Objective:To construct a prior based on the inherent properties of PET to accurately segment the lesion areas.Methods:A network framework for PET tumor segmentation driven by geodesic priors was proposed (geodesic network for short). Specifically, partial differential equations were constructed to characterize the geodesic distances between different regions in PET images. Tumor marker points identified by CT labeling were used as the initial conditions for the equations. To enhance the contrast between areas of lung or breast tumors and normal tissues, a smooth Heaviside function was utilized to map the geodesic distances. The network framework adopted a dual-branch architecture, using geodesic priors to assist in PET image segmentation.Results:The proposed method achieved a Dice coefficient of 94.92% in lung cancer segmentation and 90.12% in breast cancer segmentation. With the addition of geodesic priors in the Unet, the Dice coefficient for breast cancer increased by 32.37% (from 42.50% to 74.87%).Conclusion:Geodesic priors can significantly improve segmentation outcomes and enhance the generalization capability of the network.

Objective:To develop and assess a three-class machine learning model for predicting wild-type, 19 del, and 21 L858R mutations of the epidermal growth factor receptor (EGFR) in lung adenocarcinoma using 18F-FDG PET/CT radiomic features and clinical features. Methods:The retrospective data was collected from 703 patients (346 males, 357 females; age (64.3±9.0) years) with lung adenocarcinoma at the First People′s Hospital of Changzhou from January 2018 to June 2023. Patients were divided into the training set (563 cases) and test set (140 cases) at the ratio of 8∶2. Clinical features were selected using recursive feature elimination (RFE). Radiomic features were extracted from PET and CT images, and the optimal feature sets were selected using minimum redundancy maximum relevance (mRMR) and least absolute shrinkage and selection operator (LASSO) methods. Base models were constructed by using random forest (RF), logistic regression (LR), support vector machine (SVM), K-nearest neighbors (KNN), and multi-layer perceptron (MLP), and the stacking method was applied to establish the CT and PET ensemble models. Delong test was used to compare the AUC differences between the PET/CT combined model and the clinical + PET/CT integrated model.Results:Among 703 patients, 273 were with EGFR wild-type, 202 were with 19 del mutation, and 228 were with 21 L858R mutation. In the single-modal analysis, the AUCs of CT ensemble model in the training and test sets were 0.893 and 0.667, respectively, while the AUCs of PET ensemble model were 0.692 and 0.660. The AUC of PET/CT combined model were 0.897 in training set and 0.672 in test set. The AUC of clinical + PET/CT integrated model showed further improvement, with AUCs of 0.902 and 0.721 in training and test sets, respectively. Notably, the clinical + PET/CT integrated model outperformed PET/CT combined model in predicting wild-type EGFR (test set AUC: 0.784 vs 0.707; Z=3.28, P=0.001). Conclusion:The three-class model (clinical + PET/CT integrated model) based on 18F-FDG PET/CT radiomics and clinical features effectively predicts EGFR mutation subtypes in lung adenocarcinoma.

Objective:To construct a prior based on the inherent properties of PET to accurately segment the lesion areas.Methods:A network framework for PET tumor segmentation driven by geodesic priors was proposed (geodesic network for short). Specifically, partial differential equations were constructed to characterize the geodesic distances between different regions in PET images. Tumor marker points identified by CT labeling were used as the initial conditions for the equations. To enhance the contrast between areas of lung or breast tumors and normal tissues, a smooth Heaviside function was utilized to map the geodesic distances. The network framework adopted a dual-branch architecture, using geodesic priors to assist in PET image segmentation.Results:The proposed method achieved a Dice coefficient of 94.92% in lung cancer segmentation and 90.12% in breast cancer segmentation. With the addition of geodesic priors in the Unet, the Dice coefficient for breast cancer increased by 32.37% (from 42.50% to 74.87%).Conclusion:Geodesic priors can significantly improve segmentation outcomes and enhance the generalization capability of the network.

Objective:To develop and assess a three-class machine learning model for predicting wild-type, 19 del, and 21 L858R mutations of the epidermal growth factor receptor (EGFR) in lung adenocarcinoma using 18F-FDG PET/CT radiomic features and clinical features. Methods:The retrospective data was collected from 703 patients (346 males, 357 females; age (64.3±9.0) years) with lung adenocarcinoma at the First People′s Hospital of Changzhou from January 2018 to June 2023. Patients were divided into the training set (563 cases) and test set (140 cases) at the ratio of 8∶2. Clinical features were selected using recursive feature elimination (RFE). Radiomic features were extracted from PET and CT images, and the optimal feature sets were selected using minimum redundancy maximum relevance (mRMR) and least absolute shrinkage and selection operator (LASSO) methods. Base models were constructed by using random forest (RF), logistic regression (LR), support vector machine (SVM), K-nearest neighbors (KNN), and multi-layer perceptron (MLP), and the stacking method was applied to establish the CT and PET ensemble models. Delong test was used to compare the AUC differences between the PET/CT combined model and the clinical + PET/CT integrated model.Results:Among 703 patients, 273 were with EGFR wild-type, 202 were with 19 del mutation, and 228 were with 21 L858R mutation. In the single-modal analysis, the AUCs of CT ensemble model in the training and test sets were 0.893 and 0.667, respectively, while the AUCs of PET ensemble model were 0.692 and 0.660. The AUC of PET/CT combined model were 0.897 in training set and 0.672 in test set. The AUC of clinical + PET/CT integrated model showed further improvement, with AUCs of 0.902 and 0.721 in training and test sets, respectively. Notably, the clinical + PET/CT integrated model outperformed PET/CT combined model in predicting wild-type EGFR (test set AUC: 0.784 vs 0.707; Z=3.28, P=0.001). Conclusion:The three-class model (clinical + PET/CT integrated model) based on 18F-FDG PET/CT radiomics and clinical features effectively predicts EGFR mutation subtypes in lung adenocarcinoma.

Objective:To investigate the value of intratumoral and peritumoral radiomics models based on 18F-FDG PET-CT in predicting epidermal growth factor receptor (EGFR) mutation status in lung adenocarcinoma and interpret peritumoral radiomics features. Methods:This study was a cross-sectional study. Patients with lung adenocarcinoma who underwent 18F-FDG PET-CT at the Third Affiliated Hospital of Soochow University between January 2018 and April 2022 were retrospectively collected and samplied into a training set (309 cases) and a test set (206 cases) in a 6∶4 ratio randomly. Radiomics features were extracted from the intratumoral and peritumoral regions of interest based on PET and CT images, respectively, and the optimal feature sets were selected. Radiomics models were established using the XGBoost algorithm, and radiomics scores (intratumoral CT label, peritumoral CT label, intratumoral PET label, peritumoral PET label) were calculated. Logistic regression analysis was used to construct a clinical model and a combined model (incorporating PET-CT intratumoral and peritumoral radiomics, clinical features, and CT semantic features). The predictive performance of the models was evaluated using receiver operating characteristic curves and the area under the curve (AUC). Unsupervised clustering, Spearman correlation analysis, and visualization methods were used for the interpretability of peritumoral radiomics features. Results:In both the training and test sets, the AUC value of CT peritumoral labels was greater than that of CT intratumoral labels for predicting EGFR mutation status in lung adenocarcinoma (training set: Z=3.84, P<0.001; test set: Z=1.99, P=0.046). In the test set, the AUC value of PET intratumoral labels (0.684) was slightly higher than that of PET peritumoral labels (0.672) for predicting EGFR mutation status, but the difference was not statistically significant ( P>0.05). The combined model had the highest AUC value for predicting EGFR mutation status of lung adenocarcinoma in both the training and test sets and was significantly better than the clinical model (training set: Z=6.52, P<0.001; test set: Z=2.31, P=0.021). Interpretability analysis revealed that CT peritumoral radiomics features were correlated with CT shape features, and there were significant differences in CT peritumoral features between different EGFR mutation statuses. Conclusions:The value of CT peritumoral labels is superior to that of CT intratumoral labels in predicting EGFR mutation status in lung adenocarcinoma. The predictive performance of the model can be improved by combining PET-CT intratumoral and peritumoral radiomics, clinical features, and CT semantic features.

OBJECTIVE: To review the research progress of the biomechanical study of the Bristow-Latarjet procedure for anterior shoulder dislocation. METHODS: The related biomechanical literature of Bristow-Latarjet procedure for anterior shoulder dislocation was extensively reviewed and summarized. RESULTS: The current literature suggests that when performing Bristow-Latarjet procedure, care should be taken to fix the bone block edge flush with the glenoid in the sagittal plane in the direction where the rupture of the joint capsule occurs. If traditional screw fixation is used, a double-cortical screw fixation should be applied, while details such as screw material have less influence on the biomechanical characteristics. Cortical button fixation is slightly inferior to screws in terms of biomechanical performance. The most frequent site of postoperative bone resorption is the proximal-medial part of the bone block, and the cause of bone resorption at this site may be related to the stress shielding caused by the screw. CONCLUSION There is no detailed standardized guidance for bone block fixation. The optimal clinical treatment plan for different degrees of injury, the factors influencing postoperative bone healing and remodeling, and the postoperative osteoarticular surface pressure still need to be further clarified by high-quality biomechanical studies.
Humans ; Shoulder Dislocation/surgery* ; Shoulder Joint/surgery* ; Biomechanical Phenomena ; Joint Instability/surgery* ; Bone Resorption ; Arthroscopy/methods*

Objective:To investigate the clinical and radiological outcomes of ultrasound guided injection of platelet-rich plasma (PRP) in the treatment of intratendinous rotator cuff tear.Methods:A retrospective study was conducted to analyze the clinical data of 43 patients (46 shoulders) who had been treated for intratendinous partial-thickness rotator cuff tear by ultrasound guided injection of PRP consecutively from July 2021 to March 2022 at Department of Sports Medicine, Peking University Third Hospital. There were 23 males and 20 females, with an age of (47.8±13.5) years and a course of disease of 6 (4, 18) months, involving 22 left shoulders and 24 right shoulders. The visual analog scale (VAS) pain score, the University of California at Los Angeles (UCLA) rating scale, and the shoulder index of the American Shoulder and Elbow Surgeons (ASES) were determined before injection and at the last follow-up. The changes in tear size were also evaluated by magnetic resonance imaging (MRI) before PRP injection and 3 to 5 months after PRP injection.Results:The 43 patients were followed up for 15 (12, 17) months after treatment. Of this cohort, 7 shoulders (15.2%, 7/46) were recovered to complete normal and very satisfied with the injection effects while 19 shoulders(41.3%, 19/46) satisfied with the effects after injection, yielding an overall satisfaction rate of 56.5% (26/46). At the last follow-up, the VAS score [3.0 (2.0, 4.0) points], ASES score [80.0 (65.0, 88.8) points], and UCLA score [29.0 (20.0, 32.0) points] were significantly improved compared with those before injection [5.5 (4.0, 8.0) points, 55.0 (39.2, 65.0) points, and 16.0 (12.0, 20.3) points] ( P < 0.05). MRI evaluation showed the tear volume was significantly reduced after PRP injection [46.1 (20.9, 77.5) mm 3 before injection versus 28.2 (12.5, 63.6) mm 3 after injection] ( P<0.05), and a >50% tear volume diminution was observed in 13 shoulders (34.2%,13/38). There were no complications during or after injection. Conclusion:As the ultrasound guided injection of PRP into intratendinous lesions is effective and safe for patients with intratendinous partial-thickness rotator cuff tear, it can be an alternative treatment for the patients or professional athletes who are unwilling to undergo surgery.

Objective:To construct and verify of the predictive models for pathologic invasion of early lung adenocarcinoma with ground glass nodules (GGNs) based on 18F-FDG PET/CT. Methods:A retrospective analysis was conducted on 149 patients (44 males, 105 females; age (61.1±8.9) years) with pre-invasive lesions/minimally invasive adenocarcinoma (MIA) and invasive adenocarcinoma (IAC) confirmed by pathology after surgery in the First People′s Hospital of Changzhou from October 2011 to October 2019. All patients underwent PET/CT for GGNs. GGNs were randomly divided into a modeling group and validation group with the proportion of 1∶1. Mann-Whitney U test or χ2 test was used to compare the qualitative morphological characteristics (shape, edge characteristics, etc.), quantitative parameters (consolidation-to-tumor ratio, attenuation value of the ground glass opacity (GGO) component on CT (CT GGO), etc.) and quantitative functional parameters (SUV max and SUV index(GGNs SUV max/liver SUV mean) of pre-invasive lesions/MIA and IAC. Logistic regression analysis was used to construct the models, and the ROC curve was used to verify the models′ robustness. Different AUCs were compared by Delong test. Results:A total of 170 GGNs were removed by surgery and confirmed pathologically. In the modeling group ( n=89), the proportion of mixed GGNs, irregular shape, edge characteristics, bronchiectasis/twist/truncation sign, GGNs maximum diameter and solid component maximum diameter, consolidation-to-tumor ratio, CT GGO, SUV max and SUV index in IAC group were significantly higher than those in pre-invasive/MIA group ( χ2 values: 5.00-23.40, z values: from -6.53 to -2.70, all P<0.05). Models 1-3 were constructed based on the qualitative parameters (GGNs type, edge characteristics), quantitative parameters (CT GGO, SUV index), combined qualitative and quantitative parameters (GGNs type, edge characteristics, SUV index) of PET/CT, respectively, and the AUCs of ROC were 0.896, 0.880 and 0.931 in the modeling group, respectively. And the AUC of model 2 was not decreased significantly in the validation group ( n=81; AUC=0.802; z=0.81, P=0.417). Conclusion:The model combined with morphological and functional quantitative parameters of 18F-FDG PET/CT can effectively predict the pathological invasion of early lung adenocarcinoma, and the constructed model is robust.

Objective:To investigate the correlation between the SUV index (SUV max of the lesion/SUV mean of the liver) in 18F-FDG PET/CT imaging and the invasiveness of early lung adenocarcinoma presenting as ground-glass nodule (GGN). Methods:From January 2012 to March 2020, 167 GGN patients (49 males, 118 females; age: (61.5±9.0) years) with early lung adenocarcinoma who underwent PET/CT imaging in Changzhou First People′s Hospital were retrospectively enrolled. The image parameters including the GGN number, location, type, edge, shape, abnormal bronchus sign, vacuole sign, pleural depression, vessel convergence sign, GGN diameter ( DGGN), solid component diameter ( Dsolid), consolidation to tumor ratio (CTR, Dsolid/ DGGN), CT values (CT value of ground-glass opacity (CT GGO), CT value of lung parenchyma (CT LP), ΔCT GGO-LP (CT GGO-CT LP)) and SUV index were analyzed. Single and multivariate logistic regressions were used to analyze the correlation between SUV index and infiltration. The generalized additive model was used for curve fitting, and the piece-wise regression model was used to further explain the nonlinearity. Results:In 189 GGNs, invasive adenocarcinoma accounted for 85.2% (161/189). Single logistic regression showed that the GGN number, type, shape, edge, abnormal bronchus sign, pleural depression, vessel convergence sign, DGGN, Dsolid, CTR, CT GGO, ΔCT GGO-LP and SUV index were related factors of infiltration (odds ratio ( OR) values: 0.396-224.083, P<0.001 or P<0.05). After fully adjusting for confounding factors, SUV index was significantly correlated with increased risk of invasion ( OR=2.162 (95% CI: 1.191-3.923), P=0.011). Curve fitting showed that the SUV index was non-linearly related to the risk of infiltration, and the risk of infiltration increased significantly only when the SUV index was greater than 0.43 ( OR=3.509 (95% CI: 1.429-8.620), P=0.006). The correlation between SUV index and infiltration had no interaction between age, vacuoles, pleural depression and CTR subgroups (all P>0.05). Conclusions:SUV index is an independent factor related to the invasiveness of early lung adenocarcinoma. The higher the SUV index, the greater the risk of invasion; but the two are not simply linearly correlated.

Objective:To explore the value of 18F-deoxyglucose (FDG) PET and high resolution CT (HRCT) combined prediction model in the identification of invasiveness of early lung adenocarcinoma with consolidation-to-tumor ratio (CTR)≤0.5. Methods:A retrospective analysis was performed on 91 patients with early lung adenocarcinoma with CTR≤0.5 who underwent PET/CT and HRCT before surgery in the Third Affiliated Hospital of Soochow University from October 2011 to October 2019, including 110 ground-glass nodules (GGNs). According to the pathological subtypes, they were divided into preinvasive-minimally invasive adenocarcinoma (MIA) group ( n=22) and invasive adenocarcinoma (IAC) group ( n=88). The image feature parameters of GGNs of the two groups were compared, and the HRCT model and PET-HRCT combined model were constructed using Logistic regression analysis. Receiver operating characteristic (ROC) curve analysis was used to compare the diagnostic efficacy of different models. The Bootstrap resampling (times = 500) method was used for internal verification of the model, and we also performed interaction and hierarchical analysis on the model. Results:The proportions of mixed GGN, irregular shape, lobulation sign, dilated/distorted/cutoff bronchial sign, pleural indentation and vascular convergence in IAC group were significantly higher than those in preinvasive-MIA group (all P<0.05). Nodule diameter, solid component diameter, solid component ratio, CT value of ground glass attenuation component (CT GGO), and SUVindex of the IAC group were larger than those of the preinvasive-MIA group, and the differences were statistically significant ( P<0.001). Among the quantitative parameters of HRCT, CT GGO had the best diagnostic efficacy (AUC=0.775), with a sensitivity of 0.580 and a specificity of 0.909. The diagnostic efficacy of HRCT model and PET-HRCT combined model were better than CT GGO (AUC: 0.907 vs. 0.775, 0.931 vs. 0.775; P=0.027, 0.002, respectively), but the diagnostic efficacy of the former two was not statistically different ( P=0.210).When the specificity was 0.909, the sensitivity of the HRCT model and the PET-HRCT model (0.784 and 0.875, respectively) were significantly higher than that of the CT GGO (0.580), and the combined PET-HRCT model had a more significant increase in sensitivity. The PET-HRCT combined model showed no significant interaction between different nodule types, between groups with or without pleural indentation, and among nodule diameter subgroups (all P>0.05). Conclusion:PET-HRCT combined model has a good predictive value for the invasiveness of early lung adenocarcinoma with CTR≤0.5, and it can be used for GGN risk stratification to guide clinical decision-making.