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

Radiological Investigation I: X-ray and CT01:30

Radiological Investigation I: X-ray and CT

1.3K
Radiological investigations, including X-rays and computed tomography (CT) scans, are critical for diagnosing and evaluating various medical conditions. These imaging techniques provide valuable insights into the body's internal structures, aiding in the detection of abnormalities, assessment of disease progression, and development of treatment strategies. This article delves into two primary radiological investigations, chest X-rays and CT scans, outlining their purpose, procedures, and...
1.3K
Imaging Studies for Cardiovascular System III: X-Ray01:20

Imaging Studies for Cardiovascular System III: X-Ray

541
The most common cardiovascular diagnostic test is an X-ray. It produces images of the heart, blood vessels, and adjacent structures.
Definition and Purpose
An X-ray, or radiograph, is a non-invasive method that uses ionizing radiation to take images of internal structures. It is mainly used in cardiac imaging to examine the heart, lungs, and major blood vessels, aiming to identify abnormalities in the heart's size, shape, and position, such as heart failure, congenital defects, and vascular...
541

You might also read

Related Articles

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

Sort by
Same author

Evaluation of Large Language Models for Structured Data Extraction From Interstitial Lung Disease Clinical Notes: Comparative Study.

Journal of medical Internet research·2026
Same author

STARC-9: A Large-scale Dataset for Multi-Class Tissue Classification for CRC Histopathology.

Advances in neural information processing systems·2026
Same author

STARC-9: A Large-scale Dataset for Multi-Class Tissue Classification for CRC Histopathology.

ArXiv·2026
Same author

EchoAtlas: A Conversational, Multi-View Vision-Language Foundation Model for Echocardiography Interpretation and Clinical Reasoning.

medRxiv : the preprint server for health sciences·2026
Same author

A generalizable deep learning system for cardiac MRI.

Nature biomedical engineering·2026
Same author

On the origins and variation of nucleotide skews of archaeal genomes.

Frontiers in microbiology·2026

Related Experiment Video

Updated: May 6, 2026

Investigation into Deep Breathing through Measurement of Ventilatory Parameters and Observation of Breathing Patterns
08:34

Investigation into Deep Breathing through Measurement of Ventilatory Parameters and Observation of Breathing Patterns

Published on: September 16, 2019

11.3K

From Detection to Mitigation: Addressing Bias in Deep Learning Models for Chest X-Ray Diagnosis.

Clemence Mottez1, Louisa Fay2, Maya Varma3

  • 1Center for Artificial Intelligence in Medicine and Imaging, Stanford University, CA, USA, cmottez@stanford.edu.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing
|February 27, 2026
PubMed
Summary

This study introduces a bias detection and mitigation framework for deep learning on chest X-rays. Combining CNN with eXtreme Gradient Boosting (XGBoost) improves fairness across demographic groups while maintaining diagnostic accuracy.

More Related Videos

Author Spotlight: Development of a Minimally Invasive Large-Animal Model for Reliable and Reproducible Cardiovascular Research
06:51

Author Spotlight: Development of a Minimally Invasive Large-Animal Model for Reliable and Reproducible Cardiovascular Research

Published on: October 20, 2023

1.8K
A Novel Dual-Modal Deep Learning Approach for Real-Time Removal of Hepatic Fluorescence in Indocyanine Green-Guided Laparoscopic Cholecystectomy
09:21

A Novel Dual-Modal Deep Learning Approach for Real-Time Removal of Hepatic Fluorescence in Indocyanine Green-Guided Laparoscopic Cholecystectomy

Published on: April 17, 2026

44

Related Experiment Videos

Last Updated: May 6, 2026

Investigation into Deep Breathing through Measurement of Ventilatory Parameters and Observation of Breathing Patterns
08:34

Investigation into Deep Breathing through Measurement of Ventilatory Parameters and Observation of Breathing Patterns

Published on: September 16, 2019

11.3K
Author Spotlight: Development of a Minimally Invasive Large-Animal Model for Reliable and Reproducible Cardiovascular Research
06:51

Author Spotlight: Development of a Minimally Invasive Large-Animal Model for Reliable and Reproducible Cardiovascular Research

Published on: October 20, 2023

1.8K
A Novel Dual-Modal Deep Learning Approach for Real-Time Removal of Hepatic Fluorescence in Indocyanine Green-Guided Laparoscopic Cholecystectomy
09:21

A Novel Dual-Modal Deep Learning Approach for Real-Time Removal of Hepatic Fluorescence in Indocyanine Green-Guided Laparoscopic Cholecystectomy

Published on: April 17, 2026

44

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Health Equity

Background:

  • Deep learning models enhance chest X-ray diagnostics but risk exacerbating healthcare disparities due to performance variations across demographic groups.
  • Existing bias mitigation techniques can be computationally intensive and may not always yield optimal results.

Purpose of the Study:

  • To develop and evaluate a comprehensive framework for detecting and mitigating sex, age, and race-based disparities in chest X-ray diagnostic AI.
  • To assess the effectiveness of a CNN-XGBoost pipeline in improving fairness and maintaining predictive performance.

Main Methods:

  • Extended a CNN-XGBoost pipeline for multi-label classification on chest X-rays across four medical conditions.
  • Evaluated model-agnostic generalizability using DenseNet-121 and ResNet-50 backbones.
  • Compared the lightweight adapter training approach with traditional bias mitigation methods like adversarial training, reweighting, data augmentation, and active learning.

Main Results:

  • Replacing the CNN's final layer with an eXtreme Gradient Boosting classifier improved subgroup fairness while maintaining or enhancing overall predictive performance.
  • The proposed method demonstrated competitive or superior bias reduction compared to traditional techniques at a lower computational cost.
  • Combining eXtreme Gradient Boosting retraining with active learning achieved the most significant bias reduction across all demographic subgroups on CheXpert and MIMIC datasets.

Conclusions:

  • The CNN-XGBoost approach offers a practical and computationally efficient solution for reducing bias in deep learning models for chest X-ray analysis.
  • This framework promotes equitable deployment of AI in clinical radiology, ensuring improved diagnostic accuracy for all patient populations.
  • The model-agnostic nature and strong performance highlight its potential for broad applicability in medical imaging AI.