Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: May 28, 2026

Intracranial Implantation with Subsequent 3D In Vivo Bioluminescent Imaging of Murine Gliomas
09:46

Intracranial Implantation with Subsequent 3D In Vivo Bioluminescent Imaging of Murine Gliomas

Published on: November 6, 2011

Human-in-the-Loop Enhances Machine Learning Inference in Intraoperative Optical Coherence Tomography Glioma Imaging.

Radik Zinatullin1,2, Alexander Sovetsky1, Artem Grishin2

  • 1Russian Academy of Sciences, Institute of Applied Physics, 46 Ulyanov Str., 603951 Nizhny Novgorod, Russia.

Medical Sciences (Basel, Switzerland)
|May 27, 2026
PubMed
Summary

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

Hybrid channels containing the dupα7 subunit mediate resistance to α7-nAChR targeting therapy in metastatic melanoma.

American journal of physiology. Cell physiology·2026
Same author

Multiparametric Detection of Effects of TILs and Oncolytic Virotherapy on Xenograft Mouse Model of Glioblastoma.

Biomedicines·2025
Same author

Optical express-biopsy of gliomas using macroscopic fluorescence lifetime imaging.

Biomedical optics express·2025
Same author

Brain Tumor-Induced Changes in Routine Parameters of the Lipid Spectrum of Blood Plasma and Its Short-Chain Fatty Acids.

Current issues in molecular biology·2025
Same author

Optical Coherence Tomography Angiography, Elastography, and Attenuation Imaging for Evaluation of Liver Regeneration.

Diagnostics (Basel, Switzerland)·2025
Same author

Fluorescence Lifetime Imaging of NAD(P)H in Patients' Lymphocytes: Evaluation of Efficacy of Immunotherapy.

Cells·2025
Same journal

The Clinical Impact of Patient Embarrassment in Gynecology: A Comprehensive Review of Barriers, Consequences, and Mitigation Strategies.

Medical sciences (Basel, Switzerland)·2026
Same journal

Physical Performance as a Predictor of Length of Hospital Stay in Patients Undergoing Open-Heart Surgery: A Multicenter Prospective Study.

Medical sciences (Basel, Switzerland)·2026
Same journal

Renal Involvement in Pediatric Small-Vessel Vasculitis: A Comprehensive Review of Clinical Impact, Diagnosis, and Management.

Medical sciences (Basel, Switzerland)·2026
Same journal

MRI-Based Radiomics and Artificial Intelligence for Prediction of Recurrence and Prognostic Outcomes in Oral Tongue Squamous Cell Carcinoma: A Systematic Review with Functional Meta-Synthesis.

Medical sciences (Basel, Switzerland)·2026
Same journal

Present and Future Options for Pharmacotherapy in Cardiovascular Disease: Hemodynamic and Mechanistic Therapeutic Targets.

Medical sciences (Basel, Switzerland)·2026
Same journal

Narrative Review of Digital Twins in the Health Domain: Development, Application, and Evidence Consolidation.

Medical sciences (Basel, Switzerland)·2026
See all related articles
This summary is machine-generated.

A Human-in-the-Loop (HITL) workflow combining AI segmentation maps with surgeon analysis significantly improved glioma detection accuracy using intraoperative Optical Coherence Tomography (OCT). This hybrid approach leverages human expertise to overcome AI limitations, ensuring reliable diagnostics and maintaining clinical responsibility.

Area of Science:

  • Neurosurgery
  • Artificial Intelligence
  • Medical Imaging

Background:

  • Integrating Artificial Intelligence (AI) into clinical workflows presents challenges in decision-making responsibility due to autonomous systems' potential for error.
  • High-stakes fields like surgery require careful consideration of AI integration to balance automation with clinical accountability.
  • This study investigates a Human-in-the-Loop (HITL) workflow using intraoperative Optical Coherence Tomography (OCT) for glioma detection.

Purpose of the Study:

  • To evaluate if integrating Machine Learning (ML)-generated segmentation maps with human contextual analysis enhances diagnostic reliability.
  • To compare the HITL approach against standalone structural, quantitative imaging, and AI models.
  • To determine if the HITL workflow resolves the tension between automation and clinical responsibility in glioma surgery.
Keywords:
gliomahuman-in-the-loopintraoperative imagingmachine learningoptical biopsyoptical coherence tomography

More Related Videos

Thinned-skull Cortical Window Technique for In Vivo Optical Coherence Tomography Imaging
07:28

Thinned-skull Cortical Window Technique for In Vivo Optical Coherence Tomography Imaging

Published on: November 19, 2012

Label-free, High-Resolution 3D Imaging and Machine Learning Analysis of Intestinal Organoids via Low-Coherence Holotomography
10:40

Label-free, High-Resolution 3D Imaging and Machine Learning Analysis of Intestinal Organoids via Low-Coherence Holotomography

Published on: August 12, 2025

Related Experiment Videos

Last Updated: May 28, 2026

Intracranial Implantation with Subsequent 3D In Vivo Bioluminescent Imaging of Murine Gliomas
09:46

Intracranial Implantation with Subsequent 3D In Vivo Bioluminescent Imaging of Murine Gliomas

Published on: November 6, 2011

Thinned-skull Cortical Window Technique for In Vivo Optical Coherence Tomography Imaging
07:28

Thinned-skull Cortical Window Technique for In Vivo Optical Coherence Tomography Imaging

Published on: November 19, 2012

Label-free, High-Resolution 3D Imaging and Machine Learning Analysis of Intestinal Organoids via Low-Coherence Holotomography
10:40

Label-free, High-Resolution 3D Imaging and Machine Learning Analysis of Intestinal Organoids via Low-Coherence Holotomography

Published on: August 12, 2025

Main Methods:

  • Retrospective analysis of 86 intraoperative OCT scans from 27 patients.
  • Blind assessment by five neurosurgeons across structural scans, parametric maps, and ML-generated segmentation maps.
  • Benchmarking HITL performance against standalone SVM and Gemini 3.1 Pro models, measuring accuracy and inter-rater consistency.

Main Results:

  • The HITL approach achieved the highest performance with 94% accuracy and 98% sensitivity, significantly outperforming standalone models.
  • HITL demonstrated superior inter-rater consistency (0.98) compared to quantitative maps (0.68), indicating enhanced interpretability.
  • Surgeons using HITL corrected AI errors in 69% of false positive cases, highlighting the value of human contextual intelligence.

Conclusions:

  • The HITL workflow effectively integrates human contextual intelligence with ML, augmenting diagnostic objectivity and reliability.
  • This paradigm ensures that ultimate diagnostic responsibility remains with human clinicians, enhancing safety in neurosurgery.
  • Publicly available intraoperative OCT brain scan data is provided to promote reproducibility and open science.