Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Cleaning, Sterilization, and Disinfection

Cleaning, Sterilization, and Disinfection

Cleaning, disinfection, and sterilization are the methods that help to break the infection chain and prevent disease.
Cleaning
The cleaning process usually involves using water with detergents or enzymatic cleaner and removing foreign material from objects and surfaces, including organic material such as body fluids or inorganic material like soil. Cleaning is performed before high-level disinfection and sterilization because foreign materials on the cover of the devices interfere with process...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Accelerating scientific discovery with Co-Scientist.

ArXiv·2026

Same author

Evaluating the robustness and readiness of large frontier models in health AI applications.

Nature medicine·2026

Same author

Disparate privacy risks from medical AI.

Nature·2026

Same author

Towards Conversational AI for Disease Management.

Nature·2026

Same author

Pancreatic mu opioid receptors regulate metabolism and ingestive behaviors.

bioRxiv : the preprint server for biology·2026

Same author

Dorsal raphe nucleus enkephalin peptide modulates behavioral preference.

Neuropsychopharmacology : official publication of the American College of Neuropsychopharmacology·2026

Search research articles

Related Experiment Video

Updated: Oct 1, 2025

Protease- and Acid-catalyzed Labeling Workflows Employing 18O-enriched Water

Protease- and Acid-catalyzed Labeling Workflows Employing 18O-enriched Water

Published on: February 20, 2013

Active label cleaning for improved dataset quality under resource constraints.

Mélanie Bernhardt¹, Daniel C Castro¹, Ryutaro Tanno¹

¹Health Intelligence, Microsoft Research Cambridge, Cambridge, CB1 2FB, UK.

Nature Communications

|March 5, 2022

Summary

Active label cleaning prioritizes data samples for re-annotation, improving machine learning model training. This data-driven method corrects noisy labels more effectively than random selection, optimizing expert time for better dataset quality.

More Related Videos

Design and Operation of a Continuous 13C and 15N Labeling Chamber for Uniform or Differential, Metabolic and Structural, Plant Isotope Labeling

Design and Operation of a Continuous 13C and 15N Labeling Chamber for Uniform or Differential, Metabolic and Structural, Plant Isotope Labeling

Published on: January 16, 2014

Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline

Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline

Published on: January 30, 2019

Related Experiment Videos

Last Updated: Oct 1, 2025

Protease- and Acid-catalyzed Labeling Workflows Employing 18O-enriched Water

Protease- and Acid-catalyzed Labeling Workflows Employing 18O-enriched Water

Published on: February 20, 2013

Design and Operation of a Continuous 13C and 15N Labeling Chamber for Uniform or Differential, Metabolic and Structural, Plant Isotope Labeling

Design and Operation of a Continuous 13C and 15N Labeling Chamber for Uniform or Differential, Metabolic and Structural, Plant Isotope Labeling

Published on: January 16, 2014

Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline

Measuring the Shape and Size of Activated Sludge Particles Immobilized in Agar with an Open Source Software Pipeline

Published on: January 30, 2019

Area of Science:

Machine Learning
Data Science
Computer Vision

Background:

Label noise in data annotation negatively impacts machine learning model performance.
Re-annotating large datasets to remove label noise is often infeasible, especially in resource-constrained fields like healthcare.

Purpose of the Study:

To introduce a data-driven approach called "active label cleaning" for prioritizing samples for re-annotation.
To mitigate the detrimental effects of label noise on model training and evaluation.

Main Methods:

Ranking data instances based on estimated label correctness and labeling difficulty.
Developing a simulation framework to evaluate the efficacy of re-labeling strategies.

Main Results:

Cleaning noisy labels effectively reduces their negative impact on model training, evaluation, and selection.
Active label cleaning corrects labels up to 4x more effectively than random selection in realistic scenarios.

Conclusions:

Active label cleaning offers a resource-efficient strategy for improving dataset quality by optimizing the use of expert time.
This approach enhances the reliability and performance of machine learning models trained on imperfect data.