Automated segmentation of dermal fillers in OCT images of mice using convolutional neural networks

• Main Authors: Pfister, Martin, Schützenberger, Kornelia, Pfeiffenberger, Ulrike, Messner, Alina, Chen, Zhe, Puchner, Stefan, Garhöfer, Gerhard, Schmetterer, Leopold, Gröschl, Martin, Werkmeister, René M., Aranha dos Santos, Valentin
• Other Authors: Lee Kong Chian School of Medicine (LKCMedicine)
• Format: Article
• Language: English
• Published: 2019
• Subjects: Convolutional Neural Network; Optical Coherence Tomography; Science::Medicine
• Online Access: https://hdl.handle.net/10356/86177; http://hdl.handle.net/10220/49858
• Institution: Nanyang Technological University

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 10×10 mm 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.