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

Search research articles

Related Experiment Video

Updated: Jun 9, 2025

Ultrasound Cyclo Plasty in Eyes with Glaucoma

Ultrasound Cyclo Plasty in Eyes with Glaucoma

Published on: January 26, 2018

A Computational Framework for Intraoperative Pupil Analysis in Cataract Surgery.

Binh Duong Giap¹, Karthik Srinivasan², Ossama Mahmoud^1,3

¹Kellogg Eye Center, Department of Ophthalmology & Visual Sciences, University of Michigan, 1000 Wall Street, Ann Arbor, Michigan, 48105.

Ophthalmology Science

|October 22, 2024

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

TACTIC: A transfer learning framework to predict drug interactions in emerging pathogens.

Cell reports methods·2026

Same author

Corneal nerve regeneration: treatments and monitoring approaches.

Annals of medicine·2026

Same author

Toward a Random Background for Ligand Optimization.

bioRxiv : the preprint server for biology·2026

Same author

Optimizing outcomes in keratolimbal allograft for limbal stem cell deficiency.

Current opinion in ophthalmology·2026

Same author

Distinguishing Factors for Microbial Keratitis Groups: A Cross-Sectional Survey of US Cornea Specialists.

Cornea·2026

Same author

Hypervariable loop profiling decodes sequence determinants of antibody stability.

Nature structural & molecular biology·2026

This study introduces a computational framework for automated pupil analysis during cataract surgery, accurately predicting the need for pupil expansion devices and improving surgical planning.

Area of Science:

Ophthalmology and Computational Imaging
Artificial Intelligence in Medical Devices

Background:

Pupillary instability is a significant risk factor for cataract surgery complications.
Accurate, real-time assessment of pupil dynamics is crucial for surgical success.
Existing methods for pupil monitoring may lack the precision required for complex surgical phases.

Purpose of the Study:

To develop and validate an innovative computational framework for automated assessment of pupil morphologic changes during cataract surgery.
To enhance the reliability and accuracy of intraoperative pupil analysis.
To provide a tool for predicting the need for pupil expansion devices (PEDs).

Main Methods:

Retrospective analysis of 240 cataract surgery video recordings.
A 3-stage framework involving feature extraction (tensor-based wavelet), deep learning (DL) for anatomy recognition (pupil, limbus, palpebral fissure segmentation), and obstruction (OB) detection/compensation.

Keywords:

Cataract surgery Deep learning Feature extraction, Pupil analysis Segmentation

More Related Videos

Video-oculography in Mice

Video-oculography in Mice

Published on: July 19, 2012

Full-Circle Cauterization of Limbal Vascular Plexus for Surgically Induced Glaucoma in Rodents

Full-Circle Cauterization of Limbal Vascular Plexus for Surgically Induced Glaucoma in Rodents

Published on: February 15, 2022

Related Experiment Videos

Last Updated: Jun 9, 2025

Ultrasound Cyclo Plasty in Eyes with Glaucoma

Ultrasound Cyclo Plasty in Eyes with Glaucoma

Published on: January 26, 2018

Video-oculography in Mice

Video-oculography in Mice

Published on: July 19, 2012

Full-Circle Cauterization of Limbal Vascular Plexus for Surgically Induced Glaucoma in Rodents

Full-Circle Cauterization of Limbal Vascular Plexus for Surgically Induced Glaucoma in Rodents

Published on: February 15, 2022

Validation using a dataset of 5700 intraoperative frames from 190 surgeries; classification models trained to predict PED usage.

Main Results:

The Feature Pyramid Network architecture achieved high segmentation performance (Dice 96.52%), further improved with OB compensation (Dice 96.82%).
A Support Vector Machine classifier accurately predicted surgeon PED usage with 96.67% accuracy and 99.44% AUC.
The framework demonstrated high accuracy compared to human annotations and outperformed isolated DL segmentation models.

Conclusions:

The developed computational framework provides accurate, automated pupil analysis during cataract surgery.
The system offers significant improvements over existing methods and enables clinically valuable predictive analytics.
This technology has the potential to enhance surgical planning and reduce complications associated with pupillary instability.