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

From Self-Esteem and Academic Performance to Anxiety: A Cross-Lagged Study of Chinese First-Generation College Students.

Behavioral sciences (Basel, Switzerland)·2026
Same author

A Bibliometric Analysis of Global Research Hotspots and Progress on Microbial Extracellular Polymeric Substances in Bioremediation.

Microorganisms·2026
Same author

Numerical and experimental assessment of implant-induced thermal risks during electrosurgical procedures.

Biomedical physics & engineering express·2026
Same author

Comparative effectiveness of different inhaler technique education modalities on clinical outcomes in patients with asthma and chronic obstructive pulmonary disease: a protocol for a systematic review and network meta-analysis of randomised controlled trials.

BMJ open·2026
Same author

Prevalence of insufficient outdoor activity and caregiver-related correlates among school-aged children in Beijing, China: a cross-sectional analysis.

Frontiers in public health·2026
Same author

Ion sequential therapy aligned with pathological changes enhances cardiac function after myocardial infarction.

Cell reports. Medicine·2026
Same journal

Facial iPPG heatmap patterns based on period-aware autoencoder show association with carotid atherosclerosis towards non-contact hemodynamic assessment.

Computer methods and programs in biomedicine·2026
Same journal

Explainable machine learning models predict liver fibrosis risk and outcome in the general population: Development and multi-cohort external validation.

Computer methods and programs in biomedicine·2026
Same journal

Evaluation of surrogate endpoints for survival outcomes using the surrogate package in R.

Computer methods and programs in biomedicine·2026
Same journal

Relative spectral and frication-based descriptors as numerical indicators of place of articulation shifts in fricatives produced by Polish children.

Computer methods and programs in biomedicine·2026
Same journal

Leaflet resection improves valve expansion and hemodynamic performance in redo TAVI with balloon- and self-expanding transcatheter heart valve configurations.

Computer methods and programs in biomedicine·2026
Same journal

Spectral super-resolution for Parkinson's voice via representation-level methods under mixed-reality acquisition.

Computer methods and programs in biomedicine·2026
See all related articles

Related Experiment Video

Updated: May 29, 2025

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.3K

SeLa-MIL: Developing an instance-level classifier via weakly-supervised self-training for whole slide image

Yingfan Ma1, Mingzhi Yuan1, Ao Shen1

  • 1Digital Medical Research Center, School of Basic Medical Sciences, Fudan University, Shanghai, 200032, China; Shanghai Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention, Fudan University, Shanghai, 200032, China.

Computer Methods and Programs in Biomedicine
|February 6, 2025
PubMed
Summary
This summary is machine-generated.

SeLa-MIL enhances pathology image classification by using semi-supervised learning to leverage labeled and unlabeled data, improving accuracy for difficult cancer diagnoses. This method excels at identifying critical positive instances within whole slide images (WSIs).

Keywords:
Computational pathologyMultiple instance learningWeak supervisionWhole slide images classification

More Related Videos

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
Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

471

Related Experiment Videos

Last Updated: May 29, 2025

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.3K
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
Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

471

Area of Science:

  • Computational pathology
  • Machine learning for medical imaging
  • Artificial intelligence in cancer diagnosis

Background:

  • Whole Slide Image (WSI) classification is vital for cancer diagnosis but often uses multiple instance learning (MIL) due to annotation costs.
  • Existing MIL methods struggle with suboptimal outcomes by focusing on bag-level classification and neglecting instance-level data.
  • Accurate classification of challenging positive instances near decision boundaries remains a significant hurdle.

Purpose of the Study:

  • To introduce SeLa-MIL, a novel semi-supervised learning approach for WSI classification.
  • To improve both instance-level and bag-level classification accuracy by utilizing labeled and unlabeled instances.
  • To specifically enhance the identification of hard positive instances in pathology images.

Main Methods:

  • Reformulated MIL as a semi-supervised instance classification task to integrate labeled and unlabeled data.
  • Developed a weakly supervised self-training framework using a constrained optimization problem to handle all-negative labeled instances.
  • Employed global and local constraints on pseudo-labels derived from positive WSI information for improved hard positive instance learning.

Main Results:

  • SeLa-MIL demonstrated superior performance over existing methods on synthetic, MIL benchmark, and WSI datasets.
  • Achieved substantial improvements in both instance-level and bag-level classification accuracy.
  • Effectiveness was further validated by visualizations highlighting relevant pathology regions for cancer diagnosis.

Conclusions:

  • SeLa-MIL successfully addresses MIL challenges in WSI classification through semi-supervised learning, weakly supervised learning, and pseudo-labeling.
  • The approach enhances classification accuracy and generalization capabilities across diverse datasets.
  • Presents a valuable tool for advancing pathology image analysis and computer-aided diagnosis.