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

Adaptive, Privacy-Preserving Small Language Models for Multi-Task Clinical Assistance.

Journal of imaging informatics in medicine·2026
Same author

Best Practices for the Safe Use of Large Language Models and Other Generative AI in Radiology.

Radiology·2025
Same author

Enhancing Magnetic Resonance Imaging (MRI) Report Comprehension in Spinal Trauma: Readability Analysis of AI-Generated Explanations for Thoracolumbar Fractures.

JMIR AI·2025
Same author

Pitfalls and Best Practices in Evaluation of AI Algorithmic Biases in Radiology.

Radiology·2025
Same author

AI-generated Podcast Summaries of <i>Radiology</i> Articles: Analysis of Content and Quality.

Radiology·2025
Same author

Open-Source Large Language Models in Radiology: A Review and Tutorial for Practical Research and Clinical Deployment.

Radiology·2025

Related Experiment Video

Updated: Aug 3, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

2.8K

Performance and Usability of Code-Free Deep Learning for Chest Radiograph Classification, Object Detection, and

Samantha M Santomartino1, Nima Hafezi-Nejad1, Vishwa S Parekh1

  • 1University of Maryland Medical Intelligent Imaging (UM2ii) Center, Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, 670 W Baltimore St, First Floor, Room 1172, Baltimore, MD 21201 (S.M.S., P.H.Y.); The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, Baltimore, Md (N.H.N., V.S.P.); Department of Computer Science, Whiting School of Engineering (V.S.P.), and Malone Center for Engineering in Healthcare (P.H.Y.), Johns Hopkins University, Baltimore, Md.

Radiology. Artificial Intelligence
|April 10, 2023
PubMed
Summary

Code-free deep learning (CFDL) platforms showed limited performance and usability for analyzing chest radiographs, failing to train effective models for disease classification and segmentation. Further development is needed for practical application in radiology.

Keywords:
Artificial IntelligenceAutomated Machine LearningChest RadiographsCode-Free Deep LearningDeep LearningPneumoniaPneumothoraxRadiology

More Related Videos

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
10:44

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Published on: June 21, 2024

561
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

470

Related Experiment Videos

Last Updated: Aug 3, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

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

Published on: November 30, 2022

2.8K
Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
10:44

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Published on: June 21, 2024

561
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

470

Area of Science:

  • Radiology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Deep learning (DL) models are increasingly used in medical imaging analysis.
  • Code-free deep learning (CFDL) platforms aim to simplify DL model creation.
  • Evaluating CFDL platforms for chest radiograph analysis is crucial for clinical adoption.

Purpose of the Study:

  • To assess the performance and usability of CFDL platforms for creating DL models.
  • To evaluate CFDL models for disease classification, object detection, and segmentation on chest radiographs.

Main Methods:

  • Six CFDL platforms were retrospectively evaluated.
  • Models were trained for thoracic pathologic conditions, pneumonia detection, and pneumothorax segmentation using various chest radiograph datasets.
  • Model performance was measured by F1 scores, and usability was assessed based on feasibility, ease of use, and cost.

Main Results:

  • CFDL platforms exhibited limited performance, with poor external validation scores for most classification tasks.
  • Only one pneumonia detection model was successfully trained (F1 score of 0.48); no segmentation models were trained.
  • Platform usability was constrained, with all requiring some level of coding.

Conclusions:

  • CFDL platforms currently demonstrate limited efficacy and usability for chest radiograph analysis.
  • Further advancements are necessary to enhance the performance and accessibility of CFDL tools in radiology.
  • The study highlights the need for improved CFDL solutions for automated medical image analysis.