BACKGROUND:Knee finite element modelling can provide insight into knee mechanics,but its complex image segmentation is more difficult for researchers.With the development of deep learning techniques,deep learning techniques have been widely used in knee joint finite element modelling.OBJECTIVE:To replace the manual segmentation step in finite element modelling of the knee joint by using 3D Swin UNETR in combination with a semi-automatic segmentation technique for statistical shape models.METHODS:Manual(artificial)knee joint finite element model was developed based on MR and semi-automatic knee joint finite element model was developed based on 3D Swin UNETR+statistical shape model segmentation.The same loads and boundary conditions were applied to both models.Validation was performed by calculating the Dice similarity coefficient,mean distance,and comparing the peak equivalent stresses,maximum principal stresses,and maximum shear stresses of the two models.RESULTS AND CONCLUSION:(1)The Dice similarity coefficients of the manual and semi-automatic segmented femur and tibia were more than 98％,and the average distances were less than or equal to(0.35±0.08)mm.(2)With the longitudinal load of 750 N and 10 Nm internal overturning moment applied to the femur tip of both manual and semi-automatic finite element models,the peak equivalent stress,maximum principal stress,and maximum shear stresses of meniscus in manual finite element model were 14.12,18.54,and 7.35 MPa;peak equivalent force,maximum principal stress,and maximum shear stress of femoral cartilage were 2.22,2.15,and 1.18 MPa;peak equivalent force,maximum principal stress,and maximum shear stress of tibial cartilage were 2.50,1.91,and 1.41 MPa;semi-automatic finite element model of meniscus:peak equivalent force,maximum principal stress,and maximum shear stress were 14.93,18.53,and 7.75 MPa.The peak equivalent force,maximum principal stress,and maximum shear stress of femoral cartilage were 2.26,2.18,and 1.20 MPa;the peak equivalent stress,maximum principal stress,and maximum shear stress of tibial cartilage were 2.60,1.91,and 1.46 MPa.The peak equivalent stress,maximum principal stress,and maximum shear stress of manual and semi-automatic finite element models were basically consistent,with no significant difference(P＞0.05).(3)The semi-automatic segmentation technique proposed in this study can replace manual segmentation in creating accurate finite element models of the knee joint.

BACKGROUND:Finite element modeling,as an important engineering analysis technique,has been widely used in various fields of bioengineering research.However,there is little literature on what material properties should be selected for each anatomical structure of the knee joint finite element modeling at different ages for different research purposes.OBJECTIVE:To summarize the material properties of knee joint finite element models at different ages based on previous knee joint finite element studies.METHODS:The search terms were"knee,finite element,material selection,ligament injury,osteoarthritis,elderly,children,young people"in Chinese and English.Articles were searched on CNKI and PubMed,with a timeframe of 1950 to 2024.According to inclusion and exclusion criteria,108 articles were finally included for summary.RESULTS AND CONCLUSION:Children's knee bone density will increase with age,reaching peaks in adulthood.From middle-aged to the age,the elastic modulus of knee joint femur,tibia,fibula,and patella will decrease with age,and then return to the elastic modulus of childhood.The elastic modulus of children and adult cartilage is basically the same,and the elastic modulus of the elderly increases.With the increase of age,the elastic modulus of the knee ligament will decrease to a certain extent,but there is no significant difference in the elastic modulus of the knee ligament of young people and the elderly.With the increase of age,the loss of mechanical integrity of the knee meniscus will damage the biomechanical function of the tissue and disturb the various anisotropic biomechanical responses that are effectively carried and transmitted by the tissue.Knee joint finite element modeling can be used to deeply understand the biomechanical characteristics of the knee joints,develop new implanted materials,predict knee joint diseases,improve surgical technology,and guide patients to rehabilitate exercise.

BACKGROUND:Knee finite element modelling can provide insight into knee mechanics,but its complex image segmentation is more difficult for researchers.With the development of deep learning techniques,deep learning techniques have been widely used in knee joint finite element modelling.OBJECTIVE:To replace the manual segmentation step in finite element modelling of the knee joint by using 3D Swin UNETR in combination with a semi-automatic segmentation technique for statistical shape models.METHODS:Manual(artificial)knee joint finite element model was developed based on MR and semi-automatic knee joint finite element model was developed based on 3D Swin UNETR+statistical shape model segmentation.The same loads and boundary conditions were applied to both models.Validation was performed by calculating the Dice similarity coefficient,mean distance,and comparing the peak equivalent stresses,maximum principal stresses,and maximum shear stresses of the two models.RESULTS AND CONCLUSION:(1)The Dice similarity coefficients of the manual and semi-automatic segmented femur and tibia were more than 98％,and the average distances were less than or equal to(0.35±0.08)mm.(2)With the longitudinal load of 750 N and 10 Nm internal overturning moment applied to the femur tip of both manual and semi-automatic finite element models,the peak equivalent stress,maximum principal stress,and maximum shear stresses of meniscus in manual finite element model were 14.12,18.54,and 7.35 MPa;peak equivalent force,maximum principal stress,and maximum shear stress of femoral cartilage were 2.22,2.15,and 1.18 MPa;peak equivalent force,maximum principal stress,and maximum shear stress of tibial cartilage were 2.50,1.91,and 1.41 MPa;semi-automatic finite element model of meniscus:peak equivalent force,maximum principal stress,and maximum shear stress were 14.93,18.53,and 7.75 MPa.The peak equivalent force,maximum principal stress,and maximum shear stress of femoral cartilage were 2.26,2.18,and 1.20 MPa;the peak equivalent stress,maximum principal stress,and maximum shear stress of tibial cartilage were 2.60,1.91,and 1.46 MPa.The peak equivalent stress,maximum principal stress,and maximum shear stress of manual and semi-automatic finite element models were basically consistent,with no significant difference(P＞0.05).(3)The semi-automatic segmentation technique proposed in this study can replace manual segmentation in creating accurate finite element models of the knee joint.

BACKGROUND:Finite element modeling,as an important engineering analysis technique,has been widely used in various fields of bioengineering research.However,there is little literature on what material properties should be selected for each anatomical structure of the knee joint finite element modeling at different ages for different research purposes.OBJECTIVE:To summarize the material properties of knee joint finite element models at different ages based on previous knee joint finite element studies.METHODS:The search terms were"knee,finite element,material selection,ligament injury,osteoarthritis,elderly,children,young people"in Chinese and English.Articles were searched on CNKI and PubMed,with a timeframe of 1950 to 2024.According to inclusion and exclusion criteria,108 articles were finally included for summary.RESULTS AND CONCLUSION:Children's knee bone density will increase with age,reaching peaks in adulthood.From middle-aged to the age,the elastic modulus of knee joint femur,tibia,fibula,and patella will decrease with age,and then return to the elastic modulus of childhood.The elastic modulus of children and adult cartilage is basically the same,and the elastic modulus of the elderly increases.With the increase of age,the elastic modulus of the knee ligament will decrease to a certain extent,but there is no significant difference in the elastic modulus of the knee ligament of young people and the elderly.With the increase of age,the loss of mechanical integrity of the knee meniscus will damage the biomechanical function of the tissue and disturb the various anisotropic biomechanical responses that are effectively carried and transmitted by the tissue.Knee joint finite element modeling can be used to deeply understand the biomechanical characteristics of the knee joints,develop new implanted materials,predict knee joint diseases,improve surgical technology,and guide patients to rehabilitate exercise.

Background::Breast cancer (BC) risk-stratification tools for Asian women that are highly accurate and can provide improved interpretation ability are lacking. We aimed to develop risk-stratification models to predict long- and short-term BC risk among Chinese women and to simultaneously rank potential non-experimental risk factors.Methods::The Breast Cancer Cohort Study in Chinese Women, a large ongoing prospective dynamic cohort study, includes 122,058 women aged 25-70 years old from the eastern part of China. We developed multiple machine-learning risk prediction models using parametric models (penalized logistic regression, bootstrap, and ensemble learning), which were the short-term ensemble penalized logistic regression (EPLR) risk prediction model and the ensemble penalized long-term (EPLT) risk prediction model to estimate BC risk. The models were assessed based on calibration and discrimination, and following this assessment, they were externally validated in new study participants from 2017 to 2020.Results::The AUC values of the short-term EPLR risk prediction model were 0.800 for the internal validation and 0.751 for the external validation set. For the long-term EPLT risk prediction model, the area under the receiver operating characteristic curve was 0.692 and 0.760 in internal and external validations, respectively. The net reclassification improvement index of the EPLT relative to the Gail and the Han Chinese Breast Cancer Prediction Model (HCBCP) models for external validation was 0.193 and 0.233, respectively, indicating that the EPLT model has higher classification accuracy.Conclusions::We developed the EPLR and EPLT models to screen populations with a high risk of developing BC. These can serve as useful tools to aid in risk-stratified screening and BC prevention.

Objective To predict the torque on the affected side of the hip,knee,and ankle joints in stroke patients during walking using principal component analysis(PCA)and backpropagation(BP)neural networks.Methods Kinematic and dynamic data from 30 stroke patients were synchronously collected using an 8-lens Qualisys infrared point high-speed motion capture system and Kistler three-dimensional(3D)force measurement platform.The torques of the hip,knee,and ankle joints in the stroke patients were calculated using OpenSim,and the initial variables with a cumulative contribution rate of 99％were screened using PCA.The normalized root mean square error(NRMSE),root mean square error(RMSE),mean absolute percentage error(MAPE),mean absolute error(MAE),and R2 were used as evaluation indicators for the PCA-BP model.The consistency between the calculated joint torque and predicted torque was evaluated using Kendall's W coefficient.Results PCA data showed that the trunk,pelvis,and affected sides of the hip,knee,and ankle joints had a significant impact on the torque of the affected sides of the hip,knee,and ankle joints on the x,y,and z axes(sagittal,coronal,and vertical axes,respectively).The NRMSE between predicted and measured values was 5.14％-8.86％,RMSE was 0.184-0.371,MAPE was 3.5％-4.0％,MAE was 0.143-0.248,and R was 0.998-0.999.Conclusions The established PCA-BP model can accurately predict the torque of the hip,knee,and ankle joints in stroke patients during walking,with a significantly shortened measurement time.This model can replace traditional joint torque calculation in the gait analysis of stroke patients,provides a new approach to obtaining biomechanical data of stroke patients,and is an effective method for the clinical treatment of stroke patients.

Objective To predict the stress on the anterior cruciate ligament(ACL)in the left leg of a volleyball player during ball-snapping landing,by using an XCM deep neural network model.Methods A complete finite element model of the knee joint was established based on magnetic resonance(MR)and CT images.The kinematic and kinetic data of the volleyball player were collected synchronously using an eight-lens Qualisys motion capture system and a Kistler three-dimensional(3D)force platform.The knee joint moments were calculated using the musculoskeletal model in OpenSim.The joint moments were used as the input to the finite element model,with ACL stresses as the output.The kinematic and kinetic data were used as the input for the neural network,with ACL stress as the output.Results The peak equivalent ACL stress of the volleyball player during ball-snapping landing was(27.7±0.36)MPa,the maximum principal stress was(8.2±0.23)MPa,the maximum shear stress was(14.7±0.32)MPa,the equivalent strain was(5.7±0.008)%,the maximum principal strain was(5.0±0.006)%,and the maximum shear strain was(7.6±0.009)%.The normalized root mean square error(NRMSE)between the predicted and calculated values ranged from 5.84%to 7.12%.The root mean square error(RMSE)ranged from 0.251 to 0.282.Conclusions The XCM model can predict the ACL stress during volleyball spikes within a certain range.This study has provided a new method to obtain biomechanical data on volleyball players as well as an effective method to help volleyball players prevent ACL injuries.

Objective To predict the stress on the anterior cruciate ligament(ACL)in the left leg of a volleyball player during ball-snapping landing,by using an XCM deep neural network model.Methods A complete finite element model of the knee joint was established based on magnetic resonance(MR)and CT images.The kinematic and kinetic data of the volleyball player were collected synchronously using an eight-lens Qualisys motion capture system and a Kistler three-dimensional(3D)force platform.The knee joint moments were calculated using the musculoskeletal model in OpenSim.The joint moments were used as the input to the finite element model,with ACL stresses as the output.The kinematic and kinetic data were used as the input for the neural network,with ACL stress as the output.Results The peak equivalent ACL stress of the volleyball player during ball-snapping landing was(27.7±0.36)MPa,the maximum principal stress was(8.2±0.23)MPa,the maximum shear stress was(14.7±0.32)MPa,the equivalent strain was(5.7±0.008)%,the maximum principal strain was(5.0±0.006)%,and the maximum shear strain was(7.6±0.009)%.The normalized root mean square error(NRMSE)between the predicted and calculated values ranged from 5.84%to 7.12%.The root mean square error(RMSE)ranged from 0.251 to 0.282.Conclusions The XCM model can predict the ACL stress during volleyball spikes within a certain range.This study has provided a new method to obtain biomechanical data on volleyball players as well as an effective method to help volleyball players prevent ACL injuries.

Objective:To investigate the effect of polypeptide N-acetylgalactosaminaminyltransferase 2 (GALNT2) on the proliferation and apoptosis of human retinal vascular endothelial cells (HRCECs) cultured in high glucose and its possible mechanism.Methods:The small hairpin RNA (shRNA) targeting GALNT2 gene was constructed to interfere with the lentiviral vector and infect HRCECs.HRCECs were divided into blank control group, model group, NC-shGALNT2 group and shGALNT2 group, which were cultured in medium containing 5.5 mmol/L glucose, 25 mmol/L glucose, shGALNT2 negative control virus 25 mmol/L glucose and shGALNT2 knockdown virus 25 mmol/L glucose for 24 hours, respectively.The relative expression of GALNT2 mRNA in the four groups was detected by real-time fluorescence quantitative PCR.The relative expression levels of GALNT2, epidermal growth factor (EGF), EGF receptor (EGFR) and phosphorylated EGFR (p-EGFR) were detected by Western blot.The proliferative values of HRCECs were detected by cell counting kit-8 method.The apoptosis rate of different groups was detected by flow cytometry. Results:The relative expression levels of GALNT2 mRNA and protein were significantly higher in model group than in blank control group, and were significantly lower in shGALNT2 group than in blank control group (all at P<0.05). The cell proliferation value was significantly lower in model group than in blank control group, and was significantly higher in shGALNT2 than in model group and NC-shGALNT2 group (all at P<0.05). The apoptosis rates of blank control group, model group, NC-shGALNT2 group and shGALNT2 group were (4.73±0.26)%, (8.66±0.25)%, (9.26±1.12)% and (5.47±0.18)%, respectively, with a significant overall difference ( F=342.921, P<0.001). The apoptosis rate was significantly higher in model group than in blank control group, and was significantly lower in shGALNT2 group than in model group and NC-shGALNT2 group (all at P<0.05). The relative expression level of EGFR protein was significantly higher and the relative expression level of p-EGFR protein was significantly lower in model group than in blank control group (all at P<0.05). The relative expression of p-EGFR protein was significantly higher in shGALNT2 group than in model group (all at P<0.05). Conclusions:Knocking down GALNT2 can improve the proliferative ability of HRCECs under high glucose culture and reduce apoptosis, which may be related to the activation of EGFR signaling pathway.

Due to damage to the hemi-advanced central nervous system of stroke hemiplegic patients, their ability of sit-to-stand transfer is impaired, and they are prone to fall during the sit-to-stand transfer. This article describes the characteristics of sit-to-stand transfer for hemiplegic patients at different foot placement from a biomechanical perspective, discusses the correlation between different features, analyzes the reasons for their fall, and describes the application of sit-to-stand transfer training in postoperative rehabilitation of hemiplegic patients， so as to provide references for postoperative rehabilitation of hemiplegic patients.