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

Empathy fatigue in ecosystem conservation: The awareness decline among concerns over Japan's nuclear wastewater discharge.

Marine pollution bulletin·2026
Same author

Clinical analysis of 21 cases of chlorfenapyr poisoning.

Clinical toxicology (Philadelphia, Pa.)·2026
Same author

AhNPR4B Interacts with AhPR2-Like and May Contribute to Disease Resistance and Cold Tolerance in Peanut.

Plants (Basel, Switzerland)·2026
Same author

Identification of end-stage renal disease-associated loci in X chromosome: an X chromosome-wide association study.

MedScience·2026
Same author

Clinical Practice of Haemoadsorption Combined with Haemodialysis in Maintenance Haemodialysis Patients with Kidney Failure: Chinese Expert Consensus.

Blood purification·2026
Same author

Seasonal Drought Reduces Carbon Sequestration in Coastal Wetlands.

Global change biology·2026

Related Experiment Video

Updated: May 20, 2025

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

2.6K

A deep learning model based on Mamba for automatic segmentation in cervical cancer brachytherapy.

Lele Zang1, Jing Liu1, Huiqi Zhang2

  • 1Department of Gynecology, Clinical Oncology School of Fujian Medical University, Fujian Cancer Hospital, Fuzhou, 350011, Fujian, China.

Scientific Reports
|March 25, 2025
PubMed
Summary

A new Mamba-based model (AM-UNet) accurately segments cervical cancer brachytherapy targets (HRCTV) and organs at risk (OARs). This AI tool shows potential for improving treatment planning and clinical workflows.

Keywords:
Auto-segmentationBrachytherapyCervical cancerComputedDeep learning

More Related Videos

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.2K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.4K

Related Experiment Videos

Last Updated: May 20, 2025

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

2.6K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.2K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.4K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Oncology
  • Radiotherapy Physics

Background:

  • Cervical cancer brachytherapy requires precise delineation of clinical target volumes (CTV) and organs at risk (OARs).
  • Manual contouring is time-consuming and subject to inter-observer variability.
  • Automated segmentation models can potentially improve efficiency and consistency.

Purpose of the Study:

  • To develop and evaluate an automatic segmentation model, AM-UNet based on the Mamba framework.
  • To compare the performance of AM-UNet against other deep learning models for cervical cancer brachytherapy segmentation.
  • To assess the clinical applicability and dosimetric impact of the proposed model.

Main Methods:

  • Development of AM-UNet using the Mamba framework for segmenting high-risk clinical target volume (HRCTV) and OARs.
  • Training and validation on 694 CT scans from 179 cervical cancer patients.
  • Performance evaluation using Dice Similarity Coefficient (DSC), 95% Hausdorff Distance (HD95), and dose-volume index (DVI) compared to UNet, DeepLab V3, UNETR, and nnU-Net.

Main Results:

  • AM-UNet achieved high mean DSCs: 0.862 (HRCTV), 0.937 (bladder), 0.823 (rectum), and 0.725 (sigmoid).
  • Subjective evaluation indicated 93.07% of AM-UNet HRCTV segmentations were clinically acceptable or required minor adjustments.
  • Dosimetric differences between AM-UNet and manual contours were within 1%.

Conclusions:

  • The AM-UNet model demonstrates robust performance for automated segmentation in cervical cancer brachytherapy.
  • Its accuracy and efficiency suggest significant potential for enhancing clinical workflows and treatment planning.
  • This AI-driven approach could lead to more consistent and precise radiotherapy delivery.