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

Glucans from <i>Lentinus edodes</i> Inhibit Myeloid-Derived Suppressor Cell-Induced Regulatory T Cells via the TLR4-TAK1-JNK Signaling Pathway to Scavenge Reactive Oxygen Species.

Journal of agricultural and food chemistry·2026
Same author

Bioactive Seed Coating with Chitosan-Salicylic Acid Networks Activates Folate Metabolism and Nutritional Fortification in Wheat Seedlings.

Journal of agricultural and food chemistry·2026
Same author

Trichoderma modulates Pseudomonas metabolism: Co-inoculation enhances phosphorus acquisition of Pyrus betulifolia in calcareous soil.

Microbiological research·2026
Same author

Modelling the structural evolution, electronic structures and optical properties of Sc<sub>6</sub>Se<sub>n</sub><sup>0/-</sup> (n = 1-12) clusters.

Communications chemistry·2026
Same author

Bidirectional association between edentulism and sarcopenia in Chinese middle-aged and older adults: a nationally representative longitudinal cohort study.

Clinical oral investigations·2026
Same author

AN AUTOMATED CHEMILUMINESCENCE IMMUNOASSAY FOR DETECTION OF GIARDIA DUODENALIS ANTIGENS FROM CANINE SPECIMENS.

The Journal of parasitology·2026

Related Experiment Video

Updated: Jul 3, 2026

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

Generative morphodynamic forecasting enables robust zero-shot volumetric medical segmentation.

Duwei Dai1, Caixia Dong2, Guowei Dai3

  • 1Department of Gastroenterology, The Second Affiliated Hospital of Xi'an Jiaotong University, Xi'an 710004, Shaanxi, China; Institute of Medical Artificial Intelligence, The Second Affiliated Hospital of Xi'an Jiaotong University, Xi'an 710004, Shaanxi, China.

Medical Image Analysis
|July 1, 2026
PubMed
Summary
This summary is machine-generated.

This study introduces a new framework for 3D medical image segmentation, improving accuracy in complex cases by forecasting anatomical changes. It enhances interactive segmentation with better topological consistency and efficiency.

Keywords:
3D medical image segmentationGenerative visual priorsNeural stochastic differentialUncertainty estimation

More Related Videos

Pioneering Patient-Specific Approaches for Precision Surgery Using Imaging and Virtual Reality
06:18

Pioneering Patient-Specific Approaches for Precision Surgery Using Imaging and Virtual Reality

Published on: April 5, 2024

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

Related Experiment Videos

Last Updated: Jul 3, 2026

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

Pioneering Patient-Specific Approaches for Precision Surgery Using Imaging and Virtual Reality
06:18

Pioneering Patient-Specific Approaches for Precision Surgery Using Imaging and Virtual Reality

Published on: April 5, 2024

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

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computer Vision

Background:

  • Video foundation models show promise for interactive volumetric medical image segmentation.
  • These models struggle with patient-specific topological changes, leading to memory drift and segmentation errors.
  • Existing reactive memory architectures and geometric prompts offer limited guidance for complex anatomical structures.

Purpose of the Study:

  • To develop a generative anticipatory framework to improve 3D medical image segmentation accuracy and robustness.
  • To mitigate memory drift and segmentation errors in video foundation models when applied to complex 3D medical volumes.
  • To enhance interactive segmentation efficiency and topological consistency under challenging imaging conditions.

Main Methods:

  • Introduced a generative anticipatory framework augmenting reactive tracking with morphological forecasting.
  • Combined large language models for semantic reasoning with neural stochastic differential equations for latent dynamics.
  • Proposed an uncertainty-guided dual-stream memory architecture integrating forecasted priors with visual evidence.
  • Formulated human-in-the-loop interactive corrections via Bayesian state resetting.

Main Results:

  • The framework demonstrated improved topological consistency under challenging imaging conditions.
  • Achieved strong training-free generalization across diverse clinical datasets.
  • Showed improved robustness to morphodynamic variation and higher interactive efficiency compared to existing methods.
  • The uncertainty-aware approach effectively balanced visual observations and forecasted anatomical trajectories.

Conclusions:

  • The proposed generative anticipatory framework offers a promising direction for promptable volumetric medical segmentation.
  • The uncertainty-guided memory architecture enhances robustness and accuracy in segmenting complex 3D medical images.
  • This approach improves interactive segmentation efficiency and topological consistency, particularly in cases with significant anatomical changes.