Synchrotron X-Ray Phase Contrast Imaging and Deep Neural Networks for Cardiac Collagen Quantification in Hypertensive Rat Model

Hector Dejea, Christine Tanner, R. Achanta, Marco Stampanoni, Fernando Perez-Cruz, Ender Konukoglu, Anne Bonnin: Synchrotron X-Ray Phase Contrast Imaging and Deep Neural Networks for Cardiac Collagen Quantification in Hypertensive Rat Model. En: Coudi`ere, Yves; Ozenne, Valéry; Vigmond, Edward; Zemzemi, Nejib (Ed.): Functional Imaging and Modeling of the Heart, pp. 187–195, Springer International Publishing, Cham, 2019, ISBN: 978-3-030-21949-9.

Resumen

Än excessive deposition of collagen matrix in the myocardium has been clearly identified as an indication of the progression towards heart failure. Nevertheless, few studies have been performed for its quantification and most of them use 2D histological images, thus losing valuable encoded 3D information. In this study, several biopsies of areas of the left ventricle from age-matched spontaneously hypertensive rats and Wistar Kyoto rats were imaged using synchrotron radiation-based X-ray phase contrast imaging. Then, an optimized deep neural network was used for automatic image segmentation in order to assess collagen fraction differences between models as well as its age dependency. The results show a general increase in the collagen percentage in the hypertensive model and for older rats. Such tendency is comparable with the reports found in the literature. Therefore, this proof of concept shows that synchrotron imaging in combination with deep neural networks is a powerful tool for the investigation and quantification of cardiac microstructures."

    BibTeX (Download)

    @inproceedings{10.1007/978-3-030-21949-9_21,
    title = {Synchrotron X-Ray Phase Contrast Imaging and Deep Neural Networks for Cardiac Collagen Quantification in Hypertensive Rat Model},
    author = {Hector Dejea and Christine Tanner and R. Achanta and Marco Stampanoni and Fernando Perez-Cruz and Ender Konukoglu and Anne Bonnin},
    editor = {Yves Coudi`ere and Val\'{e}ry Ozenne and Edward Vigmond and Nejib Zemzemi},
    isbn = {978-3-030-21949-9},
    year  = {2019},
    date = {2019-01-01},
    urldate = {2019-01-01},
    booktitle = {Functional Imaging and Modeling of the Heart},
    pages = {187--195},
    publisher = {Springer International Publishing},
    address = {Cham},
    abstract = {\"{A}n excessive deposition of collagen matrix in the myocardium has been clearly identified as an indication of the progression towards heart failure. Nevertheless, few studies have been performed for its quantification and most of them use 2D histological images, thus losing valuable encoded 3D information. In this study, several biopsies of areas of the left ventricle from age-matched spontaneously hypertensive rats and Wistar Kyoto rats were imaged using synchrotron radiation-based X-ray phase contrast imaging. Then, an optimized deep neural network was used for automatic image segmentation in order to assess collagen fraction differences between models as well as its age dependency. The results show a general increase in the collagen percentage in the hypertensive model and for older rats. Such tendency is comparable with the reports found in the literature. Therefore, this proof of concept shows that synchrotron imaging in combination with deep neural networks is a powerful tool for the investigation and quantification of cardiac microstructures."},
    keywords = {},
    pubstate = {published},
    tppubtype = {inproceedings}
    }