The varying effectiveness of anterior cruciate ligament (ACL) injury prevention programs between soccer and basketball may be due to differences in sport-specific injury mechanisms. Bone bruise patterns may provide information regarding injury mechanisms. To compare bone bruise and meniscal injury patterns for ACL injuries sustained in soccer versus basketball. Cross-sectional study; Level of evidence, 3. Clinical notes, operative reports, and magnetic resonance imaging scans were reviewed for patients who sustained a noncontact ACL rupture while playing soccer or basketball between August 2016 and August 2018. The presence, location, and signal intensity of bone bruises on the tibia and femur were documented, and patterns were classified according to the location of the bone bruise in the lateral-medial direction. The meniscal and bone bruise injury patterns and the specific bone bruise locations were compared between the soccer and basketball groups. Overall, 138 patients were included (56 with soccer-related and 82 with basketball-related ACL injury). No significant difference between the groups was observed in bone bruise patterns (P = .743) or meniscal injury patterns (P = .952). Bone bruise on the lateral side only of both the femur and the tibia was the most common pattern in both soccer (41.9%) and basketball (47.0%) groups; the most common meniscal injury type was an isolated lateral meniscal injury in both soccer (50.0%) and basketball (45.0%) groups. For patients with bone bruises on both the lateral and the medial sides of both the femur and the tibia (BF+BT), the bone bruise signal intensity on the lateral side of the femur (P < .001) and tibia (P = .009) was significantly higher than that on the medial side for both groups. The bone bruises on the lateral side of the femur (P < .001) and tibia (P = .002) were significantly more anterior than those on the medial side for patients with the BF+BT pattern. No significant differences in bone bruise location or meniscal injury type were detected when comparing ACL injuries sustained during soccer versus basketball. The study results suggest a similar biomechanical loading pattern for ACL injuries in these sports.

The process of determining which disease or condition explains a person's symptoms and signs can be very complicated and may be inaccurate in some cases. The general belief is that diagnosing diseases relies on doctors' keen intuition, rich experience and professional equipment. In this work, we employ ideas from recent advances in plantar pressure research and from the powerful capacity of the convolutional neural network for learning representations. Here, we propose a model using convolutional neural network based on plantar pressure for medical diagnosis. Our model learns a network that maps plantar pressure data to its corresponding medical diagnostic label. We then apply our model to make the medical diagnosis on datasets we collected from cooperative hospital and achieve an accuracy of 98.36%. We demonstrate that the model base on the convolutional neural network is competitive in medical diagnosis.