EUVIMEDEUVIMED entdecken
Open Access

Deep learning fusion of multi-channel imaging from polarization-sensitive optical coherence tomography

Yunlong Liu iD, Chen Wang iD, Paul Calle, Justin Reynolds, Sinaro Ly iD, Haoyang Cui iD, Alberto J de Armendi, Shashank S Shettar, Kar-Ming Fung, Qi Li, Rupa Haldavnekar, Qinggong Tang iD und 1 weitere

Biomedical Optics Express · 01.07.2026 · 17 (7) · 3553

DOI: 10.1364/boe.597049 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biomedical Optics Express, online erschienen am 11.06.2026. Verfasst von Yunlong Liu und 12 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, University of Oklahoma, Norman, OK, USA. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIGMS NIH HHS, NCI NIH HHS, NIDDK NIH HHS.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-contrast polarization-sensitive optical coherence tomography (PS-OCT) provides complementary structural and polarization information that may improve epidural tissue classification. Here, we evaluated deep learning fusion of four PS-OCT channels, including intensity, phase retardation, degree of polarization uniformity (DOPU), and optic axis, using porcine (n = 6) and human (n = 5) spinal specimens. We benchmarked six multi-channel fusion strategies: Probability averaging, feature concatenation, trainable weighted output, shared-stage resnet, merged multi-channel input, and pooled data. Across subject-level nested cross-validation, multi-channel methods achieved modest but consistent accuracy improvements over the best single-channel baselines while reducing subject-to-subject variability. On porcine data, Probability Averaging increased mean validation accuracy by 3.46% (93.07% vs. 89.61% for the best single-channel baseline). On human data, fusion methods maintained the high single-channel baseline (approximately 97% to 98%) while modestly improving stability, with probability averaging achieving the highest mean validation accuracy (98.26%). In cross-testing, trainable weighted output achieved 92.32% versus 91.53% for the best porcine single-channel baseline, and probability averaging achieved 97.87% versus 97.75% for the best human single-channel baseline. On the human cohort, the gain in mean accuracy was small, but multi-channel fusion produced a statistically significant reduction in between-subject variance (Levene's p = 0.0108) and removed the need to know in advance which single channel would generalize best. Overall, multi-channel fusion improved classification performance and robustness, with probability averaging offering a favorable balance between accuracy and complexity because it requires no additional training beyond single-channel models.

Autor:innen und Institutionen

  • School of Computer Science, University of Oklahoma, Norman, OK, USA.
  • Stephenson School of Biomedical Engineering, University of Oklahoma, Norman, OK, USA.
  • Department of Anesthesiology, University of Oklahoma Health Campus, Oklahoma City, 73104, OK, USA.
  • Department of Pathology, University of Oklahoma Health Campus, Oklahoma City, 73104, OK, USA.
  • Stephenson Cancer Center, University of Oklahoma Health Campus, Oklahoma City, OK, USA.
  • School of Electrical and Computer Engineering, University of Oklahoma, Norman, OK, USA.

ORCID-Profile: Yunlong Liu, Chen Wang, Sinaro Ly, Haoyang Cui, Qinggong Tang

Förderung

  • NIGMS NIH HHS
  • NCI NIH HHS
  • NIDDK NIH HHS
  • University of Oklahoma Health Sciences Center
  • National Science Foundation
  • National Institutes of Health
  • Oklahoma Center for the Advancement of Science and Technology
  • Medical Imaging COBRE

Zitieren

APA

Liu, Y., Wang, C., Calle, P., Reynolds, J., Ly, S., Cui, H., de Armendi, A. J., Shettar, S. S., Fung, K. M., Li, Q., Haldavnekar, R., Tang, Q., & Pan, C. (2026). Deep learning fusion of multi-channel imaging from polarization-sensitive optical coherence tomography. Biomedical Optics Express, 17(7), 3553. https://doi.org/10.1364/boe.597049

Vancouver

Liu Y, Wang C, Calle P, Reynolds J, Ly S, Cui H, et al. Deep learning fusion of multi-channel imaging from polarization-sensitive optical coherence tomography. Biomedical Optics Express. 2026;17(7):3553. doi:10.1364/boe.597049

BibTeX
@article{Liu2026,
  author = {Liu, Yunlong and Wang, Chen and Calle, Paul and Reynolds, Justin and Ly, Sinaro and Cui, Haoyang and de Armendi, Alberto J and Shettar, Shashank S and Fung, Kar-Ming and Li, Qi and Haldavnekar, Rupa and Tang, Qinggong and Pan, Chongle},
  title = {Deep learning fusion of multi-channel imaging from polarization-sensitive optical coherence tomography},
  journal = {Biomedical Optics Express},
  year = {2026},
  volume = {17},
  number = {7},
  pages = {3553},
  doi = {10.1364/boe.597049}
}
Kostenlos starten →