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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

3D lithography of diamond thermal emitters for microscale emissivity control.

Nature communications·2026
Same author

Label tree semantic losses for rich multi-class medical image segmentation.

Frontiers in artificial intelligence·2026
Same author

Lower cranial nerve responses after laryngeal stimulation in posterior fossa surgery: a study of medullary complex motor functions.

Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology·2026
Same author

Ultra-broadband ultraviolet detection and imaging enabled by copper-halide inside transparent glass.

Nature communications·2026
Same author

Consensus on the use of artificial intelligence in the management and measurement of vestibular schwannomas: A protocol for a modified delphi consensus.

Neuroradiology·2026
Same author

Streamlining stereo-differentiable rendering for marker-free real-time tracking of surgical robots.

International journal of computer assisted radiology and surgery·2026

Related Experiment Video

Updated: Jun 10, 2025

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
07:46

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

658

Deep Reinforcement Learning Based System for Intraoperative Hyperspectral Video Autofocusing.

Charlie Budd1, Jianrong Qiu2, Oscar MacCormac1,3

  • 1King's College London, Biomedical Engineering & Imaging Science, London.

Medical Image Computing and Computer-Assisted Intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
|October 15, 2024
PubMed
Summary

This study introduces a novel autofocusing system for hyperspectral imaging (HSI) to improve intraoperative tissue differentiation. The new deep reinforcement learning method significantly enhances focus accuracy and usability in surgical settings.

Keywords:
AutofocusComputer Assisted InterventionDeep Reinforcement LearningHyperspectral Imaging

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

2.7K
Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals
00:07

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals

Published on: August 22, 2019

8.0K

Related Experiment Videos

Last Updated: Jun 10, 2025

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
07:46

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

658
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

2.7K
Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals
00:07

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals

Published on: August 22, 2019

8.0K

Area of Science:

  • Medical Imaging
  • Optical Engineering
  • Artificial Intelligence

Background:

  • Hyperspectral imaging (HSI) offers detailed spectral information crucial for intraoperative tissue differentiation.
  • Current handheld HSI systems face hardware limitations, including shallow focal depth, hindering surgical application.
  • Integrating advanced optical and AI solutions is needed to overcome these limitations.

Purpose of the Study:

  • To develop and evaluate a novel autofocusing system for video hyperspectral imaging exoscopes.
  • To improve the usability and precision of HSI for real-time intraoperative applications.
  • To address the limited focal depth issue in current HSI hardware.

Main Methods:

  • Integration of a focus-tunable liquid lens into a video HSI exoscope.
  • Development of deep reinforcement learning-based autofocusing algorithms.
  • Creation of a robotic focal-time scan dataset for realistic performance evaluation.
  • Benchmarking against traditional autofocusing methods and conducting blinded usability trials with neurosurgeons.

Main Results:

  • The novel deep reinforcement learning autofocus algorithm demonstrated significantly lower mean absolute focal error (0.070 ±.098) compared to traditional methods (0.146 ±.148, p < 0.05).
  • Blinded usability trials indicated a strong preference for the novel autofocus approach among neurosurgeons.
  • The system showed improved performance and usability for intraoperative HSI.

Conclusions:

  • The developed focus-tunable liquid lens and deep reinforcement learning autofocus system effectively overcomes focal depth limitations in HSI.
  • This enhanced system offers a desirable solution for improving intraoperative tissue differentiation using HSI.
  • The findings support the integration of advanced HSI technologies in surgical environments.