An approach for fully automatic femoral neck-shaft angle evaluation on radiographs

Wei, Qiang; Han, Jiawei; Jia, Yang; Zhu, Liyang; Zhang, Shuai; Lu, Yufeng; Yang, Bin; Tang, Shaojie

doi:10.1063/1.5089738

Cited by 11 publications

(8 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wei et al proposed an automatic method to measure the NSA on radiograph. With their method based on the 2D radiographs, our methods based on CT data made the automatic measurement of the NSA comprehensive [22]. Hartel et al used a novel 3D modeling and analytical technology to measure the NSA based on CT data.…”

Section: Discussionmentioning

confidence: 99%

Comparing Two Different Automatic Methods to Measure Femoral Neck-Shaft Angle Based on PointNet++ Network

Li¹,

Yang²,

Li³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Bacnground: Accurate measurement of the femoral neck-shaft angle (NSA) is of great significance for diagnosing hip joint diseases and preoperative planning of total hip arthroplasty. However, the fitting lines of the femoral neck and femoral shaft did not always intersect in 3D space. Thus, it is unclear whether there is a difference between 2D and 3D methods for measuring NSA. Methods: The femoral point cloud datasets from 310 subjects were segmented into three regions, including the femoral head, femoral neck, and femoral shaft using PointNet++. We created a projection plane to simulate the hip anteroposterior radiograph and fitted the femoral neck axis and femoral shaft axis to complete the 2D measurement, while we directly fitted the two axes in space to complete the 3D measurement. Also, we conducted the manual measurement of the NSA. We verified the accuracy of the segmentation and compared the results of the two automatic and manual methods. Results: The Dice coefficient of femoral segmentation reached 0.9746, and MIoU of that was 0.9165. No significant difference was found between any two of the three methods. While comparing the 2D and 3D methods, the average accuracy was 98.00%, and the average error was 2.58°. Conclusion: This paper proposed two accurate and automatic methods to measure the NSA based on a 2D plane and a 3D model respectively. Although the femoral neck and femoral shaft axes did not intersect in 3D space, the NSAs obtained by 2D and 3D methods were basically consistent.

show abstract

Section: Discussionmentioning

confidence: 99%

Comparing Two Different Automatic Methods to Measure Femoral Neck-Shaft Angle Based on PointNet++ Network

Li¹,

Yang²,

Li³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…We employed m = 5 femoral anatomical measurements: neck shaft angle (NSA), femoral version (FV), bicondylar width (BW), head diameter (HD), and femur length (FL), which were automatically computed using a set of 18 anatomical landmarks [31]- [36]. Angulation (NSA), torsion (FV) and dimension (HD) of the proximal femur are essential for surgical planning of hip joint replacements [31]- [33], [35], [36], whereas BW is an important measurement for knee joint replacements [34] and FL provides an evaluation of the size of the femur [32]. Scapular anatomical measurements.…”

Section: B Automatic Derivation Of Anatomical Measurements From Landm...mentioning

confidence: 99%

Anatomically Parameterized Statistical Shape Model: Explaining Morphometry through Statistical Learning

Boutillon,

Salhi,

Burdin

et al. 2022

Preprint

View full text Add to dashboard Cite

Statistical shape models (SSMs) are a popular tool to conduct morphological analysis of anatomical structures which is a crucial step in clinical practices. However, shape representations through SSMs are based on shape coefficients and lack an explicit oneto-one relationship with anatomical measures of clinical relevance. While a shape coefficient embeds a combination of anatomical measures, a formalized approach to find the relationship between them remains elusive in the literature. This limits the use of SSMs to subjective evaluations in clinical practices. We propose a novel SSM controlled by anatomical parameters derived from morphometric analysis. Methods: The proposed anatomically parameterized SSM (ANAT SSM ) is based on learning a linear mapping between shape coefficients (latent space) and selected anatomical parameters (anatomical space). This mapping is learned from a synthetic population generated by the standard SSM. Determining the pseudo-inverse of the mapping allows us to build the ANAT SSM . We further impose orthogonality constraints to the anatomical parameterization (OC-ANAT SSM ) to obtain independent shape variation patterns. The proposed contribution was evaluated on two skeletal databases of femoral and scapular bone shapes using clinically relevant anatomical parameters within each (five for femoral and six for scapular bone). Results: Anatomical measures of the synthetically generated shapes exhibited realistic statistics. The learned matrices corroborated well with the obtained statistical relationship, while the two SSMs achieved moderate to excellent performance in predicting anatomical parameters on unseen shapes. Conclusion: This study demonstrates the use of anatomical representation for creating anatomically parameterized SSMs and as a result, removes the limited clinical interpretability of standard SSMs. Significance: The proposed models could help analyze differences in relevant bone morphometry between populations, and be integrated in patientspecific pre-surgery planning or in-surgery assessment.

show abstract

“…In fact, deep learning has been applied in image segmentation; the neural network model represented by Unet shows good performance in medical image segmentation. Wei et al (2020) used the improved network model based on Unet to segment the femur to calculated caput-collum-diaphyseal angle and achieved relatively good results. Li et al (2019) automatically identified the outer margin of the acetabulum and the lower margin of teardrops through the Mask-RCNN network model for the automatic measurement of Sharp angle.…”

Section: Applications Of Computer-aided Detection Systemsmentioning

confidence: 99%

“…Both methods use neural networks in measuring hip joint angles and obtain good model performance. However, Wei et al (2020) only segmented the femur and did not automatically segment the acetabulum simultaneously. In addition, Li et al (2019) measured Sharp angle by identifying key points such as the outer edge of the acetabulum and the lower edge of teardrops; however, if the number of key points is too small, the model may be over-fitted as occurred in their initial research.…”

Section: Applications Of Computer-aided Detection Systemsmentioning

confidence: 99%

Computer-Aided System Application Value for Assessing Hip Development

et al. 2020

View full text Add to dashboard Cite

PurposeA computer-aided system was used to semiautomatically measure Tönnis angle, Sharp angle, and center-edge (CE) angle using contours of the hip bones to establish an auxiliary measurement model for developmental screening or diagnosis of hip joint disorders.MethodsWe retrospectively analyzed bilateral hip x-rays for 124 patients (41 men and 83 women aged 20–70 years) who presented at the Affiliated Zhongshan Hospital of Dalian University in 2017 and 2018. All images were imported into a computer-aided detection system. After manually outlining hip bone contours, Tönnis angle, Sharp angle, and CE angle marker lines were automatically extracted, and the angles were measured and recorded. An imaging physician also manually measured all angles and recorded hip development, and Pearson correlation coefficients were used to compare computer-aided system measurements with imaging physician measurements. Accuracy for different angles was calculated, and the area under the receiver operating characteristic (AUROC) curve was used to represent the diagnostic efficiency of the computer-aided system.ResultsFor Tönnis angle, Sharp angle, and CE angle, correlation coefficients were 0.902, 0.887, and 0.902, respectively; the accuracies of the computer-aided detection system were 89.1, 93.1, and 82.3%; and the AUROC curve values were 0.940, 0.956, and 0.948.ConclusionThe measurements of Tönnis angle, Sharp angle, and CE angle using the semiautomatic system were highly correlated with the measurements of the imaging physician and can be used to assess hip joint development with high accuracy and diagnostic efficiency.

show abstract

An approach for fully automatic femoral neck-shaft angle evaluation on radiographs

Cited by 11 publications

References 20 publications

Comparing Two Different Automatic Methods to Measure Femoral Neck-Shaft Angle Based on PointNet++ Network

Comparing Two Different Automatic Methods to Measure Femoral Neck-Shaft Angle Based on PointNet++ Network

Anatomically Parameterized Statistical Shape Model: Explaining Morphometry through Statistical Learning

Computer-Aided System Application Value for Assessing Hip Development

Contact Info

Product

Resources

About