Radiological age assessment based on clavicle ossification in CT: enhanced accuracy through deep learning.

BACKGROUND: Radiological age assessment using reference studies is inherently limited in accuracy due to a finite number of assignable skeletal maturation stages. To overcome this limitation, we present a deep learning approach for continuous age assessment based on clavicle ossification in computed tomography (CT). METHODS: Thoracic CT scans were retrospectively collected from the picture archiving and communication system. Individuals aged 15.0 to 30.0 years examined in routine clinical practice were included. All scans were automatically cropped around the medial clavicular epiphyseal cartilages. A deep learning model was trained to predict a person's chronological age based on these scans. Performance was evaluated using mean absolute error (MAE). Model performance was compared to an optimistic human reader performance estimate for an established reference study method. RESULTS: The deep learning model was trained on 4,400 scans of 1,935 patients (training set: mean age = 24.2 years ± 4.0, 1132 female) and evaluated on 300 scans of 300 patients with a balanced age and sex distribution (test set: mean age = 22.5 years ± 4.4, 150 female). Model MAE was 1.65 years, and the highest absolute error was 6.40 years for females and 7.32 years for males. However, performance could be attributed to norm-variants or pathologic disorders. Human reader estimate MAE was 1.84 years and the highest absolute error was 3.40 years for females and 3.78 years for males. CONCLUSIONS: We present a deep learning approach for continuous age predictions using CT volumes highlighting the medial clavicular epiphyseal cartilage with performance comparable to the human reader estimate.

Timing characteristics of body segments during the maximal instep kick in experienced football players.

BACKGROUND: The first aim of this study was to describe duration and relative timing of the phases of the maximal instep kick. The second aim was to describe the concurrence of maximal range of motion, maximal angular acceleration, maximal angular deceleration and maximal angular velocity of body segments with four key points. METHODS: Twenty experienced football players performed three maximal instep kicks. The kicks were analysed using a full body, three-dimensional motion capture system. Camera recordings determined kicking leg events. The concurrence of peak kinematics of body segments with four key points was calculated. RESULTS: Duration and timing of five phases were identified. Key point maximal hip extension (51.4±5.0%) concurred significantly with maximal range of motion (ROM) of shoulder extension. Key point maximal knee flexion (63.6±5.2%) concurred significantly with maximal angular acceleration of spine flexion and pelvis posterior tilt. Key point knee flexion 90 degrees (69.3±4.9%) concurred significantly with maximal angular velocity of shoulder flexion and spine flexion, maximal angular deceleration of hip flexion and maximal angular acceleration of knee extension. Key point ball impact (75.2±5.2%) concurred significantly with maximal ROM of hip deflexion and pelvis anterior rotation and with maximal angular deceleration of spine flexion and pelvis anterior rotation. CONCLUSIONS: This study demonstrated that eleven peak kinematics of upper body and kicking leg segments, significantly concurred with four kicking leg positions. These results provide Key points for kicking coordination and stress the importance of dynamical coupling as a kicking mechanism.