scholarly journals Auxiliary Diagnostic Method for Patellofemoral Pain Syndrome Based on One-Dimensional Convolutional Neural Network

2021 ◽  
Vol 9 ◽  
Author(s):  
Wuxiang Shi ◽  
Yurong Li ◽  
Dujian Xu ◽  
Chen Lin ◽  
Junlin Lan ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Diagnostic Method ◽  
Pain Syndrome ◽  
Patellofemoral Pain Syndrome ◽  
Patellofemoral Pain ◽  
Flexion Angle ◽  
Data Set ◽  
One Dimensional ◽  
Semg Signals

Early accurate diagnosis of patellofemoral pain syndrome (PFPS) is important to prevent the further development of the disease. However, traditional diagnostic methods for PFPS mostly rely on the subjective experience of doctors and subjective feelings of the patient, which do not have an accurate-unified standard, and the clinical accuracy is not high. With the development of artificial intelligence technology, artificial neural networks are increasingly applied in medical treatment to assist doctors in diagnosis, but selecting a suitable neural network model must be considered. In this paper, an intelligent diagnostic method for PFPS was proposed on the basis of a one-dimensional convolutional neural network (1D CNN), which used surface electromyography (sEMG) signals and lower limb joint angles as inputs, and discussed the model from three aspects, namely, accuracy, interpretability, and practicability. This article utilized the running and walking data of 41 subjects at their selected speed, including 26 PFPS patients (16 females and 10 males) and 16 painless controls (8 females and 7 males). In the proposed method, the knee flexion angle, hip flexion angle, ankle dorsiflexion angle, and sEMG signals of the seven muscles around the knee of three different data sets (walking data set, running data set, and walking and running mixed data set) were used as input of the 1D CNN. Focal loss function was introduced to the network to solve the problem of imbalance between positive and negative samples in the data set and make the network focus on learning the difficult-to-predict samples. Meanwhile, the attention mechanism was added to the network to observe the dimension feature that the network pays more attention to, thereby increasing the interpretability of the model. Finally, the depth features extracted by 1D CNN were combined with the traditional gender features to improve the accuracy of the model. After verification, the 1D CNN had the best performance on the running data set (accuracy = 92.4%, sensitivity = 97%, specificity = 84%). Compared with other methods, this method could provide new ideas for the development of models that assisted doctors in diagnosing PFPS without using complex biomechanical modeling and with high objective accuracy.

scholarly journals Diagnosis of Patellofemoral Pain Syndrome Based on a Multi-Input Convolutional Neural Network With Data Augmentation

2021 ◽  
Vol 9 ◽  
Author(s):  
Wuxiang Shi ◽  
Yurong Li ◽  
Baoping Xiong ◽  
Min Du
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Pain Syndrome ◽  
Data Preprocessing ◽  
Patellofemoral Pain Syndrome ◽  
Patellofemoral Pain ◽  
Diagnostic Methods ◽  
Lower Limbs

Patellofemoral pain syndrome (PFPS) is a common disease of the knee. Despite its high incidence rate, its specific cause remains unclear. The artificial neural network model can be used for computer-aided diagnosis. Traditional diagnostic methods usually only consider a single factor. However, PFPS involves different biomechanical characteristics of the lower limbs. Thus, multiple biomechanical characteristics must be considered in the neural network model. The data distribution between different characteristic dimensions is different. Thus, preprocessing is necessary to make the different characteristic dimensions comparable. However, a general rule to follow in the selection of biomechanical data preprocessing methods is lacking, and different preprocessing methods have their own advantages and disadvantages. Therefore, this paper proposes a multi-input convolutional neural network (MI-CNN) method that uses two input channels to mine the information of lower limb biomechanical data from two mainstream data preprocessing methods (standardization and normalization) to diagnose PFPS. Data were augmented by horizontally flipping the multi-dimensional time-series signal to prevent network overfitting and improve model accuracy. The proposed method was tested on the walking and running datasets of 41 subjects (26 patients with PFPS and 15 pain-free controls). Three joint angles of the lower limbs and surface electromyography signals of seven muscles around the knee joint were used as input. MI-CNN was used to automatically extract features to classify patients with PFPS and pain-free controls. Compared with the traditional single-input convolutional neural network (SI-CNN) model and previous methods, the proposed MI-CNN method achieved a higher detection sensitivity of 97.6%, a specificity of 76.0%, and an accuracy of 89.0% on the running dataset. The accuracy of SI-CNN in the running dataset was about 82.5%. The results prove that combining the appropriate neural network model and biomechanical analysis can establish an accurate, convenient, and real-time auxiliary diagnosis system for PFPS to prevent misdiagnosis.

scholarly journals VASTUS LATERALIS OBLIQUE ACTIVITY DURING GAIT OF SUBJECTS WITH PATELLOFEMORAL PAIN

2017 ◽  
Vol 23 (2) ◽  
pp. 88-92
Author(s):  
Gilmar Moraes Santos ◽  
Karina Gramani Say ◽  
Flávio Pulzatto ◽  
Thiele de Cássia Libardoni ◽  
Larissa Milani Brognoli Sinhorim ◽  
...  
Keyword(s):  
Knee Joint ◽  
Vastus Lateralis ◽  
Pain Syndrome ◽  
Patellofemoral Pain Syndrome ◽  
Patellofemoral Pain ◽  
Flexion Angle ◽  
Oblique Muscle ◽  
Electromyographic Activity ◽  
Healthy Controls ◽  
Patellar Stability

ABSTRACT Introduction: So far, little is known about the behavior of electromyographic activity of vastus lateralis oblique muscle during treadmill gait in subjects with and without patellofemoral pain syndrome. Objective: The purpose of this study was to investigate the electromyographic activity of the patellar stabilizers muscles and the angle of the knee joint flexion in subjects with and without patellofemoral pain syndrome. Method: Fifteen subjects without (21 ± 3 years) and 12 with patellofemoral pain syndrome (20 ± 2 years) were evaluated. The electromyographic activity and flexion angle of the knee joint were obtained during gait on the treadmill with a 5 degree inclination. Results: The knee flexion angle was significantly lower in the subjects with patellofemoral pain syndrome when compared with the healthy controls. The electromyographic activity of vastus lateralis longus was significantly greater during gait on the treadmill with inclination in subjects with patellofemoral pain syndrome. The results also showed that the electromyographic activity of vastus lateralis oblique and vastus medialis oblique were similar in both groups, regardless of the condition (with/without inclination). Conclusion: We have shown that knee kinematics during gait differs among patients with and without patellofemoral pain syndrome and healthy controls and that a different motor strategy persists even when the pain is no longer present. In addition, the findings suggested that the vastus lateralis oblique has a minor role in patellar stability during gait.

scholarly journals Research on intelligent diagnostic techniques for rolling bearings based on unbalanced data sets

2022 ◽  
Vol 355 ◽  
pp. 03034
Author(s):  
Zhikai Xing ◽  
Yongbao Liu ◽  
Qiang Wang ◽  
Jun Li
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Sampling Technique ◽  
Rolling Bearing ◽  
Classification Problem ◽  
Diagnostic Techniques ◽  
Support Vector ◽  
Data Set ◽  
One Dimensional ◽  
Vibration Data

In this paper, based on the combination of comprehensive sampling and one-dimensional convolutional neural network, a bearing fault intelligent diagnosis technique is proposed for the classification of rolling bearing vibration data. At first, the fault data set is expanded by ADASYN method. Then, the data is cleaned up by Tomek link under sampling technique, the risk of overfitting caused by overlap of different classes is reduced and the data of different categories is more apparent, and finally the normal data set and fault data set after comprehensive sampling are classified by one-dimensional convolutional neural network algorithm. Compared with random forests and support vector machines, the results show that the method has a high accuracy in identifying classifications and can effectively solve the classification problem of unbalanced bearing data.

Sign in / Sign up

Export Citation Format

Share Document