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

Dietary milk polar lipids ameliorate hepatic lipid accumulation through coordinated regulation of Wnt-PPARĪ³ signaling and remodeling of the gut microbiota.

Food science of animal resourcesĀ·2026
Same author

Effective contrast-enhanced preprocessing for intracranial artery segmentation in digital subtraction angiography.

Physics in medicine and biologyĀ·2026
Same author

Cerebral arteries segmentation based on projection domain in single exposure computed tomographic angiography.

Medical physicsĀ·2026
Same author

Evaluation of Posture-Dependent Signal Intensity and Contrast Alterations in Low-Field Brain Magnetic Resonance Imaging.

Diagnostics (Basel, Switzerland)Ā·2026
Same author

Comparison of Clinical and Radiological Outcomes Between Suction Aspiration and Combination Methods of Mechanical Thrombectomy in Patients With Acute Cerebral Infarction: The COMPETE Trial.

Journal of Korean medical scienceĀ·2026
Same author

Forensic DNA extraction from decomposed human soft tissues: Optimization using ethanol treatment and surfactant-based lysis conditions.

Forensic science internationalĀ·2026

Related Experiment Video

Updated: Jan 11, 2026

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

729

Modeling of Severity Classification Algorithm Using Abdominal Aortic Aneurysm Computed Tomography Image Segmentation

Sewon Lim1, Hajin Kim1, Kang-Hyeon Seo2

  • 1Department of Health Science, General Graduate School of Gachon University, 191, Hambakmoe-ro, Yeonsu-gu, Incheon 21936, Republic of Korea.

Sensors (Basel, Switzerland)
|November 13, 2025
PubMed
Summary

This study enhances abdominal aortic aneurysm (AAA) segmentation accuracy in CT scans using the median-modified Wiener filter (MMWF) with U-Net. The MMWF significantly improves segmentation and enables precise severity classification.

Keywords:
U-Netabdominal aortic aneurysmmedian modified Wiener filternoise reduction algorithmseverity classification

More Related Videos

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

3.2K
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

3.3K

Related Experiment Videos

Last Updated: Jan 11, 2026

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

729
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

3.2K
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

3.3K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Cardiovascular Imaging

Background:

  • Accurate segmentation of abdominal aortic aneurysms (AAA) in computed tomography (CT) images is crucial for diagnosis and treatment planning.
  • Image noise in CT scans often degrades vessel boundaries, hindering precise segmentation and impacting clinical decisions.
  • U-Net is a popular deep learning model for medical image segmentation, but its performance is sensitive to image noise.

Purpose of the Study:

  • To evaluate the effectiveness of various denoising filters in improving U-Net based segmentation of abdominal aortic aneurysms (AAA).
  • To assess the impact of noise reduction on the accuracy of AAA segmentation and subsequent severity classification.
  • To compare the performance of median-modified Wiener filter (MMWF) against other filters for AAA image analysis.

Main Methods:

  • Poisson-Gaussian noise was artificially introduced into abdominal aortic aneurysm (AAA) CT images.
  • Several denoising filters, including average, median, Wiener, and median-modified Wiener filters (MMWF), were applied to the noisy images.
  • U-Net model performed segmentation on the denoised images, followed by diameter measurement using the Hough circle algorithm for severity classification.

Main Results:

  • The median-modified Wiener filter (MMWF) significantly enhanced segmentation accuracy, improving key metrics like Dice score and Jaccard coefficient.
  • MMWF application led to substantial improvements in Matthews correlation coefficient (31.09%), Dice score (34.25%), Jaccard coefficient (53.99%), and mean surface distance (3.70%) compared to noisy images.
  • Severity classification based on MMWF-processed images achieved 100% sensitivity, precision, and accuracy, outperforming other filtering methods.

Conclusions:

  • The median-modified Wiener filter (MMWF) is highly effective in reducing noise and improving U-Net based segmentation of abdominal aortic aneurysms (AAA) from CT images.
  • Combining MMWF denoising with U-Net segmentation and Hough circle algorithm analysis provides a robust method for accurate AAA severity classification.
  • This approach holds significant potential for enhancing the early diagnosis and treatment planning of vascular diseases like AAA.