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

A single nucleotide polymorphism in LRP2 is associated with susceptibility to Alzheimer's disease in the Chinese population.

Clinica chimica acta; international journal of clinical chemistryĀ·2010
Same author

Three-component assembly and divergent ring-expansion cascades of functionalized 2-iminooxetanes.

Angewandte Chemie (International ed. in English)Ā·2010
Same author

Prokaryotic expression and potential application of the truncated PCV-2 capsid protein.

Virologica SinicaĀ·2010
Same author

Serum and urinary cell-free MiR-146a and MiR-155 in patients with systemic lupus erythematosus.

The Journal of rheumatologyĀ·2010
Same author

Peptide dendrimers as efficient and biocompatible gene delivery vectors: Synthesis and in vitro characterization.

Journal of controlled release : official journal of the Controlled Release SocietyĀ·2010
Same author

The amplification and evolution of orthologous 22-kDa Ī±-prolamin tandemly arrayed genes in coix, sorghum and maize genomes.

Plant molecular biologyĀ·2010

Related Experiment Video

Updated: Jul 4, 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

2.8K

A modified U-Net convolutional neural network for segmenting periprostatic adipose tissue based on contour feature

Gang Wang1, Jinyue Hu2, Yu Zhang3

  • 1Department of Urology, Affiliated Haikou Hospital of Xiangya Medical College, Central South University, Haikou, 570208, Hainan Province, China.

Heliyon
|February 6, 2024
PubMed
Summary

This study introduces a U-Net deep learning model for accurate segmentation of periprostatic adipose tissue (PPAT) using MRI T2W images. The model demonstrates superior performance in identifying PPAT contours, outperforming other networks.

Keywords:
Contour featureDeep learningPeriprostatic adipose tissueProstate cancerU-shaped fully convolutional neural network (U-Net)

More Related Videos

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

405
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

2.5K

Related Experiment Videos

Last Updated: Jul 4, 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

2.8K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

405
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

2.5K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Oncology

Background:

  • Accurate segmentation of periprostatic adipose tissue (PPAT) is crucial for prostate cancer staging and treatment planning.
  • Current segmentation methods often lack precision and automation, necessitating advanced computational approaches.

Purpose of the Study:

  • To develop and evaluate a novel U-Net deep learning model for automated and accurate segmentation of PPAT from MRI T2W images.
  • To improve the identification of PPAT contours by incorporating peripheral contour measures and a modified U-Net architecture.

Main Methods:

  • A modified U-Net convolutional neural network was trained using MRI T2W images and their gradient images, focusing on peripheral contour control points.
  • A weighted loss function was employed to enhance convergence speed and detection accuracy.
  • Convex curve fitting was utilized to obtain the final PPAT contour based on detected control points.

Main Results:

  • The proposed U-Net model achieved Dice similarity coefficient (DSC), Hausdorff distance (HD), and intersection over union (IoU) of 70.1%, 27 mm, and 56.1% on cropped 270x270-pixel images.
  • The model successfully predicted complete PPAT contours, outperforming FCN, U-Net, and SegNet.
  • Reduced image resolution led to decreased accuracy, with 256x256-pixel images yielding DSC of 68.7%, HD of 26.7 mm, and IoU of 54.1%.

Conclusions:

  • The U-Net model based on peripheral contour features effectively identifies and segments PPAT.
  • Cropped 270x270-pixel images are optimal for this U-Net model, with lower resolutions diminishing accuracy.
  • This automated method provides a foundation for rapid and accurate PPAT image analysis.