EUVIMEDEUVIMED entdecken
Open Access

Triple-level domain adaptation for bronchoscopic depth estimation with enhanced anatomical fidelity

Jian Chen, Ali Shuaib, Zhitong Zuo, Xiaoyan Wang, Ya Guo

Biomedical Engineering Letters · 2026-07 · 16 (4) · 993-1003

DOI: 10.1007/s13534-026-00565-0 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biomedical Engineering Letters, online erschienen am 14.03.2026. Verfasst von Jian Chen und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Internet of Things Engineering, Jiangnan University, Wuxi, China. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Kuwait Foundation for the Advancement of Sciences, Taihu Light Science and Technology Research - Medical and Health Technology Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Monocular depth estimation is a key technology in bronchoscopy navigation systems, providing essential information for 3D reconstruction and precise localization. However, the limited availability of annotated data hinders the application of supervised learning methods for monocular depth estimation. To address this limitation, unsupervised domain adaptation (UDA) has been introduced to leverage labeled source-domain data and improve target-domain performance. Existing single-level UDA methods can reduce domain discrepancies but often distort the spatial structure of bronchial lumens or fail to preserve fine-grained local details, diminishing both the anatomical fidelity and geometric consistency in the predicted depth maps. To overcome these challenges, we introduce triple-level domain adaptation for depth estimation (TriDADE), which unifies image-level adaptive Fourier domain adaptation, feature-level domain adaptation, and pixel-level discrimination with consistency constraints, to refine depth maps jointly. Experiments demonstrate that TriDADE achieves the lowest absolute relative error of 0.0971, surpassing even the intra-domain training performance, while improving depth prediction accuracy under the 1.25 threshold ([Formula: see text]) to 92%, significantly outperforming existing UDA methods. Qualitative results further elucidate the advantages of preserving bronchial lumen boundaries and fine anatomical details while producing smooth and geometrically consistent depth gradients. The proposed TriDADE framework effectively addresses the limitations of existing UDA methods, delivering substantial gains in both quantitative accuracy and anatomical fidelity. These improvements support the development of downstream clinical applications such as bronchoscopy navigation, 3D reconstruction, and precise diagnosis.

Schlagwörter

Stichwörter der Autor:innen

Anatomical fidelityBronchoscopy navigationMonocular depth estimationUnsupervised domain adaptation

Autor:innen und Institutionen

  • School of Internet of Things Engineering, Jiangnan University, Wuxi, China.
  • Biomedical Engineering Unit, Department of Physiology, College of Medicine, Kuwait University, Kuwait, Kuwait.
  • Department of Respiratory Disease, The Hospital Affiliated to Jiangnan University, Wuxi, China.
  • Department of Pulmonary and Critical Care Medicine, Beijing Jishuitan Hospital, Capital Medical University, Beijing, China.

Förderung

  • Kuwait Foundation for the Advancement of Sciences
  • Taihu Light Science and Technology Research - Medical and Health Technology Research

Zitieren

APA

Chen, J., Shuaib, A., Zuo, Z., Wang, X., & Guo, Y. (2026). Triple-level domain adaptation for bronchoscopic depth estimation with enhanced anatomical fidelity. Biomedical Engineering Letters, 16(4), 993-1003. https://doi.org/10.1007/s13534-026-00565-0

Vancouver

Chen J, Shuaib A, Zuo Z, Wang X, Guo Y. Triple-level domain adaptation for bronchoscopic depth estimation with enhanced anatomical fidelity. Biomedical Engineering Letters. 2026;16(4):993-1003. doi:10.1007/s13534-026-00565-0

BibTeX
@article{Chen2026,
  author = {Chen, Jian and Shuaib, Ali and Zuo, Zhitong and Wang, Xiaoyan and Guo, Ya},
  title = {Triple-level domain adaptation for bronchoscopic depth estimation with enhanced anatomical fidelity},
  journal = {Biomedical Engineering Letters},
  year = {2026},
  volume = {16},
  number = {4},
  pages = {993--1003},
  doi = {10.1007/s13534-026-00565-0}
}
Kostenlos starten →