Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Clinical Implementation and Oncological Relevance of Molecular Profiling in Brain Metastases Patients-A Multicenter Retrospective Cohort Study.

International journal of cancer·2026

Same author

Prevalence of somatic SF3B1R625H mutation in lactotroph tumours from a multi-centric cohort: a digital PCR-based study.

European journal of endocrinology·2026

Same author

Craniometric Anatomy of the Middle Meningeal Artery Bifurcation With Relevance for Simultaneous Surgical Occlusion in Chronic Subdural Hematoma.

Operative neurosurgery (Hagerstown, Md.)·2026

Same author

Cadaver-based hands-on course in cervical spine surgery: a prospective evaluation of surgical confidence and self-perceived autonomy.

Acta neurochirurgica·2026

Same author

Endoscopic endonasal approach for recurrent craniopharyngioma in adults.

Neurosurgical focus·2026

Same author

The "Rescue screw" as a freehand revision strategy for implant loosening: a technical note and comparative biomechanical study on human cadavers.

The spine journal : official journal of the North American Spine Society·2026

Same journal

A multimodal deepsurv approach: integrating radiomics and clinical factors for brain metastasis survival prediction.

Journal of clinical neuroscience : official journal of the Neurosurgical Society of Australasia·2026

Same journal

CSF-venous fistula with subdural hematoma in the setting of chronic anticoagulation.

Journal of clinical neuroscience : official journal of the Neurosurgical Society of Australasia·2026

Same journal

Tumor control and cranial nerve outcomes after Gamma Knife radiosurgery for Glomus jugulare tumors: a systematic review, meta-analysis, and institutional failure pattern analysis.

Journal of clinical neuroscience : official journal of the Neurosurgical Society of Australasia·2026

Same journal

Clinical utility of maximal and minimal intensity projections in T2-weighted MRI for neurosurgical planning.

Journal of clinical neuroscience : official journal of the Neurosurgical Society of Australasia·2026

Same journal

Clinical and CT perfusion outcomes after direct STA-MCA bypass in moyamoya and non-moyamoya steno-occlusive disease: an Indonesian single-center cohort.

Journal of clinical neuroscience : official journal of the Neurosurgical Society of Australasia·2026

Same journal

Effect of non-consecutive treatment during hypofractionated stereotactic radiosurgery (HF-SRS) for brain metastases.

Journal of clinical neuroscience : official journal of the Neurosurgical Society of Australasia·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Feb 17, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Real-time intraoperative depth estimation in transsphenoidal surgery using deep learning: A feasibility study.

Olivier Zanier¹, Aron Alakmeh², Raffaele Da Mutten³

¹Machine Intelligence in Clinical Neuroscience & Microsurgical Neuroanatomy (MICN) Laboratory, Department of Neurosurgery, Clinical Neuroscience Center, University Hospital Zurich, University of Zurich, Zurich, Switzerland; Department of Oncology, University of Oxford, Oxford OX3 7DQ, United Kingdom.

Journal of Clinical Neuroscience : Official Journal of the Neurosurgical Society of Australasia

|February 15, 2026

Summary

This summary is machine-generated.

Deep learning models like DINOv2 can estimate depth in endoscopic neurosurgery videos, potentially improving surgeon orientation. This artificial intelligence application aids in visualizing surgical fields without special equipment.

Keywords:

Deep learning Depth estimation Endoscopy Pituitary surgery Transsphenoidal surgery

More Related Videos

Lateral Molar Approach-Driven Transoral Endoscopic Procedure for Benign Infratemporal Fossa Tumor Resection

Lateral Molar Approach-Driven Transoral Endoscopic Procedure for Benign Infratemporal Fossa Tumor Resection

Published on: August 15, 2025

Role of Diffusion MRI Tractography in Endoscopic Endonasal Skull Base Surgery

Role of Diffusion MRI Tractography in Endoscopic Endonasal Skull Base Surgery

Published on: July 5, 2021

Related Experiment Videos

Last Updated: Feb 17, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Lateral Molar Approach-Driven Transoral Endoscopic Procedure for Benign Infratemporal Fossa Tumor Resection

Lateral Molar Approach-Driven Transoral Endoscopic Procedure for Benign Infratemporal Fossa Tumor Resection

Published on: August 15, 2025

Role of Diffusion MRI Tractography in Endoscopic Endonasal Skull Base Surgery

Role of Diffusion MRI Tractography in Endoscopic Endonasal Skull Base Surgery

Published on: July 5, 2021

Area of Science:

Neurosurgery
Medical Imaging
Artificial Intelligence

Background:

Endoscopic endonasal and transcranial approaches are vital in neurosurgery for resecting tumors like pituitary adenomas.
Standard endoscopic video is 2D, limiting depth perception and intraoperative orientation.

Purpose of the Study:

To explore the use of the deep learning model DINOv2 for generating 3D depth information from 2D endoscopic surgical videos.
To assess the feasibility of enhancing intraoperative orientation in neurosurgery using AI-driven depth estimation.

Main Methods:

Applied the DINOv2 deep learning model to video feeds from eight transsphenoidal endonasal surgeries.
Generated numeric depth maps and visualized them using colormaps.
Evaluated depth estimation quality subjectively by neurosurgeons and semi-quantitatively against manual segmentations.

Main Results:

DINOv2 successfully generated depth maps and colormaps, aligning well with expert subjective assessments.
Semi-quantitative analysis showed a mean DICE Similarity Index of 0.48 for depth area estimations.
Results indicate potential but require cautious interpretation due to non-standardized segmentation cutoffs.

Conclusions:

Deep learning, specifically DINOv2, can estimate depth in endoscopic neurosurgery imaging.
This technology holds promise for improving intraoperative orientation and augmenting endoscopic video feeds.
AI offers significant opportunities to enhance surgical visualization and navigation.