Related Experiment Video
Updated: Jan 9, 2026
05:42
Orthopedic Robot-Assisted Femoral Neck System in the Treatment of Femoral Neck Fracture
Published on: March 3, 2023
3.1K
From Imaging to Intervention: A Multicenter-Validated Radiomics Pipeline for Guiding Femoral Neck Fracture Surgical
Lin Mu1, Yao Liu2, Yunming Xie3
1Department of Radiology, The First Hospital of Jilin University, Changchun 130021, Jilin Province, China (L.M., K.L., Z.M., H.X., M.L., D.D., H.Z.).
Academic Radiology
|December 2, 2025
Summary
A new radiomics pipeline model accurately assesses femoral neck fracture (FNF) stability and guides surgical decisions. This AI-driven tool enhances objective clinical decision-making for orthopedic surgeons.
Area of Science:
- Orthopedic Surgery
- Radiology
- Artificial Intelligence in Medicine
Background:
- Femoral neck fractures (FNFs) pose significant challenges in determining stability and guiding surgical intervention.
- Accurate assessment of FNF stability is crucial for optimal patient outcomes and treatment planning.
Purpose of the Study:
- To develop and validate a computational pipeline model for diagnosing FNF stability.
- To create a model that aids surgeons in making informed surgical decisions for FNFs.
Main Methods:
- Utilized CT images for automatic segmentation of fracture regions in FNF patients, followed by manual refinement.
- Developed a logistic-regression model incorporating radiomic features to generate a Rad-score for fracture stability classification.
- Integrated the Rad-score into a downstream model for surgical decision support, validated across multiple centers.
Main Results:
- The radiomics model demonstrated strong performance in classifying FNF stability, with AUCs of 0.905 (internal) and 0.821 (external).
- The surgical decision-making model achieved AUCs of 0.881 (internal) and 0.820 (external), indicating robust predictive capabilities.
- The pipeline model was validated on large internal and external datasets from 32 and 33 centers, respectively.
Conclusions:
- The developed radiomics pipeline model effectively classifies FNF stability and supports surgical decision-making.
- The model's integration of explainable AI in fracture quantification aids clinicians in objective decision-making.
- This AI-driven approach shows promise for improving the management of femoral neck fractures.
