Related Experiment Video
Updated: Jun 28, 2025

Three-Dimensional Preoperative Virtual Planning in Derotational Proximal Femoral Osteotomy
Published on: February 17, 2023
Development of an automatic surgical planning system for high tibial osteotomy using artificial intelligence
Kazuki Miyama1, Takenori Akiyama2, Ryoma Bise3
1Department of Orthopaedic Surgery, Graduate School of Medical Sciences, Kyushu University, 3-1-1 Maidashi, Higashi-Ku, Fukuoka 812-8582, Japan; Department of Advanced Information Technology, Kyushu University, 744 Motooka, Nishi-Ku, Fukuoka 819-0395, Japan; Akiyama Clinic, 2-28-39, Noke, Sawaraku, Fukuoka City, Fukuoka 814-0171, Japan.
This study introduces an AI system for high tibial osteotomy (HTO) surgical planning. The deep learning system accurately and rapidly measures lower-limb alignment, aiding pre-operative planning.
Area of Science:
- Orthopaedic Surgery
- Medical Imaging Analysis
- Artificial Intelligence in Medicine
Background:
- High tibial osteotomy (HTO) requires precise surgical planning for optimal patient outcomes.
- Current methods for assessing lower-limb alignment can be time-consuming and subjective.
- The integration of artificial intelligence (AI) offers potential for automating and improving surgical planning processes.
Purpose of the Study:
- To develop and validate an automatic surgical planning system for HTO using deep learning.
- To assess the system's accuracy in measuring key lower-limb alignment parameters.
- To evaluate the efficiency of the AI system compared to manual measurements.
Main Methods:
- A deep learning-based AI system was developed to automatically detect anatomical landmarks on whole-leg standing radiographs.
- The system simulated high tibial osteotomy (HTO) and measured five lower-limb alignment parameters: hip knee angle (HKA), weight-bearing line ratio (WBL ratio), mechanical lateral distal femoral angle (mLDFA), mechanical medial proximal tibial angle (mMPTA), and mechanical lateral distal tibial angle (mLDTA).
- Accuracy was validated against ground truth (GT) values provided by experienced orthopaedic surgeons, with inter-rater reliability assessed using intraclass correlation coefficients (ICC).
Main Results:
- The AI system demonstrated high accuracy, with absolute errors within 1.5° or 1.5% for all measured parameters.
- Excellent reliability was achieved for HKA (0.99) and WBL ratios (>0.99) in pre-osteotomy simulations, with ICC values >0.80 for all parameters.
- The system's measurement time (0.24 seconds) was significantly faster than that of human surgeons (118 seconds).
Conclusions:
- The proposed AI system is a practically applicable tool for accurate and rapid measurement of lower-limb alignment parameters in pre- and post-osteotomy simulations.
- The system demonstrates significant potential for enhancing surgical planning in high tibial osteotomy (HTO).
- The speed and accuracy of the AI system suggest it could streamline the surgical planning workflow.

