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

TCRBinder: Unified pre-trained language model with paired-chain synergy for predicting T-cell receptor binding specificity.

PLoS computational biology·2026
Same author

Adaptive feature unlearning for trustworthy medical imaging privacy.

Medical image analysis·2026
Same author

Deep learning-based Breast Imaging Reporting and Data System classification and establishment of diagnostic model in breast cancer diagnosis with automated breast ultrasound.

Quantitative imaging in medicine and surgery·2026
Same author

Anatomy-Guided Spatiotemporal Affinity Learning for Unsupervised Domain Adaptation in Echocardiography Segmentation.

IEEE journal of biomedical and health informatics·2026
Same author

Performance Evaluation of SmartBrain: A Wearable PET System for Human Brain Imaging.

Journal of nuclear medicine : official publication, Society of Nuclear Medicine·2026
Same author

CT-based AI system for quantitative and integrated management of acute respiratory distress syndrome in critical care.

NPJ digital medicine·2026

Related Experiment Video

Updated: Jul 16, 2025

Labeling of Breast Cancer Patient-derived Xenografts with Traceable Reporters for Tumor Growth and Metastasis Studies
09:53

Labeling of Breast Cancer Patient-derived Xenografts with Traceable Reporters for Tumor Growth and Metastasis Studies

Published on: November 30, 2016

12.2K

Ambiguity-aware breast tumor cellularity estimation via self-ensemble label distribution learning.

Xiangyu Li1, Xinjie Liang1, Gongning Luo1

  • 1School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China.

Medical Image Analysis
|September 14, 2023
PubMed
Summary

This study introduces a self-ensemble label distribution learning (SLDL) framework for accurate tumor cellularity (TC) estimation. SLDL effectively handles inter-rater ambiguity and improves TC value recovery, achieving state-of-the-art results.

Keywords:
Breast cancerCVAELabel ambiguityLabel distribution learningNeoadjuvant therapyTumor cellularity

More Related Videos

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
10:39

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

2.4K
Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
09:53

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Published on: August 16, 2020

7.3K

Related Experiment Videos

Last Updated: Jul 16, 2025

Labeling of Breast Cancer Patient-derived Xenografts with Traceable Reporters for Tumor Growth and Metastasis Studies
09:53

Labeling of Breast Cancer Patient-derived Xenografts with Traceable Reporters for Tumor Growth and Metastasis Studies

Published on: November 30, 2016

12.2K
A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
10:39

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

2.4K
Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
09:53

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Published on: August 16, 2020

7.3K

Area of Science:

  • Computational pathology
  • Medical image analysis
  • Machine learning for oncology

Background:

  • Accurate tumor cellularity (TC) estimation is crucial for cancer diagnosis and treatment planning.
  • Existing label distribution learning (LDL) methods face challenges in exploiting inter-rater ambiguity and generating appropriate label distributions.
  • Addressing label ambiguity in breast tumor cellularity estimation requires novel approaches.

Purpose of the Study:

  • To develop a novel self-ensemble label distribution learning (SLDL) framework for improved tumor cellularity estimation.
  • To overcome limitations of existing LDL methods in handling inter-rater ambiguity and label distribution generation.
  • To achieve state-of-the-art performance in breast tumor cellularity estimation.

Main Methods:

  • Proposed an expertness-aware conditional VAE for single-rater modeling and an attention-based multi-rater fusion strategy for inter-rater ambiguity exploitation.
  • Developed a template-based label distribution generation method tailored for TC estimation using annotation priors.
  • Introduced a novel restricted distribution loss combining unimodal and regression losses for enhanced TC value estimation.
  • Leveraged both inter-rater and intra-rater variability to address label ambiguity in breast tumor cellularity estimation.

Main Results:

  • The proposed SLDL framework demonstrated significant improvements in TC value estimation.
  • SLDL effectively addressed challenges related to inter-rater ambiguity and label distribution generation.
  • Experimental results on the BreastPathQ dataset showed SLDL outperforming existing methods by a large margin.
  • Achieved new state-of-the-art results for the tumor cellularity estimation task.

Conclusions:

  • The SLDL framework offers a robust and effective solution for tumor cellularity estimation.
  • The novel methods for handling label ambiguity and distribution generation contribute to improved accuracy.
  • SLDL sets a new benchmark for performance in breast tumor cellularity estimation tasks.