Abstract:
Segmentation of microvessels measured using two-photon microscopy has been studied in the literature with limited success due to uneven intensities associated with optica...Show MoreMetadata
Abstract:
Segmentation of microvessels measured using two-photon microscopy has been studied in the literature with limited success due to uneven intensities associated with optical imaging and shadowing effects. In this work, we address this problem using a customized version of a recently developed fully convolutional neural network, namely, FC-DensNets. To train and validate the network, manual annotations of 8 angiograms from two-photon microscopy was used. Segmentation results are then compared with that of a state-of-the-art scheme that was developed for the same purpose and also based on deep learning. Experimental results show improved performance of used FC-DenseNet in providing accurate and yet end-to-end segmentation of microvessels in two-photon microscopy.
Published in: 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
Date of Conference: 18-21 July 2018
Date Added to IEEE Xplore: 28 October 2018
ISBN Information:
ISSN Information:
PubMed ID: 30440483