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

Adjuvant visible incoherent polarised phototherapy in chronic skin defects: a single-arm prospective observational cohort study.

Lasers in medical science·2026
Same author

Image-guided cryoablation of endophytic renal tumors: technical considerations and current clinical outcomes-a narrative review.

Diagnostic and interventional radiology (Ankara, Turkey)·2026
Same author

Segmentation and Multimodal Characterization of Metal Particles in the Human Hippocampus Using Discrete Segmentation Algorithms and Correlation Spectral Analysis.

Molecules (Basel, Switzerland)·2026
Same author

Traditional and deep learning-oriented medical and biological image analysis.

Bratislavske lekarske listy·2023
Same author

Reinitiation and Subsequent Discontinuation of Angiotensin-Converting Enzyme Inhibitors and Angiotensin Receptor Blockers among New and Prevalent Users Aged 65 Years or More with Peripheral Arterial Disease.

Biomedicines·2023
Same author

Gender Differences in Non-Persistence with Angiotensin-Converting Enzyme Inhibitors and Angiotensin Receptor Blockers among Older Hypertensive Patients with Peripheral Arterial Disease.

Biomedicines·2022

Related Experiment Video

Updated: Feb 28, 2026

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions
06:18

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

1.7K

3D Medical Image Segmentation with 3D Modelling.

Mária Ždímalová1, Kristína Boratková1, Viliam Sitár2

  • 1Department of Mathematics and Descriptive Geometry, Faculty of Civil Engineering, Slovak University of Technology in Bratislava, 810 05 Bratislava, Slovakia.

Bioengineering (Basel, Switzerland)
|February 27, 2026
PubMed
Summary
This summary is machine-generated.

This study presents an enhanced Graphcut algorithm for 3D medical image segmentation, improving tumor boundary accuracy in breast and brain scans. The method offers a data-efficient alternative to deep learning for oncology diagnostics.

Keywords:
3D segmentationDICOM dataGraphcutimage processingtumor volumetry

More Related Videos

Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery
14:15

Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery

Published on: January 11, 2020

7.7K
Combining Augmented Reality and 3D Printing to Display Patient Models on a Smartphone
09:26

Combining Augmented Reality and 3D Printing to Display Patient Models on a Smartphone

Published on: January 2, 2020

19.1K

Related Experiment Videos

Last Updated: Feb 28, 2026

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions
06:18

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

1.7K
Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery
14:15

Multicolor 3D Printing of Complex Intracranial Tumors in Neurosurgery

Published on: January 11, 2020

7.7K
Combining Augmented Reality and 3D Printing to Display Patient Models on a Smartphone
09:26

Combining Augmented Reality and 3D Printing to Display Patient Models on a Smartphone

Published on: January 2, 2020

19.1K

Area of Science:

  • Medical Image Processing
  • Computational Radiology
  • Oncology Diagnostics

Background:

  • Accurate segmentation of 3D radiological images is crucial for tumor isolation in CT/MRI, enabling precise visualization, volumetry, and treatment monitoring.
  • Volumetric analysis aids adaptive therapies by detecting subtle tumor changes, surpassing standard criteria.
  • Existing methods struggle with heterogeneous tissue intensities, impacting boundary accuracy.

Purpose of the Study:

  • To develop an enhanced, interactive Graphcut algorithm for 3D DICOM segmentation.
  • To improve boundary accuracy and 3D modeling of breast and brain tumors.
  • To address challenges posed by heterogeneous tissue intensities in medical imaging.

Main Methods:

  • Augmented standard Graphcut with a clustering mechanism (k=2-5 clusters) for refined boundary detection.
  • Processed DICOM datasets into 3D volumes using metadata; utilized user-defined seeds and bounding boxes.
  • Implemented in Python 3.13 using PyMaxflow and pydicom for graph optimization and data transformation.

Main Results:

  • Achieved high Dice Similarity Coefficients (DSC): 0.92 ± 0.07 for brain tumors, 0.90 ± 0.05 for breast tumors.
  • Demonstrated reduced noise sensitivity and improved boundary definition compared to standard techniques.
  • Showcased comparable performance to deep learning benchmarks without extensive pre-training, with a 7.5% reduction in boundary errors.

Conclusions:

  • Presented an efficient and precise 3D tumor segmentation tool for diagnostics and treatment planning.
  • Demonstrated a robust, data-efficient alternative to deep learning, especially valuable when large annotated datasets are unavailable.
  • The enhanced Graphcut algorithm offers significant advantages for clinical settings requiring accurate tumor analysis.