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

You might also read

Related Articles

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

Sort by

Same author

Evaluation of nucleic acid-based matrix-assisted laser desorption/ionization time-of-flight mass spectrometry for rapid identification of <i>Mycobacterium tuberculosis</i> and drug resistance in patients with retreatment tuberculosis.

Frontiers in microbiology·2026

Same author

Cold-Driven Thermoelectric Patch for Postoperative Tumor Control.

ACS nano·2026

Same author

A QuantiFERON<sup>®</sup>-TB Gold Plus-Based Model for Predicting Latent Tuberculosis Infection in Patients with Diabetes.

Infection and drug resistance·2026

Same author

Identification of serum biomarkers in acute aortic dissection using tissue-informed metabolomics methods.

Scientific reports·2026

Same author

Integrated Gut-Brain Axis Response to Freezing and Recovery in Freeze-Tolerant Fish, <i>Perccottus glenii</i>.

Animals : an open access journal from MDPI·2026

Same author

Fallen Leaves to Their Roots: genome-wide evidence for two independent colonizations of the Taiwan island by Mogera moles.

Molecular phylogenetics and evolution·2026

Search research articles

Related Experiment Video

Updated: Jan 16, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

MPVT+: a noise-robust training framework for automatic liver tumor segmentation with noisy labels.

Xuan Cheng¹, Haoxiang Tian², Jiajun Zhou²

¹University of Electronic Science and Technology of China, Chengdu, China.

Frontiers in Medicine

|September 26, 2025

Summary

This summary is machine-generated.

MPVT+ enhances liver tumor segmentation by robustly handling noisy labels in medical images. This deep learning framework improves accuracy, reducing reliance on perfect data for automated tumor delineation.

Keywords:

annotation deep learning liver tumor segmentation noisy label semi-supervised learning

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Published on: June 3, 2022

Related Experiment Videos

Last Updated: Jan 16, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Industrialized, Artificial Intelligence-guided Laser Microdissection for Microscaled Proteomic Analysis of the Tumor Microenvironment

Published on: June 3, 2022

Area of Science:

Medical Imaging
Artificial Intelligence
Oncology

Background:

Liver cancer is a major global health concern, necessitating accurate tumor segmentation for effective patient management.
Manual segmentation of hepatic tumors is time-consuming and prone to inter-observer variability.
Deep neural networks (DNNs) offer automated segmentation but are hindered by the need for large, high-quality labeled datasets, often compromised by noisy labels.

Purpose of the Study:

To develop a noise-robust training framework for automated liver tumor segmentation.
To improve the accuracy and reliability of deep learning models when trained on imperfect medical datasets.
To reduce the dependency on meticulously labeled data in medical image analysis.

Main Methods:

Introduction of MPVT+, a novel framework integrating a pixel-wise noise-adaptation module with a multi-stage perturbation and variable-teacher (MPVT) consistency strategy.
The noise adaptor estimates label corruption probabilities and adjusts supervision weights.
MPVT employs an ensemble of stochastic teacher models with increasing perturbations to prevent overfitting to noisy labels.

Main Results:

MPVT+ significantly outperformed baseline methods on 739 liver-tumor CT datasets, achieving a Dice Similarity Coefficient (DSC) of 80.3% compared to a noise-free U-Net baseline (75.1%).
The framework demonstrated consistent superiority across various metrics including DSC, JSC, SVD, and VOE.
Validation on a substantial dataset confirms the effectiveness of the proposed noise-robust approach.

Conclusions:

Principled noise modeling and consistency training, as implemented in MPVT+, effectively leverage imperfect medical datasets.
This approach mitigates the need for perfectly curated datasets, advancing automated liver tumor segmentation towards clinical readiness.
MPVT+ represents a significant step in making AI-driven medical image analysis more practical and accessible.