MRI and sonography in Legg-Calvé-Perthes disease: clinical relevance of containment and influence on treatment

Fully automatic system to detect and segment the proximal femur in pelvic radiographic images for Legg-Calvé-Perthes disease

This study aimed to develop a method using computer vision techniques to accurately detect and delineate the proximal femur in radiographs of Legg-Calvé-Perthes disease (LCPD) patients. Currently, evaluating femoral head deformity, a crucial predictor of LCPD outcomes, relies on unreliable categorical and qualitative classifications. To address this limitation, we employed the pretrained object detection model YOLOv5 to detect the proximal femur on over 2000 radiographs, including images of shoulders and chests, to enhance robustness and generalizability. Subsequently, we utilized the U-Net convolutional neural network architecture for image segmentation of the proximal femur in more than 800 manually annotated images of stage IV LCPD. The results demonstrate outstanding performance, with the object detection model achieving high accuracy (mean average precision of 0.99) and the segmentation model attaining an accuracy score of 91%, dice coefficient of 0.75, and binary IoU score of 0.85 on the held-out test set. The proposed fully automatic proximal femur detection and segmentation system offers a promising approach to accurately detect and delineate the proximal femoral bone contour in radiographic images, which is essential for further image analysis in LCPD patients. Clinical significance: This study highlights the potential of computer vision techniques for enhancing the reliability of Legg-Calvé-Perthes disease staging and outcome prediction.

Anthropometry of the proximal femur and femoral head in children/adolescents using three-dimensional computed tomography-based measurements

Purpose

Defining normal anthropometric ranges of proximal femur and femoral head for each age group in children/adolescents is a necessity when differentiating normal anatomical variants from pathological deformities. Aim of this study is to define a set of normal anthropometric parameters based on 3D-CT measurements in normal asymptomatic children/adolescents and analyse the variations arising depending on age, side, and/or gender.

Methods

Morphology of the proximal femur was retrospectively assessed in 170 hips (85 children, < 15 years). Measurements included covered femoral head volume (CFHV), femoral head diameter (FHD), femoral head extrusion index (FHEI), coronal alpha angle (CAA), lateral centre-edge angle (LCEA), anterior (AOS) and posterior head-neck offset (POS) and femoral neck-shaft angle (FNSA). Correlation analyses as well as inter- and intra-rater reliability were performed.

Results

CFHV, LCEA, FHD and AOS/POS increased with age and FHEI, CAA, and FNSA decreased with age. None of the measurements correlated with the side. AOS showed a poor correlation with gender. Rapid growth phases were observed at the age of 1, 7 and 11. The inter- and intra-rater reliability was high (range ICC 0.8–0.99 Cronbach alpha 0.86–0.99).

Conclusion

This data delivers a description of growth phases as well as gender and age-correlated reference values of the proximal femoral morphology that could be used by paediatricians and orthopaedic/paediatric surgeons to early diagnose proximal femur deformities and provide guidance in the planning of possible operations.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00276-021-02841-3.

Ultrasound as a diagnostic tool for femoral head containment disorders in children between one and 12 years of age

PURPOSE

Ultrasound has been used to diagnose hip dysplasia in neonates and to screen until the end of their first year. For older children, femoral head containment disorders such as developmental dysplasia of the hip, Legg-Calvé-Perthes disease or cerebral palsy are usually diagnosed with plain radiographs. The aim of the present study was to evaluate ultrasound in comparison with radiographic imaging in children up to age 12 years and to determine reference values for sonographic containment parameters.

METHODS

Hip ultrasound and radiographic imaging were acquired on the same day and then compared. As a reference, normal acetabular angle and acetabulum head index were determined on radiographs. Lateral cartilage distance (LCD), lateral head distance (LHD) and femoral head extrusion angle (HA) were measured on ultrasound images.

RESULTS

We included 96 patients with 167 healthy hips in the study. A total of 55 patients were female and 41 male. The mean age was 5.2 years (sd 3.3; 1.0 to 11.9). LCD_ultrasound, LHD_ultrasound and HA_ultrasound correlated significantly with radiographic parameters. The following ultrasound values were calculated as limits for impending loss of containment: LCD_ultrasound ≥ 6.5 mm, LHD_ultrasound ≥ 3.3 mm and HA_ultrasound ≥ 27.6°.

CONCLUSION

Ultrasound is a simple, radiation-free diagnostic tool to detect femoral head containment disorders, even in children older than one year. This study provides reference values for hip ultrasound in children up to 12 years.

LEVEL OF EVIDENCE

III.