TY - JOUR
T1 - Convolutional neural networks
T2 - Ensemble modeling, fine-tuning and unsupervised semantic localization for neurosurgical CLE images
AU - Izadyyazdanabadi, Mohammadhassan
AU - Belykh, Evgenii
AU - Mooney, Michael
AU - Martirosyan, Nikolay
AU - Eschbacher, Jennifer
AU - Nakaji, Peter
AU - Preul, Mark C.
AU - Yang, Yezhou
N1 - Funding Information:
This work was supported by the Newsome Family Endowed Chair of Neurosurgery Research at the Barrow Neurological Institute held by Dr. Preul and by funds from the Barrow Neurological Foundation. Dr. Yezhou Yang is partially supported by NSF grant #1750802.
Publisher Copyright:
© 2018 Elsevier Inc.
PY - 2018/7
Y1 - 2018/7
N2 - Confocal laser endomicroscopy (CLE) is an advanced optical fluorescence technology undergoing assessment for applications in brain tumor surgery. Many of the CLE images can be distorted and interpreted as nondiagnostic. However, just one neat CLE image might suffice for intraoperative diagnosis of the tumor. While manual examination of thousands of nondiagnostic images during surgery would be impractical, this creates an opportunity for a model to select diagnostic images for the pathologists or surgeons review. In this study, we sought to develop a deep learning model to automatically detect the diagnostic images. We explored the effect of training regimes and ensemble modeling and localized histological features from diagnostic CLE images. The developed model could achieve promising agreement with the ground truth. With the speed and precision of the proposed method, it has potential to be integrated into the operative workflow in the brain tumor surgery.
AB - Confocal laser endomicroscopy (CLE) is an advanced optical fluorescence technology undergoing assessment for applications in brain tumor surgery. Many of the CLE images can be distorted and interpreted as nondiagnostic. However, just one neat CLE image might suffice for intraoperative diagnosis of the tumor. While manual examination of thousands of nondiagnostic images during surgery would be impractical, this creates an opportunity for a model to select diagnostic images for the pathologists or surgeons review. In this study, we sought to develop a deep learning model to automatically detect the diagnostic images. We explored the effect of training regimes and ensemble modeling and localized histological features from diagnostic CLE images. The developed model could achieve promising agreement with the ground truth. With the speed and precision of the proposed method, it has potential to be integrated into the operative workflow in the brain tumor surgery.
KW - Brain tumor
KW - Confocal laser endomicroscopy
KW - Ensemble modeling
KW - Neural network
KW - Surgical vision
KW - Unsupervised localization
UR - http://www.scopus.com/inward/record.url?scp=85046376836&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85046376836&partnerID=8YFLogxK
U2 - 10.1016/j.jvcir.2018.04.004
DO - 10.1016/j.jvcir.2018.04.004
M3 - Article
AN - SCOPUS:85046376836
SN - 1047-3203
VL - 54
SP - 10
EP - 20
JO - Journal of Visual Communication and Image Representation
JF - Journal of Visual Communication and Image Representation
ER -