The aims of this study were to develop an automatic system capable of calculating four radiological measurements used in the diagnosis and monitoring of cerebral palsy (CP)-related hip disease, and to demonstrate that these measurements are sufficiently accurate to be used in clinical practice. We developed a machine-learning system to automatically measure Reimer’s migration percentage (RMP), acetabular index (ACI), head shaft angle (HSA), and neck shaft angle (NSA). The system automatically locates points around the femoral head and acetabulum on pelvic radiographs, and uses these to calculate measurements. The system was evaluated on 1,650 pelvic radiographs of children with CP (682 females and 968 males, mean age 8.3 years (SD 4.5)). Each radiograph was manually measured by five clinical experts. Agreement between the manual clinical measurements and the automatic system was assessed by mean absolute deviation (MAD) from the mean manual measurement, type 1 and type 2 intraclass correlation coefficients (ICCs), and a linear mixed-effects model (LMM) for assessing bias.Aims
Methods
Accurate assessment of alignment in pre-operative and post-operative knee radiographs is important for planning and evaluating knee replacement surgery. Existing methods predominantly rely on manual measurements using long-leg radiographs, which are time-consuming to perform and are prone to reliability errors. In this study, we propose a machine-learning-based approach to automatically measure anatomical varus/valgus alignment in pre-operative and post-operative standard AP knee radiographs. We collected a training dataset of 816 pre-operative and 457 one-year post-operative AP knee radiographs of patients who underwent knee replacement surgery. Further, we have collected a separate distinct test dataset with both pre-operative and one-year post-operative radiographs for 376 patients. We manually outlined the distal femur and the proximal tibia/fibula with points to capture the knee joint (including implants in the post-operative images). This included point positions used to permit calculation of the anatomical tibiofemoral angle. We defined varus/valgus as negative/positive deviations from zero. Ground truth measurements were obtained from the manually placed points. We used the training dataset to develop a machine-learning-based automatic system to locate the point positions and derive the automatic measurements. Agreement between the automatic and manual measurements for the test dataset was assessed by intra-class correlation coefficient (ICC), mean absolute difference (MAD) and Bland-Altman analysis.Introduction
Method
