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

Imaging Studies I: Kidney, Ureter, and Bladder Studies01:28

Imaging Studies I: Kidney, Ureter, and Bladder Studies

Kidney, Ureter, and Bladder (KUB) StudiesKidney, Ureter, and Bladder (KUB) studies are standard diagnostic imaging procedures used to assess the anatomy of the urinary system. They are commonly utilized for patients experiencing abdominal pain or urinary symptoms. By using a simple X-ray of the abdomen, KUB studies can reveal structural and pathological abnormalities within the kidneys, ureters, and bladder. These studies are particularly valuable in diagnosing kidney stones, urinary...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Comprehensive Identification of <i>CPP</i> Gene Family Members in <i>Panax ginseng</i> and Expression Analysis of <i>PgCPP</i> and Key Protopanaxadiol Ginsenoside Biosynthesis Genes in Response to MeJA.

Biology·2026
Same author

The associations between coffee consumption timing patterns and metabolic syndrome: the National Health and Nutrition Examination Survey (NHANES), 2003-2018.

The British journal of nutrition·2026
Same author

Social Support and Hospital Discharge Readiness in CHD Patients: Mediating Roles of Self-Efficacy and Adherence.

Patient preference and adherence·2026
Same author

Nitric acid-modified biochar ameliorates saline-alkali soil and promotes cotton growth by regulating microbiomes and metabolites.

Bioresource technology·2026
Same author

ITCNET: a visual and language pretraining model based on multimodal fusion in predicting the breast cancer subtypes on DCE-MRI.

BMC medical informatics and decision making·2026
Same author

Social Disconnection, Genetic Risk, and the Incidence of Degenerative Valvular Heart Disease: A Population-Based Cohort Study.

Journal of the American Heart Association·2026

Related Experiment Video

Updated: Jun 19, 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

2.7K

A Comparative Analysis of U-Net and Vision Transformer Architectures in Semi-Supervised Prostate Zonal Segmentation.

Guantian Huang1, Bixuan Xia1, Haoming Zhuang1

  • 1College of Medicine and Biological Information Engineering, Northeastern University, Shenyang 110057, China.

Bioengineering (Basel, Switzerland)
|September 27, 2024
PubMed
Summary

Accurate prostate segmentation is vital for disease diagnosis. This study compares semi-supervised methods, finding Uncertainty-Aware Mean Teacher (UAMT) and Interpolation Consistency Training (ICT) effective, especially with U-Net, while Vision Transformer (ViT) needs optimization.

Keywords:
U-Netcomparative analysisprostate zonal segmentationsemi-supervised learningvision transformer

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

2.4K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

377

Related Experiment Videos

Last Updated: Jun 19, 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

2.7K
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

2.4K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

377

Area of Science:

  • Medical imaging
  • Computer vision
  • Machine learning

Background:

  • Precise segmentation of prostate regions is critical for diagnosing and treating prostate diseases.
  • Limited labeled prostate data hinders accurate segmentation, posing a significant challenge in medical imaging applications.

Purpose of the Study:

  • To evaluate and compare the effectiveness of various semi-supervised learning methods for prostate zonal segmentation.
  • To assess the performance of U-Net and Vision Transformer (ViT) architectures in conjunction with semi-supervised techniques for medical image segmentation.

Main Methods:

  • Segmentation of prostate regions was performed using U-Net and Vision Transformer (ViT) architectures.
  • Five semi-supervised learning methods were employed: entropy minimization, cross pseudo-supervision, mean teacher, uncertainty-aware mean teacher (UAMT), and interpolation consistency training (ICT).
  • Performance was benchmarked against the state-of-the-art prostate semi-supervised segmentation network, uncertainty-aware temporal self-learning (UATS).

Main Results:

  • The Uncertainty-Aware Mean Teacher (UAMT) method enhanced prostate segmentation accuracy and stability.
  • Interpolation Consistency Training (ICT) demonstrated robust and stable performance, highlighting U-Net's adaptability for medical image segmentation.
  • Uncertainty-Aware Temporal Self-Learning (UATS) showed significant efficacy with the U-Net backbone, particularly for positive prediction rates.
  • Vision Transformer (ViT) combined with semi-supervised learning requires further refinement for optimal performance.

Conclusions:

  • Semi-supervised learning methods, particularly UAMT and ICT, offer effective solutions for prostate zonal segmentation with limited labeled data.
  • U-Net architecture proves robust for medical image segmentation tasks, while ViT's potential in this domain needs further investigation.
  • This comparative analysis provides valuable insights for advancing prostate segmentation techniques and addressing data scarcity in medical imaging.