EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ConsisTNet: a spatio-temporal approach for consistent anatomical localization in endoscopic pituitary surgery

Zhehua Mao, Adrito Das, Danyal Z Khan iD, Simon C Williams, John G Hanrahan, Danail Stoyanov, Hani J Marcus, Sophia Bano

International Journal of Computer Assisted Radiology and Surgery · 2025

DOI: 10.1007/s11548-025-03369-2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Computer Assisted Radiology and Surgery, 2025. Verfasst von Zhehua Mao und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, University College London, London, UK. z.mao@ucl.ac.uk. Hauptthemen laut MEDLINE: Endoscopy, Pituitary Gland, Surgery, Computer-Assisted, Pituitary Neoplasms. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Engineering and Physical Sciences Research Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Automated localization of critical anatomical structures in endoscopic pituitary surgery is crucial for enhancing patient safety and surgical outcomes. While deep learning models have shown promise in this task, their predictions often suffer from frame-to-frame inconsistency. This study addresses this issue by proposing ConsisTNet, a novel spatio-temporal model designed to improve prediction stability.

Methods

ConsisTNet leverages spatio-temporal features extracted from consecutive frames to provide both temporally and spatially consistent predictions, addressing the limitations of single-frame approaches. We employ a semi-supervised strategy, utilizing ground-truth label tracking for pseudo-label generation through label propagation. Consistency is assessed by comparing predictions across consecutive frames using predicted label tracking. The model is optimized and accelerated using TensorRT for real-time intraoperative guidance.

Results

Compared to previous state-of-the-art models, ConsisTNet significantly improves prediction consistency across video frames while maintaining high accuracy in segmentation and landmark detection. Specifically, segmentation consistency is improved by 4.56 and 9.45% in IoU for the two segmentation regions, and landmark detection consistency is enhanced with a 43.86% reduction in mean distance error. The accelerated model achieves an inference speed of 202 frames per second (FPS) with 16-bit floating point (FP16) precision, enabling real-time intraoperative guidance.

Conclusion

ConsisTNet demonstrates significant improvements in spatio-temporal consistency of anatomical localization during endoscopic pituitary surgery, providing more stable and reliable real-time surgical assistance.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

EndoscopyPituitary GlandSurgery, Computer-AssistedPituitary NeoplasmsDeep LearningHumansSpatio-Temporal Analysis

Stichwörter der Autor:innen

Anatomical localizationEndoscopic pituitary surgeryReal-time surgical guidanceTemporal consistencyVolatility reduction

Autor:innen und Institutionen

  • Department of Computer Science, University College London, London, UK. z.mao@ucl.ac.uk.
  • UCL Hawkes Institute, University College London, London, UK. z.mao@ucl.ac.uk.
  • UCL Hawkes Institute, University College London, London, UK.
  • Department of Neurosurgery, National Hospital for Neurology and Neurosurgery, London, UK.
  • Department of Computer Science, University College London, London, UK.

ORCID-Profile: Danyal Z Khan

Förderung

  • Engineering and Physical Sciences Research Council

Zitieren

APA

Mao, Z., Das, A., Khan, D. Z., Williams, S. C., Hanrahan, J. G., Stoyanov, D., Marcus, H. J., & Bano, S. (2025). ConsisTNet: a spatio-temporal approach for consistent anatomical localization in endoscopic pituitary surgery. International Journal of Computer Assisted Radiology and Surgery. https://doi.org/10.1007/s11548-025-03369-2

Vancouver

Mao Z, Das A, Khan DZ, Williams SC, Hanrahan JG, Stoyanov D, et al. ConsisTNet: a spatio-temporal approach for consistent anatomical localization in endoscopic pituitary surgery. International Journal of Computer Assisted Radiology and Surgery. 2025. doi:10.1007/s11548-025-03369-2

BibTeX
@article{Mao2025,
  author = {Mao, Zhehua and Das, Adrito and Khan, Danyal Z and Williams, Simon C and Hanrahan, John G and Stoyanov, Danail and Marcus, Hani J and Bano, Sophia},
  title = {ConsisTNet: a spatio-temporal approach for consistent anatomical localization in endoscopic pituitary surgery},
  journal = {International Journal of Computer Assisted Radiology and Surgery},
  year = {2025},
  doi = {10.1007/s11548-025-03369-2}
}
Kostenlos starten →