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

X-ray Imaging

X-ray Imaging

German physicist Wilhelm Röntgen (1845–1923) was experimenting with electrical current when he discovered that a mysterious and invisible "ray" would pass through his flesh but leave an outline of his bones on a screen coated with a metal compound. In 1895, Röntgen made the first durable record of the internal parts of a living human: an "X-ray" image (as it came to be called) of his wife’s hand. Scientists worldwide quickly began their own experiments with...

You might also read

Related Articles

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

Sort by

Same author

Invited Commentary: Postdeployment Monitoring of AI in Radiology: Beyond the Test Set.

Radiographics : a review publication of the Radiological Society of North America, Inc·2026

Same author

Transverse-plane descriptors and modifiers of the SRS-Lenke-Aubin 3D classification provide complementary and clinically informative 3D features beyond 2D assessment in Lenke 1 AIS curves.

Spine deformity·2026

Same author

A comparison of patients with adolescent idiopathic scoliosis and Lenke C-type lumbar curves treated with selective thoracic fusion vs non-selective fusion: a 10-year follow-up study.

Spine deformity·2026

Same author

AI-derived versus surgeon-performed instrumentation in adolescent idiopathic scoliosis: a biomechanical simulation analysis.

Spine deformity·2026

Same author

Correction: The SRS-Lenke-Aubin 3D classification of adolescent idiopathic scoliosis.

Spine deformity·2026

Same author

Surgical Spine Techniques for Small-Statured Surgeons and Assistants.

The Journal of the American Academy of Orthopaedic Surgeons·2026

Same journal

Externally Tested AI for Lung Nodule Classification: A Realistic Benchmark for an Emerging Screening Era.

Radiology. Artificial intelligence·2026

Same journal

Impact of Exposure Parameters on Deep Learning Models in Chest Radiography and Implications for Deployment.

Radiology. Artificial intelligence·2026

Same journal

Impact on Cost and Expert Time of Data-Efficient Deep Learning for Medical Image Segmentation.

Radiology. Artificial intelligence·2026

Same journal

Benchmarking of AI and Radiologists for Indeterminate Lung Nodule Malignancy Risk Estimation on Screening CT: The LUNA25 Challenge.

Radiology. Artificial intelligence·2026

Same journal

When One Sequence Is Enough-And When It Isn't.

Radiology. Artificial intelligence·2026

Same journal

Cracking the Registration Conundrum in Breast MRI: Preserving the Tumor Signal to Reveal True Treatment Change.

Radiology. Artificial intelligence·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jul 8, 2025

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Anonymizing Radiographs Using an Object Detection Deep Learning Algorithm.

Bardia Khosravi¹, John P Mickley¹, Pouria Rouzrokh¹

¹From the Orthopedic Surgery Artificial Intelligence Laboratory, Department of Orthopedic Surgery (B.K., J.P.M., P.R., M.J.T., A.N.L., C.C.W.), Radiology Informatics Laboratory, Department of Radiology (B.K., P.R., B.J.E.), Department of Orthopedic Surgery (M.J.T., A.N.L., C.C.W.), and Department of Clinical Anatomy (C.C.W.), Mayo Clinic, 200 1st St SW, Rochester, MN 55905.

Radiology. Artificial Intelligence

|December 11, 2023

Summary

This summary is machine-generated.

A deep learning algorithm effectively removes radiographic markers from medical images, enabling de-identified data sharing. This supervised learning approach ensures patient privacy while retaining useful information like laterality markers.

Keywords:

Conventional Radiography Convolutional Neural Network (CNN)Experimental Investigations Skeletal-Axial Supervised Learning Thorax Transfer Learning

More Related Videos

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Published on: August 5, 2021

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

Related Experiment Videos

Last Updated: Jul 8, 2025

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Published on: August 5, 2021

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

Area of Science:

Medical Imaging
Computer Vision
Artificial Intelligence

Background:

Radiographic markers in medical images contain protected health information.
Removal of this data is crucial for de-identified data sharing and research.
Existing methods may not be efficient or accurate enough for comprehensive de-identification.

Purpose of the Study:

To develop and validate a deep learning algorithm for localizing and removing radiographic markers.
To enable secure de-identified data sharing of medical radiographs.
To assess the algorithm's accuracy and effectiveness on internal and external datasets.

Main Methods:

Annotation of 2000 hip and pelvic radiographs for training an object detection model.
Utilizing a two-pass approach involving marker localization and characterization.
Employing supervised learning and transfer learning with a convolutional neural network (CNN).
Validation on an external dataset of chest radiographs with fine-tuning.

Main Results:

Achieved an area under the precision-recall curve of 0.96 on the internal test set.
Demonstrated 100% de-identification accuracy and 93% retention accuracy for laterality markers on internal data.
External validation showed 96% de-identification accuracy, improving to 99.6% after fine-tuning.
The algorithm effectively removed identifying information while preserving clinically relevant markers.

Conclusions:

The developed deep learning algorithm is highly effective for de-identifying radiographic images.
The two-pass approach offers a robust solution for removing protected health information from medical data.
This technology facilitates secure data sharing for research and clinical advancements.