PuSH - Publication Server of Helmholtz Zentrum München: A sparse deep learning approach for automatic segmentation of human vasculature in multispectral optoacoustic tomography.

Navigation

Home

Deutsch

Research

Advanced Search

Browse by ...

... Journal

... Publication Type

... Research Data

... Publication Year

Publication overview

Support & Contact

Contact persons

Help

Data protection

Chlis, N.-K. ; Karlas, A. ; Fasoula, N.-A. ; Kallmayer, M.* ; Eckstein, H.H.* ; Theis, F.J. ; Ntziachristos, V. ; Marr, C.

A sparse deep learning approach for automatic segmentation of human vasculature in multispectral optoacoustic tomography.

Photoacoustics 20:100203 (2020)

Publ. Version/Full Text

DOI

PMC

	Open Access Gold

Abstract
Metrics
Extra information

Multispectral Optoacoustic Tomography (MSOT) resolves oxy- (HbO2) and deoxy-hemoglobin (Hb) to perform vascular imaging. MSOT suffers from gradual signal attenuation with depth due to light-tissue interactions: an effect that hinders the precise manual segmentation of vessels. Furthermore, vascular assessment requires functional tests, which last several minutes and result in recording thousands of images. Here, we introduce a deep learning approach with a sparse-UNET (S-UNET) for automatic vascular segmentation in MSOT images to avoid the rigorous and time-consuming manual segmentation. We evaluated the S-UNET on a test-set of 33 images, achieving a median DICE score of 0.88. Apart from high segmentation performance, our method based its decision on two wavelengths with physical meaning for the task-at-hand: 850 nm (peak absorption of oxy-hemoglobin) and 810 nm (isosbestic point of oxy-and deoxy-hemoglobin). Thus, our approach achieves precise data-driven vascular segmentation for automated vascular assessment and may boost MSOT further towards its clinical translation.

Altmetric

Additional Metrics?

[➜Log in]

Edit extra informations Login

Publication type Article: Journal article

Document type Scientific Article

Corresponding Author

Keywords Artificial Intelligence ; Clinical ; Deep Learning ; Machine Learning ; Multispectral Optoacoustic Tomography ; Segmentation ; Translational; Selection; Model

ISSN (print) / ISBN 2213-5979

Journal Photoacoustics

Quellenangaben Volume: 20, Article Number: 100203

Publisher Elsevier

Publishing Place Hackerbrucke 6, 80335 Munich, Germany

Non-patent literature Publications

Reviewing status Peer reviewed

Institute(s) Institute of Biological and Medical Imaging (IBMI)
Institute of Computational Biology (ICB)

Grants Helmholtz Zentrum Munchen
Helmholtz Association
Deutsches Zentrum für Herz-Kreislaufforschung
European Research Council