Deep-learning-aided sarcoma biopsy guidance using forward-view endoscopic optical coherence tomography
- 16 September 2026
- journal article
- Published by Optica Publishing Group in Biomedical Optics Express
- Vol. 17 (10) , 5213-5231
Abstract
Sarcoma diagnosis remains challenging due to tumor heterogeneity and the risk of sampling errors during biopsy, as tissue misidentification can result in non-diagnostic outcomes and repeated procedures. This study specifically targets undifferentiated pleomorphic sarcoma (UPS) and myxofibrosarcoma, imaged in specimens from the human arms and legs. Optical coherence tomography (OCT) offers high-resolution, real-time microstructural imaging and has shown strong potential for image-guided oncology. In this study, we benchmarked five 2D deep learning models and one custom 3D convolutional neural network (CNN) for normal versus tumor tissues classification using endoscopic OCT. The 2D models were applied to cross-sectional 2D images while the 3D CNN operated on volumetric images, with both evaluated across the Intensity and polarization-sensitive OCT channels (PS-OCT). 3D CNN reached the highest accuracy of 92.67% on Intensity, while PS-OCT channels benefited more from modern 2D architectures and 3D volumetric modeling, with performance gains up to 9.63% for the optic axis. These results demonstrated the feasibility of endoscopic OCT as a real-time, label-free tissue characterization tool during biopsy of these sarcoma tissues. The integration of deep learning with forward-viewing endoscopic OCT offers a promising pathway toward more accurate needle guidance and reduced diagnostic failure rates and established a reproducible benchmarking framework for future OCT-based detection and analysis of sarcoma tissues.Keywords
Funding Information
- University of Oklahoma Health Sciences Center (NCI P30CA225520)
- U.S. National Science Foundation (OIA-2132161)
- U.S. National Science Foundation (OIA-2238648)
- U.S. National Science Foundation (OIA-2331409)
- National Institutes of Health (R01DK133717)
- Oklahoma Center for the Advancement of Science and Technology (HR23-071)
- Oklahoma Center of Medical Imaging for Translational Cancer Research (P20 GM135009)
- Prevent Cancer Foundation
- American Liver Foundation
- Data Institute for Societal Challenges and the Research Council
- University of Oklahoma
This publication has 43 references indexed in Scilit:
- Ultrasound-Based Tomographic Imaging Reconstruction and Synthesis Methods: a Scoping ReviewJournal of Imaging Informatics in Medicine, 2025
- Deep Learning for Autonomous Surgical Guidance Using 3‐Dimensional Images From Forward‐Viewing Endoscopic Optical Coherence TomographyJournal of Biophotonics, 2025
- Enhancing epidural needle guidance using a polarization‐sensitive optical coherence tomography probe with convolutional neural networksJournal of Biophotonics, 2023
- Computer‐aided Veress needle guidance using endoscopic optical coherence tomography and convolutional neural networksJournal of Biophotonics, 2022
- Soft tissue and visceral sarcomas: ESMO–EURACAN–GENTURIS Clinical Practice Guidelines for diagnosis, treatment and follow-up☆Annals of Oncology, 2021
- Fully Automated Postlumpectomy Breast Margin Assessment Utilizing Convolutional Neural Network Based Optical Coherence Tomography Image Classification MethodAcademic Radiology, 2020
- Automated assessment of breast cancer margin in optical coherence tomography images via pretrained convolutional neural networkJournal of Biophotonics, 2018
- Needle tract seeding after percutaneous biopsy of sarcoma: Risk/benefit considerationsCancer, 2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- MR imaging of myxofibrosarcoma and undifferentiated sarcoma with emphasis on tail sign; diagnostic and prognostic valueEuropean Radiology, 2014