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

Fabrication of high-performance 3D Porous SnO<sub>2</sub>-Sb electrode modified with TiO<sub>2</sub>-NTs and investigation on its electrocatalytic phenol degradation behavior.

Environmental technology·2026
Same author

A review of the impact of circadian rhythm on motor function in stroke recovery patients.

Frontiers in neurology·2026
Same author

Pangenome-based structural variant imputation enables large-scale genotype-phenotype studies in dairy cattle.

Nature communications·2026
Same author

An Adaptive Multi-Scale Manifold Embedding Preprocessing Framework for High-Dimensional Data Visualization.

IEEE transactions on visualization and computer graphics·2026
Same author

Interpretable scRNA-seq Analysis with Intelligent Gene Selection.

Applied biochemistry and biotechnology·2026
Same author

Survival prediction in stage II/III rectal cancer: Role of immune-inflammatory biomarkers post neoadjuvant chemoradiotherapy.

Oncology letters·2026

Related Experiment Video

Updated: Jan 12, 2026

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
02:09

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

979

Application of multi-scale feature extraction and explainable machine learning in chest x-ray position evaluation

Chaowei Ma1,2, Rui Peng1, Bingjie Li2

  • 1Department of Radiology, Xijing Hospital, Fourth Military Medical University, Xi'an, China.

European Radiology
|November 5, 2025
PubMed
Summary

This study introduces a novel AI fusion network for accurate chest X-ray positioning assessment. The Random Forest Fusion Network (RFFN) enhances radiographer accuracy by providing interpretable feedback on patient positioning quality.

Keywords:
Chest X-rayMachine learningPositionQuality controlRandom forest

More Related Videos

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

43.4K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

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

Published on: October 10, 2018

8.6K

Related Experiment Videos

Last Updated: Jan 12, 2026

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
02:09

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

979
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

43.4K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

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

Published on: October 10, 2018

8.6K

Area of Science:

  • Artificial Intelligence in Medical Imaging
  • Deep Learning for Radiography Analysis
  • Machine Learning in Healthcare

Background:

  • Accurate patient positioning is crucial for diagnostic quality in chest radiography.
  • Current methods for assessing positioning can be subjective and time-consuming.
  • There is a need for automated, quantitative, and interpretable tools to evaluate positioning.

Purpose of the Study:

  • To develop and validate a novel deep learning-machine learning fusion network for quantitative and interpretable assessment of chest X-ray positioning.
  • To analyze critical factors influencing patient positioning layout in chest radiographs.
  • To compare the performance of the proposed fusion network against traditional classification models.

Main Methods:

  • Retrospective analysis of 3300 chest radiographs.
  • Development of an automated segmentation model (U-net++) for measuring five positioning indicators.
  • Validation of three classification models: Random Forest Fusion Network (RFFN), Threshold Classification (TC), and Multivariate Logistic Regression (MLR), using AUC, accuracy, sensitivity, and specificity.
  • Utilized SHAP (Shapley Additive Explanations) for model interpretability and evaluated measurement consistency between the Automated Measurement Model (AMM) and radiologists.

Main Results:

  • U-net++ achieved superior segmentation accuracy (mean Dice: 0.926) compared to U-net (0.812).
  • The Automated Measurement Model (AMM) demonstrated excellent agreement with reference standards (r=0.93) for positioning metrics.
  • RFFN significantly outperformed TC and MLR in image quality classification, achieving an AUC of 0.982.
  • SHAP analysis provided insights into feature importance for the RFFN model.

Conclusions:

  • The developed segmentation-based Random Forest Fusion Network (RFFN) accurately classifies image positioning and identifies critical operational factors.
  • The fusion model, enhanced by SHAP, offers clinical interpretability for AI-driven assessment of chest X-ray positioning.
  • This integrated framework provides expert-level image quality assessment and automated feedback to radiographers, enhancing diagnostic accuracy.