Deep Learning for Autonomous Surgical Guidance Using 3‐Dimensional Images From Forward‐Viewing Endoscopic Optical Coherence Tomography
Journal of Biophotonics · 2025
DOI: 10.1002/jbio.202500181 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Biophotonics, 2025. Verfasst von Sinaro Ly und 14 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, University of Oklahoma, Norman, Oklahoma, USA. Hauptthemen laut MEDLINE: Tomography, Optical Coherence, Deep Learning, Imaging, Three-Dimensional, Endoscopy. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIGMS NIH HHS, NIDDK NIH HHS, The University of Oklahoma Libraries' Open Access Fund.
Abstract (Originalsprache)
A three‐dimensional convolutional neural network (3D‐CNN) was developed for the analysis of volumetric optical coherence tomography (OCT) images to enhance endoscopic guidance during percutaneous nephrostomy. The model was performance‐benchmarked using a 10‐fold nested cross‐validation procedure and achieved an average test accuracy of 90.57% across a dataset of 10 porcine kidneys. This performance significantly exceeded that of 2D‐CNN models that attained average test accuracies ranging from 85.63% to 88.22% using 1, 10, or 100 radial sections extracted from the 3D OCT volumes. The 3D‐CNN (~12 million parameters) was benchmarked against three state‐of‐the‐art volumetric architectures: the 3D Vision Transformer (3D‐ViT, ~45 million parameters), 3D‐DenseNet121 (~12 million parameters), and the Multi‐plane and Multi‐slice Transformer (M3T, ~29 million parameters). While these models achieved comparable inferencing accuracy, the 3D‐CNN exhibited lower inference latency (33 ms) than 3D‐ViT (86 ms), 3D‐DenseNet121 (58 ms), and M3T (93 ms), representing a critical advantage for real‐time surgical guidance applications. These results demonstrate the 3D‐CNN's capability as a powerful and practical tool for computer‐aided diagnosis in OCT‐guided surgical interventions.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Computer Science, University of Oklahoma, Norman, Oklahoma, USA.
- Stephenson School of Biomedical Engineering, University of Oklahoma, Norman, Oklahoma, USA.
- Department of Pathology, University of Oklahoma Health Sciences Center, Oklahoma City, Oklahoma, USA.
- Stephenson Cancer Center, University of Oklahoma Health Sciences Center, Oklahoma City, Oklahoma, USA.
- Children's Hospital, University of Oklahoma Health Sciences Center, Oklahoma City, Oklahoma, USA.
- Department of Urology, University of Oklahoma Health Sciences Center, Oklahoma City, Oklahoma, USA.
ORCID-Profile: Sinaro Ly, Chen Wang, Paul Calle, Qinghao Zhang
Förderung
- NIGMS NIH HHS
- NIDDK NIH HHS
- The University of Oklahoma Libraries' Open Access Fund
- NCI NIH HHS
- Oklahoma Center for the Advancement of Science and Technology
- National Science Foundation
- National Cancer Institute
- National Institute of Diabetes and Digestive and Kidney Diseases
Zitieren
APA
Ly, S., Badré, A., Brandt, P., Wang, C., Calle, P., Reynolds, J., Zhang, Q., Fung, K. M., Cui, H., Yu, Z., Patel, S. G., Liu, Y., Bradley, N. A., Tang, Q., & Pan, C. (2025). Deep Learning for Autonomous Surgical Guidance Using 3‐Dimensional Images From Forward‐Viewing Endoscopic Optical Coherence Tomography. Journal of Biophotonics. https://doi.org/10.1002/jbio.202500181
Vancouver
Ly S, Badré A, Brandt P, Wang C, Calle P, Reynolds J, et al. Deep Learning for Autonomous Surgical Guidance Using 3‐Dimensional Images From Forward‐Viewing Endoscopic Optical Coherence Tomography. Journal of Biophotonics. 2025. doi:10.1002/jbio.202500181
BibTeX
@article{Ly2025,
author = {Ly, Sinaro and Badré, Adrien and Brandt, Parker and Wang, Chen and Calle, Paul and Reynolds, Justin and Zhang, Qinghao and Fung, Kar-Ming and Cui, Haoyang and Yu, Zhongxin and Patel, Sanjay G and Liu, Yunlong and Bradley, Nathan A and Tang, Qinggong and Pan, Chongle},
title = {Deep Learning for Autonomous Surgical Guidance Using 3‐Dimensional Images From Forward‐Viewing Endoscopic Optical Coherence Tomography},
journal = {Journal of Biophotonics},
year = {2025},
doi = {10.1002/jbio.202500181}
}
EUVIMED