, Wilfried
Popescu, Dan
Scheunders, Paul
Conference: Advanced Concepts for Intelligent Vision Systems : 20th International Conference
Type of Publication: A4 Article in conference proceedings
Field of Science: 3126 Surgery, anesthesiology, intensive care, radiology
3111 Biomedicine
213 Electronic, automation and communications engineering, electronics
217 Medical engineering
Subjects:
Funding: This work was supported by Academy of Finland (grants 268378, 303786, 311586 and 314286), European Research Council under the European Union’s Seventh Framework Programme (FP/2007-2013)/ERC Grant Agreement no. 336267, the strategic funding of the University of Oulu and KAUTE foundation.
Copyright information: © Springer Nature Switzerland AG 2020. This is a post-peer-review, pre-copyedit version of an article published in Advanced Concepts for Intelligent Vision Systems : 20th International Conference, ACIVS 2020, Auckland, New Zealand, February 10–14, 2020, proceedings. The final authenticated version is available online at: https://doi.org/10.1007/978-3-030-40605-9_12.