Hokkaido University Collection of Scholarly and Academic Papers >
Graduate School of Information Science and Technology / Faculty of Information Science and Technology >
Peer-reviewed Journal Articles, etc >
Nerve Segmentation with Deep Learning from Label-Free Endoscopic Images Obtained Using Coherent Anti-Stokes Raman Scattering
This item is licensed under:Creative Commons Attribution 4.0 International
Title: | Nerve Segmentation with Deep Learning from Label-Free Endoscopic Images Obtained Using Coherent Anti-Stokes Raman Scattering |
Authors: | Yamato, Naoki Browse this author | Matsuya, Mana Browse this author | Niioka, Hirohiko Browse this author →KAKEN DB | Miyake, Jun Browse this author →KAKEN DB | Hashimoto, Mamoru Browse this author |
Keywords: | deep learning | semantic segmentation | nerve imaging | coherent anti-Stokes Raman scattering endoscopy |
Issue Date: | Jul-2020 |
Journal Title: | Biomolecules |
Volume: | 10 |
Issue: | 7 |
Start Page: | 1012 |
Publisher DOI: | 10.3390/biom10071012 |
Abstract: | Semantic segmentation with deep learning to extract nerves from label-free endoscopic
images obtained using coherent anti-Stokes Raman scattering (CARS) for nerve-sparing surgery is
described. We developed a CARS rigid endoscope in order to identify the exact location of peripheral
nerves in surgery. Myelinated nerves are visualized with a CARS lipid signal in a label-free manner.
Because the lipid distribution includes other tissues as well as nerves, nerve segmentation is required
to achieve nerve-sparing surgery. We propose using U-Net with a VGG16 encoder as a deep learning
model and pre-training with fluorescence images, which visualize the lipid distribution similar
to CARS images, before fine-tuning with a small dataset of CARS endoscopy images. For nerve
segmentation, we used 24 CARS and 1,818 fluorescence nerve images of three rabbit prostates.
We achieved label-free nerve segmentation with a mean accuracy of 0.962 and an F1 value of 0.860.
Pre-training on fluorescence images significantly improved the performance of nerve segmentation
in terms of the mean accuracy and F1 value (p < 0.05). Nerve segmentation of label-free endoscopic
images will allow for safer endoscopic surgery, while reducing dysfunction and improving prognosis
after surgery. |
Rights: | http://creativecommons.org/licenses/by/4.0/ |
Type: | article |
URI: | http://hdl.handle.net/2115/79153 |
Appears in Collections: | 情報科学院・情報科学研究院 (Graduate School of Information Science and Technology / Faculty of Information Science and Technology) > 雑誌発表論文等 (Peer-reviewed Journal Articles, etc)
|
Submitter: 橋本 守
|