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

Positron Emission Tomography

Positron Emission Tomography

Positron emission tomography (PET) is a medical imaging technique involving radiopharmaceuticals — substances that emit short-lived radiation. Although the first PET scanner was introduced in 1961, it took 15 more years before radiopharmaceuticals were combined with the technique and revolutionized its potential.
One of the main requirements of a PET scan is a positron-emitting radioisotope, which is produced in a cyclotron and then attached to a substance used by the part of the body...

You might also read

Related Articles

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

Sort by

Same author

Unleashing the potential of open-set noisy samples against label noise for medical image classification.

Medical image analysis·2025

Same author

Reproductive outcomes of women with moderate to severe intrauterine adhesions after transcervical resection of adhesion: A systematic review and meta-analysis.

Medicine·2023

Same author

A convolutional neural network with pixel-wise sparse graph reasoning for COVID-19 lesion segmentation in CT images.

Computers in biology and medicine·2023

Same author

Long noncoding RNAs regulate intrauterine adhesion and cervical cancer development and progression.

Seminars in cell & developmental biology·2023

Same author

BiT-MAC: Mortality prediction by bidirectional time and multi-feature attention coupled network on multivariate irregular time series.

Computers in biology and medicine·2023

Same author

A nomogram prediction of citrate reaction during mononuclear cell collection in solid tumor patients.

Journal of clinical apheresis·2023

Same journal

Wavelet-inspired diffusion model with near-field constraint for real-time echocardiography dehazing.

Medical image analysis·2026

Same journal

Co-assistant networks by pathology foundation model and convolutional neural network for gigapixel whole slide image analysis.

Medical image analysis·2026

Same journal

MBAS2024: A large-scale benchmark for multi-class bi-atrial segmentation in multi-center contrast-enhanced MRIs.

Medical image analysis·2026

Same journal

Respiratory motion augmentation for personalized super-resolution (RMApSR) of 3D cine MR images in MRI-guided radiotherapy.

Medical image analysis·2026

Same journal

Biom3d, a modular framework to host and develop 3D segmentation methods.

Medical image analysis·2026

Same journal

Embracing intra-class heterogeneity for semi-supervised medical image segmentation: From diversity to precision.

Medical image analysis·2026

See all related articles

Search research articles

Related Experiment Video

Updated: May 3, 2026

Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench

Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench

Published on: August 23, 2017

Modeling annotator preference and stochastic annotation error for medical image segmentation.

Zehui Liao¹, Shishuai Hu¹, Yutong Xie²

¹National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, School of Computer Science and Engineering, Northwestern Polytechnical University, Xi'an 710072, China.

Medical Image Analysis

|December 9, 2023

Summary

This summary is machine-generated.

Manual annotation of medical images introduces bias. A new Preference-involved Annotation Distribution Learning (PADL) framework models annotator preferences and errors to improve medical image segmentation accuracy.

Keywords:

Human preference Medical image segmentation Multiple annotators Stochastic annotation errors

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

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Related Experiment Videos

Last Updated: May 3, 2026

Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench

Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench

Published on: August 23, 2017

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

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Area of Science:

Artificial Intelligence
Medical Imaging
Computer Vision

Background:

Manual annotation of medical images is subjective and prone to bias.
Deep learning models can inherit or amplify these annotator-related biases.
Existing methods struggle to address bias stemming from annotator preferences.

Purpose of the Study:

To introduce a novel framework, Preference-involved Annotation Distribution Learning (PADL), for medical image segmentation.
To address annotator-related biases by modeling individual preferences and stochastic errors.
To generate both a consensus (meta) segmentation and annotator-specific segmentations.

Main Methods:

The PADL framework incorporates a Stochastic Error Modeling (SEM) module.
Human Preference Modeling (HPM) modules are used to capture individual annotator characteristics.
The framework models annotator preferences and stochastic errors to produce diverse segmentations.

Main Results:

The PADL framework was evaluated on two medical image benchmarks with diverse modalities.
Promising performance was achieved across five distinct medical image segmentation tasks.
The framework successfully generated meta and annotator-specific segmentations, addressing bias.

Conclusions:

The PADL framework offers a robust solution for mitigating annotator bias in medical image segmentation.
Modeling annotator preferences and errors leads to more reliable and accurate segmentation outcomes.
This approach enhances the trustworthiness of deep learning models in medical image analysis.