Endometrial cancer (EC) is one of the most common gynecological malignancies, with an increasing incidence rate worldwide. Accurate segmentation of lesion areas in computed tomography (CT) images is a critical step in assisting clinical diagnosis. In this study, we propose a novel deep learning-based segmentation model, termed spatial choice and weight union network (SCWU-Net), which incorporates two newly designed modules: the spatial selection module (SSM) and the combination weight module (CWM). The SSM enhances the model's ability to capture contextual information through deep convolutional blocks, while the CWM, based on joint attention mechanisms, is employed within the skip connections to further boost segmentation performance. By integrating the strengths of both modules into a U-shaped multi-scale architecture, the model achieves precise segmentation of EC lesion regions. Experimental results on a public dataset demonstrate that SCWU-Net achieves a Dice similarity coefficient (DSC) of 82.98%, an intersection over union (IoU) of 78.63%, a precision of 92.36%, and a recall of 84.10%. Its overall performance is significantly outperforming other state-of-the-art models. This study enhances the accuracy of lesion segmentation in EC CT images and holds potential clinical value for the auxiliary diagnosis of endometrial cancer.
Humans ; Endometrial Neoplasms/diagnostic imaging* ; Female ; Tomography, X-Ray Computed/methods* ; Deep Learning ; Algorithms ; Image Processing, Computer-Assisted/methods* ; Neural Networks, Computer

Lung cancer is a leading cause of cancer-related deaths worldwide, with its high mortality rate primarily attributed to delayed diagnosis. Radiomics, by extracting abundant quantitative features from medical images, offers novel possibilities for early diagnosis and precise treatment of lung cancer. This article reviewed the latest advancements in radiomics for lung cancer management, particularly its integration with artificial intelligence (AI) to optimize diagnostic processes and personalize treatment strategies. Despite existing challenges, such as non-standardized image acquisition parameters and limitations in model reproducibility, the incorporation of AI significantly enhanced the precision and efficiency of image analysis, thereby improving the prediction of disease progression and the formulation of treatment plans. We emphasized the critical importance of standardizing image acquisition parameters and discussed the role of AI in advancing the clinical application of radiomics, alongside future research directions.
Humans ; Lung Neoplasms/diagnosis* ; Artificial Intelligence ; Early Detection of Cancer/methods* ; Precision Medicine ; Image Processing, Computer-Assisted/methods* ; Tomography, X-Ray Computed ; Radiomics

OBJECTIVES: To develop and validate a preoperative clinical-radiomics model for predicting overall survival (OS) and disease-free survival (DFS) in patients with extrahepatic cholangiocarcinoma (eCCA) undergoing radical resection. METHODS: In this retrospective study, consecutive patients with pathologically-confirmed eCCA who underwent radical resection at our institution from 2015 to 2022 were included. The patients were divided into a training cohort and a validation cohort according to the chronological order of their CT examinations. Least absolute shrinkage and selection operator (LASSO)-Cox regression was employed to select predictive radiomic features and clinical variables. The selected features and variables were incorporated into a Cox regression model. Model performance for 1-year OS and DFS prediction was assessed using calibration curves, area under receiver operating characteristic curve (AUC), and concordance index (C-index). RESULTS: This study included 123 patients (mean age 64.0 ± 8.4 years, 85 males/38 females), with 86 in the training cohort and 37 in the validation cohort. The OS-predicting model included four clinical variables and four radiomic features. It achieved a training cohort AUC of 0.858 (C-index = 0.800) and a validation cohort AUC of 0.649 (C-index = 0.605). The DFS-predicting model included four clinical variables and four other radiomic features. It achieved a training cohort AUC of 0.830 (C-index = 0.760) and a validation cohort AUC of 0.717 (C-index = 0.616). CONCLUSIONS The preoperative clinical-radiomics models show promise as a tool for predicting 1-year OS and DFS in eCCA patients after radical surgery.
Humans ; Male ; Female ; Retrospective Studies ; Middle Aged ; Cholangiocarcinoma/mortality* ; Prognosis ; Bile Duct Neoplasms/mortality* ; Tomography, X-Ray Computed/methods* ; Aged ; Radiomics

OBJECTIVE: To investigate the impact of bone mass and volume of low-density zones beneath the tibial plateau on the maximum von Mises stresses experienced by the cartilage and meniscus in the knee joint. METHODS: The study included one healthy adult volunteer, from whom CT scans were obtained, and one patient diagnosed with knee osteoarthrisis (KOA), for whom X-ray films were acquired. A static model of the knee joint featuring a low-density zone was established based on a normal knee model. In the finite element analysis, axial loads of 1 000 N and 1 800 N were applied to the weight-bearing region of the upper surface of the femoral head for model validation and subsequent finite element studies, respectively. The maximum von Mises stresses in the femoral cartilage, as well as the medial and lateral tibial cartilage and menisci, were observed, and the stress percentage of the medial and lateral components were concurrently analyzed. Additionally, HE staining, as well as alkaline magenta staining, were performed on the pathological specimens of patients with KOA in various low-density regions. RESULTS: The results of model validation indicated that the model was consistent with normal anatomical structures and correlated with previous calculations documented in the literature. Static analysis revealed that the maximum von Mises stress in the medial component of the normal knee was the lowest and increased with the advancement of the hypointensity zone. In contrast, the lateral component exhibited an opposing trend, with the maximum von Mises stress in the lateral component being the highest and decreasing as the hypointensity zone progressed. Additionally, the medial component experienced an increasing proportion of stress within the overall knee joint. HE staining demonstrated that the chondrocyte layer progressively deteriorated and may even disappear as the hypointensity zone expanded. Furthermore, alkaline magenta staining indicated that the severity of microfractures in the trabecular bone increased concurrently with the expansion of the hypointensity zone. CONCLUSION The presence of subtalar plateau low-density zone may aggravate joint degeneration. In clinical practice, it is necessary to pay attention to the changes in the subtalar plateau low-density zone and actively take effective measures to strengthen the bone status of the subtalar plateau low-density zone and restore the complete biomechanical function of the knee joint, in order to slow down or reverse the progression of osteoarthritis.
Humans ; Finite Element Analysis ; Knee Joint/physiology* ; Tibia/anatomy & histology* ; Cartilage, Articular/physiology* ; Menisci, Tibial/physiopathology* ; Tomography, X-Ray Computed ; Osteoarthritis, Knee/diagnostic imaging* ; Weight-Bearing ; Bone Density ; Adult ; Stress, Mechanical ; Male ; Middle Aged ; Biomechanical Phenomena ; Female

OBJECTIVE: To explore the reliability and accuracy of the arbitrary point method for measuring the anteversion angle of acetabular prosthesis after total hip arthroplasty (THA) based on pelvic X-ray films. METHODS: The clinical data of 23 patients (25 hips) who underwent THA between December 2018 and September 2023 and met the selection criteria were retrospectively analyzed. Among them, there were 16 males and 7 females, with an average age of 57.6 years (range, 34-81 years); 13 hips had THA on the left side and 12 on the right side. There were 19 cases (21 hips) of osteonecrosis of the femoral head, 2 cases (2 hips) of femoral neck fractures, 1 case (1 hip) of developmental dysplasia of the hip, and 1 case (1 hip) of osteoarthritis. After THA, all patients underwent X-ray examination and CT scan. Three physicians measured the anteversion angle of acetabular prosthesis using the arbitrary point method and the CT measurement method respectively, and repeated the measurements three times. The results of the two measurement methods were compared, and the intraclass correlation coefficient (ICC) was employed to assess the reproducibility of the methods. RESULTS: The anteversion angles of acetabular prosthesis were (15.87±7.73)° measured by the arbitrary point method, and (15.31±7.89)° measured by CT measurement method. There was no significant difference between the two methods ( t=1.515, P=0.143). The ICC of the measurement results by the arbitrary point method for the three physicians were 0.97 ( P<0.001), 0.96 ( P<0.001), and 0.96 ( P<0.001), respectively; and the ICC of the measurement results by CT method were 0.93 ( P<0.001), 0.93 ( P<0.001), and 0.94 ( P<0.001), respectively. CONCLUSION The arbitrary point method for measuring the anteversion angle of acetabular prosthesis after THA based on pelvic X-ray film is easy to operate, accurate, and has high reproducibility.
Humans ; Arthroplasty, Replacement, Hip/methods* ; Male ; Female ; Aged ; Middle Aged ; Hip Prosthesis ; Acetabulum/surgery* ; Aged, 80 and over ; Retrospective Studies ; Adult ; Reproducibility of Results ; Feasibility Studies ; Tomography, X-Ray Computed

OBJECTIVE: To compare the biomechanical properties of personalized Y-shaped plates with horizontal plates, vertical plates, and traditional Y-shaped plates in the treatment of distal humeral intra-articular fractures through finite element analysis, and to evaluate their potential for clinical application. METHODS: The study selected a 38-year-old male volunteer and obtained a three-dimensional model of the humerus by scanning his upper limbs using a 64-slice spiral CT. Four types of fracture-internal fixation models were constructed using Mimics 19.0, Geomagic Wrap 2017, Creo 6.0, and other software: horizontal plates, vertical plates, traditional Y-shaped plate, and personalized Y-shaped plate. The models were then meshed using Hypermesh 14.0 software, and material properties and boundary conditions were defined in Abaqus 6.14 software. AnyBody 7.3 software was used to simulate elbow flexion and extension movements, calculate muscle strength, joint forces, and load torques, and compare the peak stress and maximum displacement of the four fixation methods at different motion angles (10°, 30°, 50°, 70°, 90°, 110°, 130°, 150°) during elbow flexion and extension. RESULTS: Under dynamic loading during elbow flexion and extension, the personalized Y-shaped plate exhibits significant biomechanical advantages. During elbow flexion, the peak internal fixation stress of the personalized Y-shaped plate was (28.8±0.9) MPa, which was significantly lower than that of the horizontal plates, vertical plates, and traditional Y-shaped plate ( P<0.05). During elbow extension, the peak internal fixation stress of the personalized Y-shaped plate was (18.1±1.6) MPa, which was lower than those of the other three models, with significant differences when compared with horizontal plates and vertical plates ( P<0.05). Regarding the peak humeral stress, the personalized Y-shaped plate model showed mean values of (10.9±0.8) and (13.1±1.4) MPa during elbow flexion and extension, respectively, which were significantly lower than those of the other three models ( P<0.05). Displacement analysis showed that the maximum displacement of the humerus with the personalized Y-shaped plate during elbow flexion was (2.03±0.08) mm, slightly higher than that of the horizontal plates, but significantly lower than that of the vertical plates, showing significant differences ( P<0.05). During elbow extension, the maximum displacement of the humerus with the personalized Y-shaped plate was (1.93±0.13) mm, which was lower than that of the other three models, with significant differences when compared with vertical plates and traditional Y-shaped plates ( P<0.05). Stress contour analysis showed that the stress of the personalized Y-shaped plate was primarily concentrated at the bifurcation of the Y-shaped structure. Displacement contour analysis showed that the personalized Y-shaped plate effectively controlled the displacement of the distal humerus during both flexion and extension, demonstrating excellent stability. CONCLUSION The personalized Y-shaped plate demonstrates excellent biomechanical performance in the treatment of distal humeral intra-articular fractures, with lower stress and displacement, providing more stable fixation effects.
Humans ; Male ; Adult ; Healthy Volunteers ; Finite Element Analysis ; Tomography, Spiral Computed ; Models, Anatomic ; Biomechanical Phenomena ; Humeral Fractures, Distal/surgery* ; Fracture Fixation, Internal/instrumentation* ; Bone Plates ; Computer Simulation ; Precision Medicine/methods* ; Elbow Joint/surgery* ; Elbow/surgery* ; Humerus/surgery* ; Torque ; Stress, Mechanical ; Intra-Articular Fractures/surgery* ; Prosthesis Design/methods* ; Imaging, Three-Dimensional ; Range of Motion, Articular

OBJECTIVE: To investigate whether adding 1 transverse screw (TS) to the triangular parallel cannulated screw (TPCS) fixation has a mechanical stability advantage for Pauwels type Ⅲ femoral neck fractures by conducting finite element analysis on four internal fixation methods. METHODS: Based on CT data of a healthy adult male volunteer's femur, three Pauwels type Ⅲ femoral neck fracture models (Pauwels angle 70°, Pauwels angle 80°, and Pauwels angle 70° combined with bone defect) were constructed using Mimics 21.0 software and SolidWorks 2017 software. Four different internal fixation models were built at the same time, including TPCS, TPCS+TS, three cross screws (TCS), and TPCS+medial buttress plate (MBP). The mechanical stability of different models under the same load was compared by finite element analysis. RESULTS: The femoral model established in this study exhibited a maximum stress of 28.62 MPa, with relatively higher stress concentrated in the femoral neck. These findings were comparable to previous studies, indicating that the constructed femoral finite element model was correct. The maximum stress of internal fixation in finite element analysis showed that TCS was the lowest and TPCS+MBP was the highest in Pauwels angle 70° and 80° models, while TPCS+TS was the lowest and TCS was the highest in Pauwels angle 70° combined with bone defect model. The maximum displacement of internal fixation in each fracture model was located at the top of the femoral head, with TCS having the highest maximum displacement of the femur. The maximum stress of fracture surface in finite element analysis showed that TCS was the lowest and TPCS was the highest in the Pauwels angle 70° model, while TPCS+MBP was the lowest and TPCS/TCS were the highest in the Pauwels angle 80° model and the Pauwels angle 70° combined with bone defect model, respectively. The maximum displacement of fracture surfece analysis showed that TPCS+MBP was the lowest and TCS was the highest in Pauwels angle 70° and 80° models, while TPCS+TS was the lowest and TCS was the highest in Pauwels angle 70° combined with bone defect model. CONCLUSION For Pauwels type Ⅲ femoral neck fractures, the biomechanical stability of TPCS+TS was superior to that of TPCS alone and TCS, but it has not yet reached the level of TPCS+MBP.
Finite Element Analysis ; Humans ; Femoral Neck Fractures/diagnostic imaging* ; Bone Screws ; Fracture Fixation, Internal/instrumentation* ; Male ; Bone Plates ; Stress, Mechanical ; Biomechanical Phenomena ; Tomography, X-Ray Computed ; Adult ; Femur Neck/surgery*

OBJECTIVE: To explore the differences in the implantation safety and stability of a S ₁ alar-iliac screw (S1AIS) or S2AIS for sacroiliac joint fixation, providing reference for selecting appropriate internal fixation in clinical practice. METHODS: Patients who underwent pelvic CT examination between January 2024 and December 2024 were selected. CT data from 80 patients with normal pelvic structure who met the selection criteria were included in a 1∶1 male to female ratio. CT digital reconstruction technology was used to measure the transverse and longitudinal diameters of the S1AIS and S2AIS insertable ranges, as well as the length, width, and sacral side length of the screw trajectory. The pelvic CT data from 30 patients were randomly selected based on a 1∶1 male to female ratio for three-dimensional (3D) printing of pelvic samples. The S1AIS/S2AIS with a diameter of 6.5 mm and 8.0 mm were implanted at the optimal entry/exit points on the left and right sides, respectively, to observe the perforation of the screw trajectory. The pelvic CT data from 1 patient was randomly selected for 3D printing of 10 pelvic samples to simulate Tile C2 fracture. They were divided into S1AIS group ( n=5) and S2AIS group ( n=5), with one S1AIS and one S2AIS fixation used for posterior sacroiliac joint separation, and the specimen stiffness and maximum load were measured by using an electric tension torsion dual axis universal mechanical tester. RESULTS: The anatomical parameter measurement showed that there was no significant difference in the length and width of the screw trajectory between S1AIS and S2AIS ( P>0.05), but the transverse and longitudinal diameters of the insertable ranges, as well as the sacral side length of the screw trajectory, were all greater than those of S2AIS, with significant differences ( P<0.05). After simulating the implantation of S1AIS and S2AIS with a diameter of 6.5 mm in pelvic specimens, no screw penetration was observed. Both S1AIS and S2AIS with a diameter of 8.0 mm showed screw penetration, with S2AIS having a higher incidence of posterior lateral sacral cortical penetration (46.7%) than S1AIS (3.3%) ( P<0.05). The biomechanical test showed that the stiffness and maximum load of S2AIS were significantly lower than those of S1AIS ( P<0.05). CONCLUSION As a method to fix the sacroiliac joint, the S1AIS has a larger insertable range, a longer sacral side length of the screw trajectory, a lower incidence of posterior lateral cortical rupture of the sacrum, and a greater fixation strength than S2AIS. Therefore, the implantation safety and fixation stability of the S1AIS are superior to S2AIS, and a diameter less than 8.0 mm screws should be selected as S2AIS for Chinese people.
Humans ; Bone Screws ; Sacroiliac Joint/diagnostic imaging* ; Male ; Female ; Sacrum/diagnostic imaging* ; Fracture Fixation, Internal/instrumentation* ; Ilium/diagnostic imaging* ; Tomography, X-Ray Computed ; Middle Aged ; Adult ; Printing, Three-Dimensional ; Aged

OBJECTIVE: To explore the biomechanical characteristics and clinical application effects of three-dimensional (3D) printed osteotomy guide plate combined with Ilizarov technique in the treatment of rigid clubfoot. METHODS: A retrospective analysis was performed on the clinical data of 11 patients with rigid clubfoot who met the inclusion criteria and were admitted between January 2019 and December 2024. There were 6 males and 5 females, aged 21-60 years with an average of 43.2 years. Among them, 5 cases were untreated congenital rigid clubfoot, 4 cases were recurrent rigid clubfoot after previous treatment, and 2 cases were rigid clubfoot due to disease sequelae. All 11 patients first received slow distraction using Ilizarov technique combined with circular external fixator until the force lines of the foot and ankle joint were basically normal. Then, 1 male patient aged 24 years was selected, and CT scanning was used to obtain imaging data of the ankle joint and foot. A 3D finite element model was established and validated using the plantar stress distribution nephogram of the patient. After validation, the biomechanical changes of the tibiotalar joint under the same load were simulated after triple arthrodesis and fixation. The optimal correction angle of the hindfoot was determined to fabricate 3D-printed osteotomy guide plates, and all 11 patients underwent triple arthrodesis using these guide plates. The functional recovery was evaluated by comparing the American Orthopaedic Foot and Ankle Society (AOFAS) score, International Clubfoot Study Group (ICFSG) score, and 36-Item Short Form Survey (SF-36) score before and after operation. RESULTS: Finite element analysis showed that the maximum peak von Mises stress of the tibiotalar joint was at hindfoot varus 3° and the minimum at valgus 6°; the maximum peak von Mises stress of the 3 naviculocuneiform joints under various conditions appeared at lateral naviculocuneiform joint before operation, and the minimum appeared at lateral naviculocuneiform joint at neutral position 0°; the maximum peak von Mises stress of the 5 tarsometatarsal joints under various conditions appeared at the 2nd tarsometatarsal joint at hindfoot neutral position 0°, and the minimum appeared at the 1st tarsometatarsal joint at valgus 6°. Clinical application results showed that the characteristics of clubfoot deformity observed during operation were consistent with the preoperative 3D reconstruction model. All 11 patients were followed up 8-24 months with an average of 13.1 months. One patient had postoperative incision exudation, which healed after dressing change; the remaining patients had good incision healing. All patients achieved good healing of the osteotomy segments, with a healing time of 3-6 months and an average of 4.1 months. At last follow-up, the AOFAS score, SF-36 score, and ICFSG score significantly improved when compared with those before operation ( P<0.05). CONCLUSION The 3D-printed osteotomy guide plate combined with Ilizarov technique has favorable biomechanical advantages in the treatment of rigid clubfoot, with significant clinical application effects. It can effectively improve the foot function of patients and achieve precise and personalized treatment.
Humans ; Clubfoot/diagnostic imaging* ; Printing, Three-Dimensional ; Male ; Osteotomy/instrumentation* ; Female ; Ilizarov Technique/instrumentation* ; Adult ; Retrospective Studies ; Biomechanical Phenomena ; Middle Aged ; Bone Plates ; Young Adult ; Finite Element Analysis ; Treatment Outcome ; Ankle Joint/physiopathology* ; Tomography, X-Ray Computed ; External Fixators

OBJECTIVE: To compare the diagnostic accuracy of supraspinatus muscle outlet X-ray film, oblique sagittal multislice helical CT (MSCT), and oblique sagittal MRI in the diagnosis of subacromial impingement syndrome (SIS). METHODS: A retrospective analysis was conducted on the imaging data of 106 patients diagnosed with SIS between January 2023 and December 2024. The cohort consisted of 32 males and 74 females, with ages ranging from 43 to 70 years (mean, 60.19 years). All patients underwent supraspinatus muscle outlet X-ray film, MSCT, and MRI scans, with MSCT further subjected to three-dimensional reconstruction. Two experienced radiologists independently evaluated the acromion morphology in each imaging modality using the Bigliani classification system. Inter-observer reliability was assessed via Kappa statistics. The CT three-dimensional reconstructions were used as the "gold standard". The overall consistency, Kappa values, sensitivity, and specificity of the three imaging modalities were calculated. Receiver operating characteristic (ROC) curves were plotted, and the area under the curve (AUC) was computed. RESULTS: The inter-observer reliability for supraspinatus muscle outlet X-ray film, oblique sagittal MSCT, and oblique sagittal MRI was moderate, with Kappa values of 0.62, 0.63, and 0.55, respectively. When compared to the CT three-dimensional reconstructions as the "gold standard", the overall consistency was 88.7% (94/106), 62.3% (66/106), and 58.5% (62/106), respectively. The supraspinatus muscle outlet X-ray film showed excellent consistency (Kappa=0.77), whereas the consistency of MSCT and MRI was lower (Kappa=0.34 and 0.29, respectively). In terms of diagnostic sensitivity and specificity, the supraspinatus muscle outlet X-ray film outperformed oblique sagittal MSCT and oblique sagittal MRI in distinguishing various acromion types. ROC analysis demonstrated that the AUC for the supraspinatus muscle outlet X-ray film was consistently higher than for oblique sagittal MSCT and oblique sagittal MRI, with the highest diagnostic performance observed for type Ⅲ hooked acromion (AUC=0.939). CONCLUSION Supraspinatus muscle outlet X-ray film provides the highest diagnostic accuracy for acromion classification in SIS patients, particularly in identifying type Ⅲ hooked acromion, which is strongly associated with SIS. Given its superior sensitivity and consistency, it should be considered the primary screening tool. MSCT and MRI serve as valuable supplementary modalities for complex cases and preoperative evaluation.
Humans ; Middle Aged ; Male ; Female ; Shoulder Impingement Syndrome/diagnostic imaging* ; Magnetic Resonance Imaging/methods* ; Retrospective Studies ; Aged ; Adult ; Imaging, Three-Dimensional ; Sensitivity and Specificity ; Tomography, Spiral Computed/methods* ; Multidetector Computed Tomography/methods* ; Reproducibility of Results