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: Jan 9, 2026

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

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

Published on: November 30, 2022

MDA-TransUNet: A Deep Learning-Based Automatic Segmentation Method for Cervical Cancer Brachytherapy.

Dezheng Cao^1,2,3,4, Jianhua Jin⁵, Jihua Han⁶

¹Department of Radiotherapy, The Second People's Hospital of Changzhou, the Third Affiliated Hospital of Nanjing Medical University, Changzhou, China.

Technology in Cancer Research & Treatment

|December 5, 2025

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

Synthetic CT-enabled weekly adaptive radiotherapy for nasopharyngeal carcinoma: Optimizing plan adaptation triggers through volumetric-dosimetric monitoring.

Journal of applied clinical medical physics·2026

Same author

Mechanical Microenvironment-Dependent Tumor Growth Intervention: Recent Advances and Translational Outlook.

Technology in cancer research & treatment·2026

Same author

Dual Sensitization Enables Synergistic Photodynamic Therapy and Radiotherapy for Breast Cancer.

Research (Washington, D.C.)·2026

Same author

EPIDSeg-Net: A Multi-Modal Fusion Framework Based on DRR Guidance in Radiotherapy is Used for Precise Segmentation of MV-EPID Lung Targets.

Technology in cancer research & treatment·2026

Same author

Unraveling spatiotemporal dynamics in transdiagnosis subtypes of major depressive disorder and bipolar disorder: insights from co-activation patterns and treatment response.

Molecular psychiatry·2025

Same author

Polydopamine/polyvinyl alcohol/graphene oxide transition layer for enhancing adhesive performance of HA coating on C<sub>f</sub>/C composites prepared by hydrothermal electrodeposition/hydrothermal treatment.

Journal of materials science. Materials in medicine·2025

Same journal

Bridging Global Attention and Local Hierarchies: A Robust Hybrid Ensemble Framework With Multi-Perspective Explainability for Automated HER2-IHC Scoring.

Technology in cancer research & treatment·2026

Same journal

Research on Predicting the Efficacy of Immunotherapy for Non-small Cell Lung Cancer Based on CT Radiomics and Peripheral Blood Inflammatory Markers.

Technology in cancer research & treatment·2026

Same journal

Survival Prediction in Patients With Epidermal Growth Factor Receptor-Mutated Non-small Cell Lung Cancer With Bone Metastases Receiving Icotinib Therapy: A Retrospective Observational Study.

Technology in cancer research & treatment·2026

Same journal

Proteomics in Acute Myeloid Leukemia: Current Applications in Precision Medicine and Targeted Immunotherapy.

Technology in cancer research & treatment·2026

Same journal

EML4-ALK in Non-small Cell Lung Cancer: Molecular Mechanisms and Targeted Therapies.

Technology in cancer research & treatment·2026

Same journal

Developing and Validating a Risk Model for Severe Bone Marrow Suppression in Esophageal Cancer Treated with Radiotherapy or Chemoradiotherapy: A Retrospective Cohort Study.

Technology in cancer research & treatment·2026

See all related articles

This summary is machine-generated.

A new MDA-TransUNet model accurately segments organs at risk and high-risk clinical target volumes for cervical cancer brachytherapy. This AI-driven approach improves speed and precision, crucial for effective radiation treatment planning.

Area of Science:

Medical Imaging
Artificial Intelligence
Oncology

Background:

Accurate segmentation of high-risk clinical target volume (HR-CTV) and organs at risk (OARs) is vital for effective cervical cancer brachytherapy.
Current manual delineation methods are time-consuming and prone to errors due to organ displacement and steep dose gradients.

Purpose of the Study:

To introduce and evaluate MDA-TransUnet, a novel CNN-Transformer hybrid model for rapid and precise segmentation of HR-CTV and OARs in cervical cancer.
To assess the segmentation accuracy and dosimetric impact of the proposed model compared to existing methods.

Main Methods:

MDA-TransUnet was applied to CT images from 122 cervical cancer brachytherapy patients across three centers.
Segmentation performance was evaluated using Dice Similarity Coefficient (DSC), Hausdorff Distance (HD95), and Average Surface Distance (ASD).

Keywords:

auto-segmentation cervical cancer deep learning high-dose-rate brachytherapy image-guided

More Related Videos

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

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

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Jan 9, 2026

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

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

Published on: November 30, 2022

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

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

Published on: December 15, 2023

Dosimetric differences were analyzed using paired t-tests on key metrics like D2cc and D90%.

Main Results:

MDA-TransUnet demonstrated superior segmentation performance, achieving high DSC values for bladder (94.54%), small bowel (88.90%), and HR-CTV (82.35%).
No significant dosimetric differences were observed between MDA-TransUnet and reference segmentations.
OAR dosimetric differences (D2cc) averaged <12%, and HR-CTV differences (Dmean, D90%) averaged <8% and <11%, respectively.

Conclusions:

MDA-TransUnet offers a superior and robust solution for segmenting OARs and HR-CTV in cervical cancer brachytherapy.
The model's fast and accurate segmentation capabilities can optimize treatment planning and potentially improve patient outcomes.
The multi-center validation confirms the model's generalizability and reliability in clinical settings.