Related Experiment Video
Updated: Jun 28, 2025
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
[Development and Application of Deep Learning-Based Model for Quality Control of Children Pelvic X-Ray Images]
Zhichen Liu1, Jincong Lin1, Kunjie Xie1
1Department of Orthopaedics, Xijing Hospital, Air Force Medical University, Xi'an, 710032.
Insights
A novel deep learning AI model accurately assesses pediatric pelvic X-ray image quality. This AI tool enhances diagnostic accuracy for developmental dysplasia of the hip (DDH) in children.
Area of Science:
- Radiology
- Artificial Intelligence
- Medical Imaging
Background:
- Pediatric pelvic X-ray quality is crucial for diagnosing conditions like developmental dysplasia of the hip (DDH).
- Current quality assessment methods can be subjective and time-consuming.
- Objective and automated quality evaluation is needed.
Purpose of the Study:
- To develop and validate a deep learning-based artificial intelligence (AI) model for assessing the quality of pediatric pelvic X-ray images.
- To construct a diagnostic model for quality control and verify its clinical feasibility.
Main Methods:
- A dataset of 3,247 anteroposteric pelvic radiographs from children was retrospectively collected.
- The data was randomly divided into training, validation, and test sets.
- An AI model was developed and trained to evaluate the reliability of image quality control.
Main Results:
- The AI model achieved high performance metrics: 99.4% diagnostic accuracy, 0.993 area under the ROC curve, 98.6% sensitivity, and 100.0% specificity.
- The model demonstrated excellent consistency for pelvic tilt index (-0.052-0.072) and pelvic rotation index (-0.088-0.055).
Conclusions:
- This study presents the first AI algorithm application for quality assessment of pediatric pelvic radiographs.
- The AI model significantly improves the diagnostic and treatment status for DDH in children.
- The developed AI method offers a reliable and accurate approach to pediatric pelvic X-ray quality control.
Objective:
A deep learning-based method for evaluating the quality of pediatric pelvic X-ray images is proposed to construct a diagnostic model and verify its clinical feasibility.
Methods:
Three thousand two hundred and forty-seven children with anteroposteric pelvic radiographs are retrospectively collected and randomly divided into training datasets, validation datasets and test datasets. Artificial intelligence model is conducted to evaluate the reliability of quality control model.
Results:
The diagnostic accuracy, area under ROC curve, sensitivity and specificity of the model are 99.4%, 0.993, 98.6% and 100.0%, respectively. The 95% consistency limit of the pelvic tilt index of the model is -0.052-0.072. The 95% consistency threshold of pelvic rotation index is -0.088-0.055.
Conclusion:
This is the first attempt to apply AI algorithm to the quality assessment of children's pelvic radiographs, and has significantly improved the diagnosis and treatment status of DDH in children.
