[Back]

M. Pfister, K. Schützenberger, U. Pfeiffenberger, A. Messner, Z. Chen, V. dos Santos, S. Puchner, G. Garhöfer, L. Schmetterer, M. Gröschl, R.M. Werkmeister:
"Automated segmentation of dermal fillers in OCT images of mice using convolutional neural networks";
Biomedical Optics Express, 10 (2019), 3; 1315 - 1328.

We present a system for automatic determination of the intradermal volume of
hydrogels based on optical coherence tomography (OCT) and deep learning. Volumetric image
data was acquired using a custom-built OCT prototype that employs an akinetic swept laser
at 1310 nm with a bandwidth of 87 nm, providing an axial resolution of 6:5 μm in tissue.
Three-dimensional data sets of a 10mm 10mm skin patch comprising the intradermal filler
and the surrounding tissue were acquired. A convolutional neural network using a u-net-like
architecture was trained from slices of 100 OCT volume data sets where the dermal filler volume
was manually annotated. Using six-fold cross-validation, a mean accuracy of 0.9938 and a
Jaccard similarity coefficient of 0.879 were achieved.

http://dx.doi.org/10.1364/BOE.10.001315