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

Interlaboratory performance testing on EPIC v2.0 CNS tumor profiling demonstrates high reproducibility of tumor classification but reveals the need for harmonized copy number variation reporting.

Brain pathology (Zurich, Switzerland)·2026
Same author

Efficacy of blended digital and face-to-face psychotherapy compared to enhanced psychotherapy for patients with Somatic Symptom Disorder (iSOMA+): study protocol for a multicenter randomized controlled pragmatic trial.

Trials·2026
Same author

Acceptance Drivers of Digital Technologies in Geriatric Long-Term Care Nursing: Systematic Evidence Synthesis.

Studies in health technology and informatics·2026
Same author

Pricing Simulator for AI-Based Diagnostic Decision Support.

Studies in health technology and informatics·2026
Same author

Advancing and Establishing Digitalization: Insights into Digitalization Practices in Elderly Care.

Studies in health technology and informatics·2026
Same author

Cross-Technology Factors Influencing Acceptance of Digital Technologies in Long-Term Care: First Findings of a Modified Delphi Study.

Studies in health technology and informatics·2026

Related Experiment Video

Updated: Jun 15, 2025

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

2.4K

Comparing nnU-Net and deepflash2 for Histopathological Tumor Segmentation.

Daniel Hieber1,2,3, Nico Haisch4, Gregor Grambow4

  • 1DigiHealth Institute, Neu-Ulm University of Applied Sciences.

Studies in Health Technology and Informatics
|August 23, 2024
PubMed
Summary

Automated Machine Learning (AutoML) frameworks like nnU-Net and deepflash2 show promise for histopathological tumor segmentation. These tools enable complex medical image analysis on consumer hardware, potentially aiding clinical applications.

Keywords:
AutoMLHistopathologyMachine LearningSegmentationdeepflash2nnU-Net

More Related Videos

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.6K
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

2.7K

Related Experiment Videos

Last Updated: Jun 15, 2025

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

2.4K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.6K
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

2.7K

Area of Science:

  • Medical Image Analysis
  • Computational Pathology
  • Artificial Intelligence in Medicine

Background:

  • Machine Learning (ML) has become more accessible, with Automated ML (AutoML) frameworks rivaling specialized models.
  • AutoML excels in complex tasks, including histopathological tumor segmentation, which traditionally requires extensive expert knowledge.

Purpose of the Study:

  • To compare the performance of two leading AutoML frameworks, nnU-Net and deepflash2, for histopathological image segmentation.
  • To evaluate the feasibility of using these frameworks on consumer hardware for clinical settings.

Main Methods:

  • Utilized a dataset of 103 whole-slide images from 56 glioblastoma patients.
  • Trained and evaluated nnU-Net and deepflash2 on a notebook with consumer-grade hardware.
  • Focused on the challenging task of segmenting tumors with heterogeneous transitions from healthy tissue.

Main Results:

  • Both nnU-Net and deepflash2 demonstrated capability in histopathological image segmentation.
  • The study assessed the practical application of AutoML on accessible hardware, moving beyond high-performance research labs.

Conclusions:

  • AutoML frameworks show potential for simplifying complex histopathological image analysis.
  • The findings suggest that AutoML tools may be suitable for clinical deployment, even without specialized high-performance computing infrastructure.