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

Tumor Neovasculature-Targeted APRPG-PEG-PDLLA/MPEG-PDLLA Mixed Micelle Loading Combretastatin A-4 for Breast Cancer Therapy.

ACS biomaterials science & engineering·2021
Same author

Accelerated Bone Regeneration by MOF Modified Multifunctional Membranes through Enhancement of Osteogenic and Angiogenic Performance.

Advanced healthcare materials·2021
Same author

Robust 4d-5f Bimetal-Organic Framework for Efficient Removal of Trace SO<sub>2</sub> from SO<sub>2</sub>/CO<sub>2</sub> and SO<sub>2</sub>/CO<sub>2</sub>/N<sub>2</sub> Mixtures.

Inorganic chemistry·2021
Same author

Explore the difference between the single-chamber and dual-chamber microbial electrosynthesis for biogas production performance.

Bioelectrochemistry (Amsterdam, Netherlands)·2021
Same author

Efficient assembly of nanopore reads via highly accurate and intact error correction.

Nature communications·2021
Same author

Characterization and phylogenetic analysis of the complete mitochondrial genome of <i>Conidiobolus</i> sp. (Entomophthorales: Ancylistaceae).

Mitochondrial DNA. Part B, Resources·2020

Related Experiment Video

Updated: Aug 18, 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

6.9K

A generalizable and robust deep learning algorithm for mitosis detection in multicenter breast histopathological

Xiyue Wang1, Jun Zhang2, Sen Yang2

  • 1College of Biomedical Engineering, Sichuan University, Chengdu 610065, China; College of Computer Science, Sichuan University, Chengdu 610065, China.

Medical Image Analysis
|December 8, 2022
PubMed
Summary

A new algorithm, FMDet, accurately detects mitotic cells in breast cancer biopsies, improving prognostication. This robust mitosis detection method shows strong generalizability across diverse datasets, aiding clinical decisions.

Keywords:
Deep learningDomain shiftFeature extractionHistopathologyMitosis detection

More Related Videos

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning
12:06

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

4.1K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.9K

Related Experiment Videos

Last Updated: Aug 18, 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

6.9K
Analyzing Mitochondrial Morphology Through Simulation Supervised Learning
12:06

Analyzing Mitochondrial Morphology Through Simulation Supervised Learning

Published on: March 3, 2023

4.1K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.9K

Area of Science:

  • Digital pathology
  • Computational oncology
  • Medical image analysis

Background:

  • Accurate mitosis counting in breast cancer biopsies is crucial for patient prognostication and treatment planning.
  • Existing mitosis detection algorithms struggle with generalizability and reproducibility across different image datasets.
  • Challenges include complex cell morphology and high similarity between mitotic and non-mitotic cells.

Purpose of the Study:

  • To develop a generalizable and robust mitosis detection algorithm for breast histopathological images.
  • To improve the accuracy and reliability of automated mitosis counting in clinical settings.
  • To address the limitations of current algorithms in terms of cross-domain performance and validation.

Main Methods:

  • The FMDet algorithm converts object detection to a semantic segmentation task for refined feature extraction.
  • A novel feature extractor with channel-wise multi-scale attention was developed for fully convolutional networks.
  • Fourier-based data augmentation was employed to reduce domain discrepancies by manipulating low-frequency spectral information.

Main Results:

  • FMDet achieved first place in the MICCAI MIDOG 2021 challenge.
  • The algorithm demonstrated state-of-the-art performance on four independent external validation datasets.
  • External validation confirmed the algorithm's robustness and superior performance compared to existing methods.

Conclusions:

  • The FMDet algorithm offers a generalizable and robust solution for mitosis detection in breast cancer histopathology.
  • Its strong performance suggests potential for deployment as a clinical decision support tool.
  • The developed methods contribute to advancing automated analysis in digital pathology.