Deep Learning-Based Automatic Diagnosis System for Developmental Dysplasia of the Hip

The clinical diagnosis of developmental dysplasia of the hip (DDH) typically involves manually measuring key radiological angles—Center-Edge (CE), Tönnis, and Sharp angles—from pelvic radiographs, a process that is time-consuming and susceptible to variability. This...

Full description

Saved in:
Bibliographic Details
Main Authors: Yang Li, Leo Yan Li-Han, Hua Tian
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Translational Engineering in Health and Medicine
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10965781/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849723152144269312
author Yang Li
Leo Yan Li-Han
Hua Tian
author_facet Yang Li
Leo Yan Li-Han
Hua Tian
author_sort Yang Li
collection DOAJ
description The clinical diagnosis of developmental dysplasia of the hip (DDH) typically involves manually measuring key radiological angles&#x2014;Center-Edge (CE), T&#x00F6;nnis, and Sharp angles&#x2014;from pelvic radiographs, a process that is time-consuming and susceptible to variability. This study aims to develop an automated system that integrates these measurements to enhance the accuracy and consistency of DDH diagnosis. We developed an end-to-end deep learning model for keypoint detection that accurately identifies eight anatomical keypoints from pelvic radiographs, enabling the automated calculation of CE, T&#x00F6;nnis, and Sharp angles. To support the diagnostic decision, we introduced a novel data-driven scoring system that combines the information from all three angles into a comprehensive and explainable diagnostic output. The system demonstrated superior consistency in angle measurements compared to a cohort of eight moderately experienced orthopedists. The intraclass correlation coefficients for the CE, T&#x00F6;nnis, and Sharp angles were 0.957 (95% CI: 0.952&#x2013;0.962), 0.942 (95% CI: 0.937&#x2013;0.947), and 0.966 (95% CI: 0.964&#x2013;0.968), respectively. The system achieved a diagnostic F1 score of 0.863 (95% CI: 0.851&#x2013;0.876), significantly outperforming the orthopedist group (0.777, 95% CI: 0.737&#x2013;0.817, <inline-formula> <tex-math notation="LaTeX">$p = 0.005$ </tex-math></inline-formula>), as well as using clinical diagnostic criteria for each angle individually (<inline-formula> <tex-math notation="LaTeX">$p\lt 0.001$ </tex-math></inline-formula>). The proposed system provides reliable and consistent automated measurements of radiological angles and an explainable diagnostic output for DDH, outperforming moderately experienced clinicians.Clinical impact: This AI-powered solution reduces the variability and potential errors of manual measurements, offering clinicians a more consistent and interpretable tool for DDH diagnosis.
format Article
id doaj-art-a876cbcceefc47d4822214462f6504e0
institution DOAJ
issn 2168-2372
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Translational Engineering in Health and Medicine
spelling doaj-art-a876cbcceefc47d4822214462f6504e02025-08-20T03:11:06ZengIEEEIEEE Journal of Translational Engineering in Health and Medicine2168-23722025-01-011317418210.1109/JTEHM.2025.356087710965781Deep Learning-Based Automatic Diagnosis System for Developmental Dysplasia of the HipYang Li0https://orcid.org/0000-0002-4799-5397Leo Yan Li-Han1https://orcid.org/0000-0001-5059-0932Hua Tian2https://orcid.org/0000-0001-7139-3372Department of Orthopedics, Peking University Third Hospital, Beijing, ChinaThe Edward S. Rogers Sr. Department of Electrical and Computer Engineering, University of Toronto, Toronto, ON, CanadaDepartment of Orthopedics, Peking University Third Hospital, Beijing, ChinaThe clinical diagnosis of developmental dysplasia of the hip (DDH) typically involves manually measuring key radiological angles&#x2014;Center-Edge (CE), T&#x00F6;nnis, and Sharp angles&#x2014;from pelvic radiographs, a process that is time-consuming and susceptible to variability. This study aims to develop an automated system that integrates these measurements to enhance the accuracy and consistency of DDH diagnosis. We developed an end-to-end deep learning model for keypoint detection that accurately identifies eight anatomical keypoints from pelvic radiographs, enabling the automated calculation of CE, T&#x00F6;nnis, and Sharp angles. To support the diagnostic decision, we introduced a novel data-driven scoring system that combines the information from all three angles into a comprehensive and explainable diagnostic output. The system demonstrated superior consistency in angle measurements compared to a cohort of eight moderately experienced orthopedists. The intraclass correlation coefficients for the CE, T&#x00F6;nnis, and Sharp angles were 0.957 (95% CI: 0.952&#x2013;0.962), 0.942 (95% CI: 0.937&#x2013;0.947), and 0.966 (95% CI: 0.964&#x2013;0.968), respectively. The system achieved a diagnostic F1 score of 0.863 (95% CI: 0.851&#x2013;0.876), significantly outperforming the orthopedist group (0.777, 95% CI: 0.737&#x2013;0.817, <inline-formula> <tex-math notation="LaTeX">$p = 0.005$ </tex-math></inline-formula>), as well as using clinical diagnostic criteria for each angle individually (<inline-formula> <tex-math notation="LaTeX">$p\lt 0.001$ </tex-math></inline-formula>). The proposed system provides reliable and consistent automated measurements of radiological angles and an explainable diagnostic output for DDH, outperforming moderately experienced clinicians.Clinical impact: This AI-powered solution reduces the variability and potential errors of manual measurements, offering clinicians a more consistent and interpretable tool for DDH diagnosis.https://ieeexplore.ieee.org/document/10965781/Convolutional neural networkdevelopmental dysplasia of the hipkeypoint detectionradiographscoring system
spellingShingle Yang Li
Leo Yan Li-Han
Hua Tian
Deep Learning-Based Automatic Diagnosis System for Developmental Dysplasia of the Hip
IEEE Journal of Translational Engineering in Health and Medicine
Convolutional neural network
developmental dysplasia of the hip
keypoint detection
radiograph
scoring system
title Deep Learning-Based Automatic Diagnosis System for Developmental Dysplasia of the Hip
title_full Deep Learning-Based Automatic Diagnosis System for Developmental Dysplasia of the Hip
title_fullStr Deep Learning-Based Automatic Diagnosis System for Developmental Dysplasia of the Hip
title_full_unstemmed Deep Learning-Based Automatic Diagnosis System for Developmental Dysplasia of the Hip
title_short Deep Learning-Based Automatic Diagnosis System for Developmental Dysplasia of the Hip
title_sort deep learning based automatic diagnosis system for developmental dysplasia of the hip
topic Convolutional neural network
developmental dysplasia of the hip
keypoint detection
radiograph
scoring system
url https://ieeexplore.ieee.org/document/10965781/
work_keys_str_mv AT yangli deeplearningbasedautomaticdiagnosissystemfordevelopmentaldysplasiaofthehip
AT leoyanlihan deeplearningbasedautomaticdiagnosissystemfordevelopmentaldysplasiaofthehip
AT huatian deeplearningbasedautomaticdiagnosissystemfordevelopmentaldysplasiaofthehip