Automated segmentation of dermal fillers in OCT images of mice using convolutional neural networks
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, prov...
Saved in:
Main Authors: | , , , , , , , , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2019
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/86177 http://hdl.handle.net/10220/49858 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-86177 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-861772020-11-01T05:22:14Z Automated segmentation of dermal fillers in OCT images of mice using convolutional neural networks 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 Lee Kong Chian School of Medicine (LKCMedicine) Convolutional Neural Network Optical Coherence Tomography Science::Medicine 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. Published version 2019-09-04T03:29:37Z 2019-12-06T16:17:22Z 2019-09-04T03:29:37Z 2019-12-06T16:17:22Z 2019 Journal Article Pfister, M., Schützenberger, K., Pfeiffenberger, U., Messner, A., Chen, Z., Aranha dos Santos, V., . . . Werkmeister, R. M. (2019). Automated segmentation of dermal fillers in OCT images of mice using convolutional neural networks. Biomedical Optics Express, 10(3), 1315-1328. doi:10.1364/BOE.10.001315 https://hdl.handle.net/10356/86177 http://hdl.handle.net/10220/49858 10.1364/BOE.10.001315 en Biomedical Optics Express © 2019 Optical Society of America under the terms of the OSA Open Access Publishing Agreement. Users may use, reuse, and build upon the article, or use the article for text or data mining, so long as such uses are for non-commercial purposes and appropriate attribution is maintained. All other rights are reserved. 14 p. application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Convolutional Neural Network Optical Coherence Tomography Science::Medicine |
spellingShingle |
Convolutional Neural Network Optical Coherence Tomography Science::Medicine 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 Automated segmentation of dermal fillers in OCT images of mice using convolutional neural networks |
description |
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. |
author2 |
Lee Kong Chian School of Medicine (LKCMedicine) |
author_facet |
Lee Kong Chian School of Medicine (LKCMedicine) 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 |
format |
Article |
author |
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 |
author_sort |
Pfister, Martin |
title |
Automated segmentation of dermal fillers in OCT images of mice using convolutional neural networks |
title_short |
Automated segmentation of dermal fillers in OCT images of mice using convolutional neural networks |
title_full |
Automated segmentation of dermal fillers in OCT images of mice using convolutional neural networks |
title_fullStr |
Automated segmentation of dermal fillers in OCT images of mice using convolutional neural networks |
title_full_unstemmed |
Automated segmentation of dermal fillers in OCT images of mice using convolutional neural networks |
title_sort |
automated segmentation of dermal fillers in oct images of mice using convolutional neural networks |
publishDate |
2019 |
url |
https://hdl.handle.net/10356/86177 http://hdl.handle.net/10220/49858 |
_version_ |
1683493870362427392 |