In order to investigate the isokinetic strength of the thigh muscles at different knee flexion angles in patients 12 months after anterior cruciate ligament (ACL) reconstruction, an open-chain concentric and eccentric tests of the quadriceps and hamstring were performed at an angular velocity of 60°/s in 16 males 12 months after ACL reconstruction and 14 healthy controls. The peak muscle strength of different contraction patterns at different knee flexion angles were analyzed and the following ratios were calculated: the concentric ratio of hamstring to quadriceps (Hc/Qc), the eccentric ratio of hamstring to quadriceps (He/Qe), the eccentric ratio of hamstring to the concentric ratio of quadriceps (He/Qc), and the concentric ratio of hamstring to the eccentric ratio of quadriceps (Hc/Qe). A two-way ANOVA with mixed design was used to examine the effects of groups and legs on isokinetic muscle strength characteristics. The following results can be concluded. The hamstring strength characteristics were similar at different knee flexion angles, with the reconstructed leg being significantly smaller than the contralateral leg and not different from the healthy controls. In contrast, the isokinetic quadriceps strength showed angle specificity, and the concentric quadriceps strength of the reconstructed leg at 40° and 50° of knee flexion differed not only from the contralateral leg but also from the healthy control leg, making it a more specific index for assessing muscle strength characteristics. Attention should be paid not only to bilateral symmetry but also to whether it is restored to the level of healthy individuals, emphasizing the recovery of muscle function at specific angles in rehabilitation. The flexion-extension strength ratios of bilateral lower limbs at smaller flexion angles differed from those of healthy controls, suggesting that postoperative rehabilitation should strengthen the control training of knee flexion movements of the reconstructed leg and improve the cushioning control ability of the contralateral leg. 

To study the identification of dynamic anterior cruciate ligament deficiency based on plantar pressure information, using convolutional neural network, raw plantar pressure data during walking were converted into images to establish the connection between plantar pressure and anterior cruciate ligament deficiency. Given plenty of input images and classification results, convolutional neural network could update its parameters for iterations to fit the connection. Plantar pressure data collected by acquisition system (FootScan^®) were divided into two parts, training set and test set. The training set was used for training the deep learning model tune the parameters, which helped the model analyze the data better, while the test set was used to generate diagnosis, compare the results to the ground-truth to evaluate the model’s accuracy, and judge its performance as an auxiliary tool for clinical diagnosis. The results show that trained deep learning model can correctly diagnose over 90% cases in the test set, and only takes about 3 seconds to make a diagnosis. The proposed dynamic plantar pressure information based deep learning model can provide auxiliary diagnosis in very short time, which provides references for the auxiliary diagnosis and rehabilitation in clinical medicine.