Automatic assessment of lower limb deformities using high-resolution X-ray images
Abstract Background Planning an osteotomy or arthroplasty surgery on a lower limb requires prior classification/identification of its deformities. The detection of skeletal landmarks and the calculation of angles required to identify the deformities are traditionally done manually, with measurement...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-05-01
|
| Series: | BMC Musculoskeletal Disorders |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12891-025-08784-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849687756612042752 |
|---|---|
| author | Reyhaneh Rostamian Masoud Shariat Panahi Morad Karimpour Alireza Almasi Nokiani Ramin Jafarzadeh Khaledi Hadi Ghattan Kashani |
| author_facet | Reyhaneh Rostamian Masoud Shariat Panahi Morad Karimpour Alireza Almasi Nokiani Ramin Jafarzadeh Khaledi Hadi Ghattan Kashani |
| author_sort | Reyhaneh Rostamian |
| collection | DOAJ |
| description | Abstract Background Planning an osteotomy or arthroplasty surgery on a lower limb requires prior classification/identification of its deformities. The detection of skeletal landmarks and the calculation of angles required to identify the deformities are traditionally done manually, with measurement accuracy relying considerably on the experience of the individual doing the measurements. We propose a novel, image pyramid-based approach to skeletal landmark detection. Methods The proposed approach uses a Convolutional Neural Network (CNN) that receives the raw X-ray image as input and produces the coordinates of the landmarks. The landmark estimations are modified iteratively via the error feedback method to come closer to the target. Our clinically produced full-leg X-Rays dataset is made publically available and used to train and test the network. Angular quantities are calculated based on detected landmarks. Angles are then classified as lower than normal, normal or higher than normal according to predefined ranges for a normal condition. Results The performance of our approach is evaluated at several levels: landmark coordinates accuracy, angles’ measurement accuracy, and classification accuracy. The average absolute error (difference between automatically and manually determined coordinates) for landmarks was 0.79 ± 0.57 mm on test data, and the average absolute error (difference between automatically and manually calculated angles) for angles was 0.45 ± 0.42°. Conclusions Results from multiple case studies involving high-resolution images show that the proposed approach outperforms previous deep learning-based approaches in terms of accuracy and computational cost. It also enables the automatic detection of the lower limb misalignments in full-leg x-ray images. |
| format | Article |
| id | doaj-art-7fb182896d8b44979af70ae7bb6ea1d0 |
| institution | DOAJ |
| issn | 1471-2474 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Musculoskeletal Disorders |
| spelling | doaj-art-7fb182896d8b44979af70ae7bb6ea1d02025-08-20T03:22:15ZengBMCBMC Musculoskeletal Disorders1471-24742025-05-0126111110.1186/s12891-025-08784-9Automatic assessment of lower limb deformities using high-resolution X-ray imagesReyhaneh Rostamian0Masoud Shariat Panahi1Morad Karimpour2Alireza Almasi Nokiani3Ramin Jafarzadeh Khaledi4Hadi Ghattan Kashani5School of Mechanical Engineering, College of Engineering, University of TehranSchool of Mechanical Engineering, College of Engineering, University of TehranSchool of Mechanical Engineering, College of Engineering, University of TehranFiroozabadi Clinical Research Development Unit (FACRDU), Iran University of Medical Sciences (lUMS)Rad Radiology and Sonography ClinicSchool of Mechanical Engineering, College of Engineering, University of TehranAbstract Background Planning an osteotomy or arthroplasty surgery on a lower limb requires prior classification/identification of its deformities. The detection of skeletal landmarks and the calculation of angles required to identify the deformities are traditionally done manually, with measurement accuracy relying considerably on the experience of the individual doing the measurements. We propose a novel, image pyramid-based approach to skeletal landmark detection. Methods The proposed approach uses a Convolutional Neural Network (CNN) that receives the raw X-ray image as input and produces the coordinates of the landmarks. The landmark estimations are modified iteratively via the error feedback method to come closer to the target. Our clinically produced full-leg X-Rays dataset is made publically available and used to train and test the network. Angular quantities are calculated based on detected landmarks. Angles are then classified as lower than normal, normal or higher than normal according to predefined ranges for a normal condition. Results The performance of our approach is evaluated at several levels: landmark coordinates accuracy, angles’ measurement accuracy, and classification accuracy. The average absolute error (difference between automatically and manually determined coordinates) for landmarks was 0.79 ± 0.57 mm on test data, and the average absolute error (difference between automatically and manually calculated angles) for angles was 0.45 ± 0.42°. Conclusions Results from multiple case studies involving high-resolution images show that the proposed approach outperforms previous deep learning-based approaches in terms of accuracy and computational cost. It also enables the automatic detection of the lower limb misalignments in full-leg x-ray images.https://doi.org/10.1186/s12891-025-08784-9Skeletal landmark detectionLower limb deformitiesOsteotomyArthroplasty surgeryConvolutional neural networks |
| spellingShingle | Reyhaneh Rostamian Masoud Shariat Panahi Morad Karimpour Alireza Almasi Nokiani Ramin Jafarzadeh Khaledi Hadi Ghattan Kashani Automatic assessment of lower limb deformities using high-resolution X-ray images BMC Musculoskeletal Disorders Skeletal landmark detection Lower limb deformities Osteotomy Arthroplasty surgery Convolutional neural networks |
| title | Automatic assessment of lower limb deformities using high-resolution X-ray images |
| title_full | Automatic assessment of lower limb deformities using high-resolution X-ray images |
| title_fullStr | Automatic assessment of lower limb deformities using high-resolution X-ray images |
| title_full_unstemmed | Automatic assessment of lower limb deformities using high-resolution X-ray images |
| title_short | Automatic assessment of lower limb deformities using high-resolution X-ray images |
| title_sort | automatic assessment of lower limb deformities using high resolution x ray images |
| topic | Skeletal landmark detection Lower limb deformities Osteotomy Arthroplasty surgery Convolutional neural networks |
| url | https://doi.org/10.1186/s12891-025-08784-9 |
| work_keys_str_mv | AT reyhanehrostamian automaticassessmentoflowerlimbdeformitiesusinghighresolutionxrayimages AT masoudshariatpanahi automaticassessmentoflowerlimbdeformitiesusinghighresolutionxrayimages AT moradkarimpour automaticassessmentoflowerlimbdeformitiesusinghighresolutionxrayimages AT alirezaalmasinokiani automaticassessmentoflowerlimbdeformitiesusinghighresolutionxrayimages AT raminjafarzadehkhaledi automaticassessmentoflowerlimbdeformitiesusinghighresolutionxrayimages AT hadighattankashani automaticassessmentoflowerlimbdeformitiesusinghighresolutionxrayimages |