Visualisation & analysis tools for X-PCI data Visualisation & analysis tools for X-PCI data

Cardiovascular imaging is routinely used to investigate cardiac structure and function as well as for the evaluation of cardiac remodeling in cardiovascular diseases (CVDs). For a complete understanding of the relationship between structural remodeling and cardiac dysfunction in CVDs, multi-scale imaging approaches are necessary to achieve a detailed description of ventricular architecture along with cardiac function. Recently, synchrotron-based X-ray phase-contrast imaging (SR X-PCI) has emerged as a powerful imaging technique for the investigation of cardiac structure ex-vivo.

SR X-PCI provides an opportunity to non-destructively study intact both human and animal explanted tissues with resolutions down to the submicron level (> 1 um), allowing the investigation of cardiac anatomy and tissue micro-structure in 3D and non-destructively, and assess alterations in different CVDs.

In this project, we have used SR X-PCI to image cardiac tissue biopsies from human patients with different cardiovascular diseases as well as multiorgan biopsies from COVID19 patients. However, one of the limitations of using this novel technique is the difficulty in interpreting the SR X-PCI images by pathologists and  difficulties in the 3D visualisation of the data due to the large size of the datasets. The aim of this TFG/TFM is to develop tools for the 3D visualisation and analysis of SR-XPCI images from biopsies using deep learning techniques among other tools. The idea is to digitally  stain SR-XPCI images into histological-like (hematoxylin & eosin) images in order to improve the interpretation and visualisation of SR X-PCI images by pathologists.



[1] Dejea, H. et al. Comprehensive Analysis of Animal Models of Cardiovascular Disease using Multiscale X-Ray Phase Contrast Tomography. Sci Rep-uk 9, 6996–6996 (2019).

[2] Dejea, H. et al. Microstructural analysis of cardiac endomyocardial biopsies with synchrotron radiation-based X-ray phase contrast imaging. FIMH 10263 LNCS, (2017).

[3] Combalia, M. et al. Digitally Stained Confocal Microscopy through Deep Learning. in Proceedings of The 2nd International Conference on Medical Imaging with Deep Learning (eds. Cardoso, M. J. et al.) vol. 102 121--129 (PMLR, 2019).