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 journal

Correction: Komatsu et al. Three-Dimensional Visualization and Detection of the Pulmonary Venous-Left Atrium Connection Using Artificial Intelligence in Fetal Cardiac Ultrasound Screening. <i>Bioengineering</i> 2026, <i>13</i>, 100.

Bioengineering (Basel, Switzerland)·2026
Same journal

Comparison of CO<sub>2</sub> Laser and Microdebrider in the Surgical Treatment of Pediatric Recurrent Respiratory Papillomatosis: A Retrospective Analysis.

Bioengineering (Basel, Switzerland)·2026
Same journal

Toward More Translational Tumor Models: Breast dECM-Based 3D Systems Capture Native Microenvironmental Cues.

Bioengineering (Basel, Switzerland)·2026
Same journal

Postural Stability Changes During the 4 Phases of the Half Squat: Kinematics Profile of the Center of Pressure and Center of Mass in High-Performance Weightlifters-A Pilot Study.

Bioengineering (Basel, Switzerland)·2026
Same journal

Definite Implant Position as Novel Readout for Effectiveness of Ridge Preservation Indicates to Beneficial Effect of Combined Treatment with Platelet-Rich Fibrin (PRF) and Xenogenic Biomaterial in Bone Regeneration.

Bioengineering (Basel, Switzerland)·2026
Same journal

Trueness and Precision of Intraoral Scanners for 3D-Printed Orthodontic Models with Attachments: An In Vitro Comparative Study.

Bioengineering (Basel, Switzerland)·2026

Related Experiment Video

Updated: Jul 10, 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

Pixel Diffuser: Practical Interactive Medical Image Segmentation without Ground Truth.

Mingeon Ju1, Jaewoo Yang1, Jaeyoung Lee1

  • 1Major in Bio Artificial Intelligence, Department of Applied Artificial Intelligence, Hanyang University at Ansan, Ansan 15588, Republic of Korea.

Bioengineering (Basel, Switzerland)
|November 25, 2023
PubMed
Summary

PixelDiffuser is a novel interactive medical image segmentation tool that requires no ground truth data. This method uses a few clicks to achieve high-quality segmentation, reducing manual effort and training costs.

Keywords:
CT segmentationautoencoderinteractive medical segmentationiterative segmentationreconstruction noise

More Related Videos

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

24.6K
Medical-grade Sterilizable Target for Fluid-immersed Fetoscope Optical Distortion Calibration
07:03

Medical-grade Sterilizable Target for Fluid-immersed Fetoscope Optical Distortion Calibration

Published on: February 23, 2017

7.7K

Related Experiment Videos

Last Updated: Jul 10, 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
From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

24.6K
Medical-grade Sterilizable Target for Fluid-immersed Fetoscope Optical Distortion Calibration
07:03

Medical-grade Sterilizable Target for Fluid-immersed Fetoscope Optical Distortion Calibration

Published on: February 23, 2017

7.7K

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Artificial Intelligence

Background:

  • Deep learning models require extensive labeled data for medical image segmentation, which is costly and time-consuming to acquire.
  • Existing interactive methods still demand significant ground truth data and user interactions for precise segmentation.

Purpose of the Study:

  • To introduce PixelDiffuser, an interactive medical image segmentation method that eliminates the need for segmentation ground truth data.
  • To enable high-quality segmentation with minimal user input (a few clicks).

Main Methods:

  • PixelDiffuser utilizes a VGG19-based autoencoder to perform segmentation.
  • The method initiates segmentation from a user-selected seed point and gradually expands the segmented region.
  • Segmentation is achieved by introducing and propagating image distortions through the autoencoder's encoding-decoding process.

Main Results:

  • PixelDiffuser achieves competitive performance in medical image segmentation with fewer than five clicks.
  • The method demonstrates effectiveness on the BTCV and CHAOS datasets, which include CT and MRI scans.
  • The model requires minimal memory and no additional training, offering efficiency.

Conclusions:

  • PixelDiffuser presents an efficient and effective solution for interactive medical image segmentation.
  • The method significantly reduces the reliance on labeled data and user interaction time.
  • This approach offers a promising alternative for clinical applications requiring rapid and accurate segmentation.