Clinical feasibility of low-magnification fluorescence imaging for breast cancer margin detection using texture analysis and deep learning
Biomedical Optics Express · 01.12.2026 · 17 (12) · 6263
DOI: 10.1364/boe.596807 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biomedical Optics Express, online erschienen am 13.11.2026. Verfasst von Tianling Niu und 8 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Gefördert von: National Institute of Biomedical Imaging and Bioengineering.
Abstract (Originalsprache)
High-resolution images of unprocessed surgical breast tissue can be obtained using microscopy with ultraviolet surface excitation (MUSE). This technique is considered a promising method for checking surgical margins during breast cancer surgery. In this study, MUSE images at 4× and 10× magnifications were compared using patch-level classification methods. Texture analysis (TA) based on local binary patterns (LBP) and deep learning (DL) with a base vision transformer (ViT) model was used. Both methods achieved similar performance at both magnifications. Using the DL method, both 4× and 10× magnifications achieved 96.30% sensitivity, 100% specificity, and 98.18% accuracy. Using the TA method, 4× achieved better specificity (100% vs 93.33%) and 10× yielded higher sensitivity (100% vs 93.33%), but both had the same accuracy (96.67%). No clear improvement in performance was observed with 10× magnification. These results show that 4× imaging achieves the same diagnostic accuracy as 10× imaging. At the same time, 4× offers a larger field of view and faster image capture. Therefore, lower magnification can be effectively used in MUSE systems for accurate and efficient intraoperative margin assessment.
Förderung
- National Institute of Biomedical Imaging and Bioengineering
Zitieren
APA
Niu, T., Afshin, P., Lu, T., Helminiak, D., Jorns, J., Patton, M., Yen, T., Ye, D. H., & Yu, B. (2026). Clinical feasibility of low-magnification fluorescence imaging for breast cancer margin detection using texture analysis and deep learning. Biomedical Optics Express, 17(12), 6263. https://doi.org/10.1364/boe.596807
Vancouver
Niu T, Afshin P, Lu T, Helminiak D, Jorns J, Patton M, et al. Clinical feasibility of low-magnification fluorescence imaging for breast cancer margin detection using texture analysis and deep learning. Biomedical Optics Express. 2026;17(12):6263. doi:10.1364/boe.596807
BibTeX
@article{Niu2026,
author = {Niu, Tianling and Afshin, Pouya and Lu, Tongtong and Helminiak, David and Jorns, Julie and Patton, Mollie and Yen, Tina and Ye, Dong Hye and Yu, Bing},
title = {Clinical feasibility of low-magnification fluorescence imaging for breast cancer margin detection using texture analysis and deep learning},
journal = {Biomedical Optics Express},
year = {2026},
volume = {17},
number = {12},
pages = {6263},
doi = {10.1364/boe.596807}
}
EUVIMED