Jove
Visualize
Contact Us

Related Concept Videos

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
  1. Home
  3. Optimal Strategies For Modeling Anatomy In A Hybrid Intelligence Framework For Auto-segmentation Of Organs.
  1. Home
  3. Optimal Strategies For Modeling Anatomy In A Hybrid Intelligence Framework For Auto-segmentation Of Organs.

Related Experiment Video

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

385

Optimal strategies for modeling anatomy in a hybrid intelligence framework for auto-segmentation of organs.

You Hao1, Jayaram K Udupa1, Yubing Tong1

  • 1Medical Image Processing Group, 602 Goddard building, 3710 Hamilton Walk, Department of Radiology, University of Pennsylvania, Philadelphia, PA 19104, United States.

Proceedings of Spie--The International Society for Optical Engineering
|July 3, 2024

View abstract on PubMed

Summary
This summary is machine-generated.

This study introduces hybrid intelligence (HI) for medical image segmentation, combining natural intelligence (NI) with artificial intelligence (AI). The enhanced HI system significantly improves computational efficiency for radiation therapy planning while maintaining high accuracy in thorax organ segmentation.

Keywords:
anatomic modelscomputed tomographydeep learninghybrid intelligenceorgan segmentationradiation therapy planning

More Related Videos

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures
09:10

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Published on: August 5, 2021

1.7K
Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions
06:18

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

1.0K

Related Experiment Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

385
Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures
09:10

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Published on: August 5, 2021

1.7K
Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions
06:18

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

1.0K

Area of Science:

  • Medical Image Analysis
  • Artificial Intelligence
  • Radiotherapy Planning

Background:

  • Organ segmentation is crucial in medical imaging, with numerous methods developed over six decades.
  • Medical images contain inherent anatomical information that can enhance AI segmentation.
  • Previous hybrid intelligence (HI) systems combined natural intelligence (NI) and artificial intelligence (AI) for robust medical image segmentation.

Purpose of the Study:

  • To introduce computational efficiency improvements in the NI component of a hybrid intelligence system for medical image segmentation.
  • To enhance the integration of the NI component with the AI (deep learning) component of the HI system.
  • To validate the improved HI system's performance in clinical studies for radiation therapy planning.

Main Methods:

  • Developed advanced modeling strategies for the natural intelligence (NI) component to improve computational efficiency.
  • Integrated the enhanced NI component with the deep learning (AI) portion of the hybrid intelligence system.
  • Applied the refined HI system to auto-segmentation tasks in radiation therapy planning using multi-center clinical data.

Main Results:

  • Achieved a 9-40 fold computational improvement in auto-segmentation for radiation therapy planning.
  • Demonstrated state-of-the-art accuracy in segmenting 11 organs within the thorax region.
  • Validated performance across clinical studies from 4 different radiation therapy centers.

Conclusions:

  • The enhanced hybrid intelligence system offers substantial computational gains for medical image segmentation in radiation therapy planning.
  • The refined NI modeling ensures efficient and effective integration with deep learning components.
  • The system maintains high accuracy, proving its clinical utility and robustness in multi-center settings.