Related Experiment Video
Updated: Aug 23, 2026
Automated Joint Space Detection Improves Bone Segmentation Accuracy
Published on: November 28, 2025
Automated segmentation of necrotic femoral head from 3D MR data
Reza A Zoroofi1, Yoshinobu Sato, Takashi Nishii
1Department of Electrical and Computer Engineering, Faculty of Engineering, Center of Excellence for Control and Intelligent Processing, University of Tehran, Tehran 14395/515, Iran. zoroofi@ut.ac.ir
Insights
This study introduces an automated method for segmenting necrotic femoral heads using MRI scans. The software accurately identifies avascular necrosis of the femoral head (ANFH), aiding early diagnosis and treatment.
Area of Science:
- Medical Image Analysis
- Computer-Assisted Diagnosis
- Orthopedics
Background:
- Avascular necrosis of the femoral head (ANFH) affects young adults, necessitating early diagnosis for effective treatment.
- Accurate segmentation of necrotic femoral heads is crucial for clinical tasks like visualization and quantitative assessment.
Purpose of the Study:
- To develop and validate novel techniques and software for automatic segmentation of necrotic femoral heads from T1-weighted MR data.
- To improve early diagnosis and management of avascular necrosis of the femoral head (ANFH).
Main Methods:
- Utilized a five-step automated segmentation process on 50 patient MR datasets.
- Incorporated 3D morphological operations, region growing, ellipse fitting (PCA, simulated annealing), anatomical constraints, and k-means clustering.
- Developed user-friendly Windows software for implementation and testing.
Main Results:
- The automated method successfully segmented necrotic femoral heads in 50 clinical cases (3000 MR images).
- The software demonstrated feasibility for segmenting avascular necrosis of the femoral head (ANFH).
Conclusions:
- The developed software and techniques provide an effective solution for automatic necrotic femoral head segmentation.
- This automated approach supports improved early diagnosis and management of avascular necrosis of the femoral head (ANFH).
Abstract:
Segmentation of diseased organs is an important topic in computer assisted medical image analysis. In particular, automatic segmentation of necrotic femoral head is of importance for various corresponding clinical tasks including visualization, quantitative assessment, early diagnosis and adequate management of patients suffering from avascular necrosis of the femoral head (ANFH). Early diagnosis and treatment of ANFH is crucial since the disease occurs in relatively young individuals with an average age of 20-50, and since treatment options for more advanced disease are frequently unsuccessful. The present paper describes several new techniques and software for automatic segmentation of necrotic femoral head based on clinically obtained multi-slice T1-weighted MR data. In vivo MR data sets of 50 actual patients are used in the study. An automatic method built up to manage the segmentation task according to image intensity of bone tissues, shape of the femoral head, and other characters. The processing scheme consisted of the following five steps. (1) Rough segmentation of non-necrotic lesions of the femur by applying a 3D gray morphological operation and a 3D region growing technique. (2) Fitting a 3D ellipse to the femoral head by a new approach utilizing the constraint of the shape of the femur, and employing a principle component analysis and a simulated annealing technique. (3) Estimating the femoral neck location, and also femoral head axis by integrating anatomical information of the femur and boundary of estimated 3D ellipse. (4) Removal of non-bony tissues around the femoral neck and femoral head ligament by utilizing the estimated femoral neck axis. (5) Classification of necrotic lesions inside the estimated femoral head by a k-means technique. The above method was implemented in a Microsoft Windows software package. The feasibility of this method was tested on the data sets of 50 clinical cases (3000 MR images).
