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 Experiment Video

Updated: Jun 21, 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

2.7K

Automatic Segmentation of Type A Aortic Dissection on Computed Tomography Images Using Deep Learning Approach.

Xiaoya Guo1, Tianshu Liu1, Yi Yang1

  • 1School of Science, Nanjing University of Posts and Telecommunications, Nanjing 210023, China.

Diagnostics (Basel, Switzerland)
|July 13, 2024
PubMed
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

NLRC3 in septic immunosuppression: Variation in expression and mechanisms of mediating immune cell dysfunction (Review).

Experimental and therapeutic medicine·2026
Same author

Genomic analysis of oesophageal carcinoma (EC) identifies recurrent mutations in histone methyltransferases as a distinctive subset.

Oncogene·2026
Same author

Chinese consensus on first-line precision therapy for advanced gastric cancer.

Innovation (Cambridge (Mass.))·2026
Same author

Type 2 diabetes genetics in 125,000 admixed adults from Mexico City.

medRxiv : the preprint server for health sciences·2026
Same author

Reduced mechanical strength correlates with decreased elastin content in aortic intima-media tissue: association with dissection in human ascending aortas.

Medical & biological engineering & computing·2026
Same author

A clinico-radiological model integrating baseline CT-derived body composition to predict prognosis in immunotherapy-treated metastatic colorectal cancer.

European journal of radiology·2026

3D nnU-Net accurately segments Type A aortic dissection (TAAD) on CT scans, improving diagnosis and treatment planning. This AI approach offers precise quantification of aortic features, aiding clinical decisions.

Area of Science:

  • Medical imaging analysis
  • Artificial intelligence in healthcare
  • Cardiovascular disease research

Background:

  • Type A aortic dissection (TAAD) is a critical condition involving the ascending aorta.
  • Accurate segmentation of TAAD is vital for clinical assessment and treatment planning.
  • Current segmentation methods may lack precision for complex aortic pathologies.

Purpose of the Study:

  • To apply and evaluate the nnU-Net framework for segmenting TAAD in contrast-enhanced CT images.
  • To quantify morphological features of TAAD using both 2D and 3D nnU-Net architectures.
  • To compare the performance of 2D and 3D nnU-Net models in TAAD segmentation and feature quantification.

Main Methods:

  • Utilized 2D and 3D nnU-Net architectures for segmenting true lumen (TL), false lumen (FL), and intimal flap.
Keywords:
computed tomographydeep learningimage segmentationnnU-Nettype A aortic dissection

More Related Videos

Three-Dimensional Printing of a Complex Aortic Anomaly
03:40

Three-Dimensional Printing of a Complex Aortic Anomaly

Published on: November 1, 2018

6.7K
Novel and Innovative Hybrid Technique for Type A Aortic Dissection
06:26

Novel and Innovative Hybrid Technique for Type A Aortic Dissection

Published on: March 28, 2025

245

Related Experiment Videos

Last Updated: Jun 21, 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

2.7K
Three-Dimensional Printing of a Complex Aortic Anomaly
03:40

Three-Dimensional Printing of a Complex Aortic Anomaly

Published on: November 1, 2018

6.7K
Novel and Innovative Hybrid Technique for Type A Aortic Dissection
06:26

Novel and Innovative Hybrid Technique for Type A Aortic Dissection

Published on: March 28, 2025

245
  • Employed Dice and cross-entropy loss functions for segmentation.
  • Performed four-fold cross-validation on CT datasets from 24 TAAD patients.
  • Evaluated performance using accuracy, precision, recall, IoU, DSC, and Hausdorff distance.

    • Main Results:

    • 3D nnU-Net demonstrated superior performance in TAAD CT segmentation, achieving up to 99.9% accuracy for TL and FL.
    • The Dice Similarity Coefficient (DSC) for TL and FL reached 88.42% and 87.10% with 3D nnU-Net.
    • 3D nnU-Net yielded lower relative errors in FL area quantification (3.89-6.80%) compared to 2D nnU-Net (4.35-9.48%).

    Conclusions:

    • nnU-Net architectures show significant potential for automated TAAD segmentation and quantification.
    • This AI-driven approach can assist in rapid diagnosis and surgical planning for TAAD.
    • The methodology supports subsequent biomechanical simulations of the aorta.