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

Hybrid bioprinting of hierarchical vascular networks at capillary-scale resolution.

Nature chemical engineering·2026
Same author

Genome evolution and transposable element expansion reveal host-associated genomic features in Cladosporium cucumerinum.

Communications biology·2026
Same author

Thin-Film Engineering of Artificial Interphases for Lithium Batteries.

Small (Weinheim an der Bergstrasse, Germany)·2026
Same author

From probiotic depletion to inflammatory cascade: multi-omics reveals the temporal progression of sleep deprivation-induced gut-liver axis disruption in mice.

Frontiers in microbiology·2026
Same author

Epicardial adipose tissue signatures in Asian coronary artery disease: Insights from cardiac CT.

American journal of preventive cardiology·2026
Same author

Consolidative therapy for PSMA-avid lesions after 3 cycles of apalutamide plus androgen deprivation in metastatic hormone-sensitive prostate cancer: A prospective phase 2 single-arm trial.

European journal of nuclear medicine and molecular imaging·2026

Related Experiment Video

Updated: Mar 21, 2026

Hybrid µCT-FMT imaging and image analysis
13:45

Hybrid µCT-FMT imaging and image analysis

Published on: June 4, 2015

13.7K

3D-SIFT-Flow for atlas-based CT liver image segmentation.

Yan Xu1, Chenchao Xu2, Xiao Kuang2

  • 1State Key Laboratory of Software Development Environment and Key Laboratory of Biomechanics and Mechanobiology of Ministry of Education, Beihang University, Beijing 100191, China and Research Institute of Beihang University in Shenzhen and Microsoft Research, Beijing 100080, China.

Medical Physics
|May 6, 2016
PubMed
Summary
This summary is machine-generated.

A new 3D registration algorithm, 3D-SIFT-Flow, accurately segments livers in CT scans. This method improves upon existing techniques, showing robust performance even with significant tissue deformation and blurry boundaries.

More Related Videos

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

43.8K
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

3.7K

Related Experiment Videos

Last Updated: Mar 21, 2026

Hybrid µCT-FMT imaging and image analysis
13:45

Hybrid µCT-FMT imaging and image analysis

Published on: June 4, 2015

13.7K
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

43.8K
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

3.7K

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Image Registration

Background:

  • Multi-atlas based liver segmentation in CT images is crucial for diagnosis and treatment planning.
  • Accurate registration is essential for effective atlas-based segmentation, especially when dealing with anatomical variations.

Purpose of the Study:

  • To introduce a novel 3D registration algorithm, 3D-scale invariant feature transform (SIFT)-Flow, for enhanced multi-atlas liver segmentation.
  • To evaluate the performance of 3D-SIFT-Flow against existing state-of-the-art registration and segmentation methods.

Main Methods:

  • Developed a registration method leveraging dense correspondence via Scale-Invariant Feature Transform (SIFT) features.
  • Computed dense SIFT features for source and target images, defining an objective function for correspondence.
  • Extended a 2D nonparametric label transfer method to 3D for fusing registered 3D atlases.

Main Results:

  • 3D-SIFT-Flow demonstrated superior performance in matching anatomical structures with significant variation and deformation compared to ELASTIX and ANTS.
  • Achieved a Dice overlap ratio of 96.27% ± 0.96% for liver segmentation on the MICCAI 2007 Grand Challenge dataset.
  • Outperformed previous state-of-the-art multi-atlas fusion methods, including joint label fusion.

Conclusions:

  • 3D-SIFT-Flow is a robust algorithm for segmenting livers from CT images, effectively handling large tissue deformation and blurry boundaries.
  • 3D label transfer proved effective and efficient in enhancing registration accuracy for multi-atlas segmentation.