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

[Intelligence level and structure in school age children with fetal growth restriction].

Zhongguo dang dai er ke za zhi = Chinese journal of contemporary pediatrics·2009
Same author

Uncoupling the D1-N-methyl-D-aspartate (NMDA) receptor complex promotes NMDA-dependent long-term potentiation and working memory.

Biological psychiatry·2009
Same author

A phospho-directed macroporous alumina-silica nanoreactor with multi-functions.

ACS nano·2009
Same author

Subintimal angioplasty for below-the-ankle arterial occlusions in diabetic patients with chronic critical limb ischemia.

Journal of endovascular therapy : an official journal of the International Society of Endovascular Specialists·2009
Same author

Natural killer/T cell lymphoma initiating with pleural effusion: the significance of MICM combined techniques for the diagnosis.

Zhongguo shi yan xue ye xue za zhi·2009
Same author

[Advance of study on animal models of lymphoma].

Zhongguo shi yan xue ye xue za zhi·2009

Related Experiment Video

Updated: Sep 28, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.0K

Kidney Tumor Segmentation Based on FR2PAttU-Net Model.

Peng Sun1, Zengnan Mo2, Fangrong Hu1

  • 1School of Electronic Engineering and Automation, Guilin University of Electronic Technology, Guilin, China.

Frontiers in Oncology
|April 4, 2022
PubMed
Summary

This study introduces FR2PAttU-Net, a deep learning model for segmenting kidney tumors in CT images. The model achieves high accuracy, aiding doctors in efficient diagnosis and resource management.

Keywords:
CTFR2PAttU-NetKiTS19data augmentationkidney tumor segmentation

More Related Videos

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
09:16

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

7.0K
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

3.0K

Related Experiment Videos

Last Updated: Sep 28, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.0K
Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
09:16

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

7.0K
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

3.0K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Oncology

Background:

  • Kidney tumor incidence is rising, posing challenges for accurate segmentation in CT scans.
  • Current segmentation methods struggle with unclear or incidental small kidney tumors.
  • Efficient and accurate tumor segmentation is crucial for timely diagnosis and treatment planning.

Purpose of the Study:

  • To develop an advanced deep learning model for precise kidney tumor segmentation in CT images.
  • To improve the efficiency and accuracy of kidney tumor detection, especially for challenging cases.
  • To provide a tool that assists medical professionals in processing large volumes of medical imaging data.

Main Methods:

  • Developed FR2PAttU-Net, a modified U-Net architecture incorporating R2Att network and parallel convolutions.
  • Implemented fuzzy set enhancement algorithm to improve image feature prominence for better model adaptation.
  • Utilized the KiTS19 dataset, employing data augmentation techniques for small sample balancing.

Main Results:

  • Achieved a kidney Dice score of 0.948 and a tumor Dice score of 0.911.
  • Obtained a composite score of 0.930, demonstrating effective segmentation performance.
  • The model showed robust performance across various convolutional depths and configurations.

Conclusions:

  • FR2PAttU-Net significantly improves kidney tumor segmentation accuracy in CT images.
  • The model's design enhances adaptability to varying tumor scales and image features.
  • This deep learning approach offers a valuable tool for efficient and accurate kidney tumor diagnosis.