Purpose To evaluate the effectiveness of deep learning image reconstruction(DLIR)algorithms in reconstructing lumbar vertebrae images from abdominal CT scans,aiming to reduce radiation dose and eliminate the need for repeat lumbar CT examinations.Materials and Methods A retrospective collection was conducted from March to May 2024 in the First Affiliated Hospital of Tianjin University of Traditional Chinese Medicine.Thirty-two patients who underwent both abdominal and lumbar CT scans in a supine head-first position were enrolled.The abdominal CT(DLIR group)utilized a tube voltage of 120 kVp and a current of 200 mA with high-intensity DLIR for lumbar reconstruction.The standard lumbar CT(lumbar group)used the same voltage with a tube current of 260 mA and was reconstructed using 60%weighted adaptive statistical iterative reconstruction.Objective assessments was used to measure the CT values,noise(standard deviation,SD value),signal-to-noise ratio and contrast-to-noise ratio(excluding adipose tissue)at the third lumbar vertebral pedicle level and the L2/L3 intervertebral disc level for muscle,adipose tissue,cancellous bone,intervertebral discs,dura mater and cortical bone.Subjective assessments employed a five-point scale to evaluate image contrast,noise and sharpness.Results The volume CT dose index in lumbar group and DLIR group were 15.25 mGy and 11.74 mGy,respectively.There was no statistical difference in CT values between the structures of both groups(all P>0.05).Compared with the lumbar group,the DLIR group showed significant reductions in SD values across the measured tissues by 31.09%,35.66%,13.48%,27.82%,24.93%and 15.09%(t=5.09-7.21,all P<0.05).The signal-to-noise ratio improved by 36.40%,52.31%,16.56%,34.13%,38.39%and 18.81%,and the contrast-to-noise ratio improved by 51.70%,51.32%,36.24%,34.47%and 53.56%(t=-9.58--4.23,all P<0.001).The DLIR group significantly outperformed the lumbar group in image contrast[4.45(4.00,5.00)points vs.4.75(4.00,5.00)points],image noise[4.06(4.00,4.00)points vs.4.39(4.00,5.00)points],and spatial resolution of fine structures[4.00(4.00,4.00)points vs.4.27(4.00,5.00)points](Z=-3.80,-4.38,-3.55,all P<0.001).Conclusion Using high-intensity DLIR for abdominal examinations can achieve high-quality lumbar CT images with a 25%reduction in radiation dose,enabling simultaneous abdominal and lumbar scanning in a single session.

Objective:To evaluate the accuracy of L-shaped reduction malarplasty under the guidance of virtual surgical planning (VSP).Methods:The data of adult female patients who were diagnosed with zygomatic protrusion or hypertrophy at Department of Orthognathic and Temporo-mandibular Joint Surgery, West China Hospital of Stomatology, Sichuan University, from January 2018 to December 2020 were analyzed retrospectively. L-shaped reduction malarplasty with or without bone resection and with the mortice and tenon joint structure on the zygomatic arch was conducted either by digital procedures comprising VSP and three-dimensional printing titanium templates (digtal surgery group) or by conventional method (control group). The incidence of postoperative complications and the patient postoperative satisfaction [using a Likert scale with a score ranging from 1 to 5, representing very dissatisfied, dissatisfied, average, satisfied and very satisfied, satisfaction rate = (very satisfied + satisfied)/ total number of patients × 100%] were statistically analyzed in the two groups. The differences in the postoperative symmetry of the zygomatic complex between the digital group and the control group were analyzed by three-dimensional cephalometry. The accuracy of VSP in L-shaped reduction malarplasty was evaluated by comparing the preoperative design model with the actual postoperative model in the digital group. The statistical analyses were conducted using SPSS 24.0 software. The chi-square test was used in the comparison of surgical complications and patient satisfaction rates. The symmetry of bilateral landmarks in the three-dimensional direction between the two groups was evaluated using the independent t-test, and the pre- and post-operative measurements in the digital group were compared using paired t-test. Results:A total of 78 patients were included, with 36 in the digital group, aged (25.2±3.6) years, and 42 in the control group, aged (24.3±2.8) years. Satisfactory reduction of zygomatic protrusion or hypertrophy was recognized among all patients. Compared with the control group, the digital group had lower percentage of complications [25% (9/36) vs. 55% (23/42)] and higher postoperative satisfaction [78% (28/36) vs. 48% (20/42)], both of which were statistically significant (all P<0.01). Regarding the symmetry of bilateral zygomatic complexes, the average deviations of ΔZb (bottom point of zygoma) in the digital group in the horizontal, vertical, and sagittal directions [(1.05±0.24), (1.05±0.24), (1.00±0.88) mm] were significantly smaller than those in the control group [(2.03±0.58), (1.32±0.68), (1.47±0.47) mm], with statistically significant differences (all P<0.05). The bone segment movements of virtual plans and actual result in the digital surgery group were measured and showed no obvious difference for the inward movement [(5.42±0.98) mm vs. (5.33±0.93) mm] and the sagittal overlap [(4.87±1.21) mm vs. (4.77±1.32) mm] at the zygoma roots, along with the step length at the long-arm of the L-shaped osteotomy line [(2.43±1.11) mm vs. (2.39±0.89) mm] (all P>0.05). The mean differences of facial width and protrusion measurements between virtual simulations and actual result in the digital group ranged from (1.13±0.47) mm to (2.07±0.88) mm, with no significant differences( P>0.05). Meanwhile, the high resemblance between virtual plans and actual result was depicted via superimposition models, with a deviation controlled within ±0.5 mm. Conclusion:The application of VSP in reduction malarplasty significantly improved surgical accuracy and reduced difficulties in the operation, which would improve patients’ postoperative satisfaction.

Objective To analyze dynamic contrast-enhanced MRI (DCE-MRI) radiomic features using machine learning algorithms, and to develop and validate a predictive model for HER-2 status in breast cancer. Methods The DCE-MRI images of 272 treatment-naive female patients with breast cancer between 2020 and 2022 were included in this study. Regions of interest (ROIs) were manually segmented using 3d-Slicer software, and radiomic features were extracted. All patients were randomly divided into training sets or validation sets at a ratio of 4∶1. The least absolute shrinkage and selection operator (LASSO) algorithm was used for feature screening on the training set, followed by the development of predictive models using six machine learning algorithms. Internal cross-validation was performed to compare the performance differences between the models. The best-performing model was selected, trained on the training set, and evaluated on the validation set. Evaluation metrics included area under the curve (AUC), sensitivity, specificity, precision, and recall rate. Results The clinical data of patients in the training set and validation set showed no significant differences. Five features were identified by the LASSO algorithm. With these features, six machine learning models were developed on the training set, and their predictive performance was internally cross-validated using the bagging method. XGBoost model had the highest mean AUC (0.696), followed by RF model (0.690); XGBoost model had the highest mean precision (0.756), followed by LR and RF models. Therefore, XGBoost was the optimal model. An HER-2 predictive model was built using the XGBoost algorithm on the training set and applied to the validation set. The AUC, precision, sensitivity, and specificity of the predictive model on the validation set were calculated, and ROC curves, precision-recall curves, calibration curves, and decision-making curves were plotted. Conclusion This study constructed and evaluated different DCE-MRI radiomics-based machine learning models for predicting HER-2 status in breast cancer. Among them, XGBoost algorithm performed the best and has the potential to become a new non-invasive method for preoperative prediction of HER-2 status, providing reliable evidence for personalized clinical diagnosis and treatment.

Purpose To evaluate the effectiveness of deep learning image reconstruction(DLIR)algorithms in reconstructing lumbar vertebrae images from abdominal CT scans,aiming to reduce radiation dose and eliminate the need for repeat lumbar CT examinations.Materials and Methods A retrospective collection was conducted from March to May 2024 in the First Affiliated Hospital of Tianjin University of Traditional Chinese Medicine.Thirty-two patients who underwent both abdominal and lumbar CT scans in a supine head-first position were enrolled.The abdominal CT(DLIR group)utilized a tube voltage of 120 kVp and a current of 200 mA with high-intensity DLIR for lumbar reconstruction.The standard lumbar CT(lumbar group)used the same voltage with a tube current of 260 mA and was reconstructed using 60%weighted adaptive statistical iterative reconstruction.Objective assessments was used to measure the CT values,noise(standard deviation,SD value),signal-to-noise ratio and contrast-to-noise ratio(excluding adipose tissue)at the third lumbar vertebral pedicle level and the L2/L3 intervertebral disc level for muscle,adipose tissue,cancellous bone,intervertebral discs,dura mater and cortical bone.Subjective assessments employed a five-point scale to evaluate image contrast,noise and sharpness.Results The volume CT dose index in lumbar group and DLIR group were 15.25 mGy and 11.74 mGy,respectively.There was no statistical difference in CT values between the structures of both groups(all P>0.05).Compared with the lumbar group,the DLIR group showed significant reductions in SD values across the measured tissues by 31.09%,35.66%,13.48%,27.82%,24.93%and 15.09%(t=5.09-7.21,all P<0.05).The signal-to-noise ratio improved by 36.40%,52.31%,16.56%,34.13%,38.39%and 18.81%,and the contrast-to-noise ratio improved by 51.70%,51.32%,36.24%,34.47%and 53.56%(t=-9.58--4.23,all P<0.001).The DLIR group significantly outperformed the lumbar group in image contrast[4.45(4.00,5.00)points vs.4.75(4.00,5.00)points],image noise[4.06(4.00,4.00)points vs.4.39(4.00,5.00)points],and spatial resolution of fine structures[4.00(4.00,4.00)points vs.4.27(4.00,5.00)points](Z=-3.80,-4.38,-3.55,all P<0.001).Conclusion Using high-intensity DLIR for abdominal examinations can achieve high-quality lumbar CT images with a 25%reduction in radiation dose,enabling simultaneous abdominal and lumbar scanning in a single session.

Objective:To evaluate the accuracy of L-shaped reduction malarplasty under the guidance of virtual surgical planning (VSP).Methods:The data of adult female patients who were diagnosed with zygomatic protrusion or hypertrophy at Department of Orthognathic and Temporo-mandibular Joint Surgery, West China Hospital of Stomatology, Sichuan University, from January 2018 to December 2020 were analyzed retrospectively. L-shaped reduction malarplasty with or without bone resection and with the mortice and tenon joint structure on the zygomatic arch was conducted either by digital procedures comprising VSP and three-dimensional printing titanium templates (digtal surgery group) or by conventional method (control group). The incidence of postoperative complications and the patient postoperative satisfaction [using a Likert scale with a score ranging from 1 to 5, representing very dissatisfied, dissatisfied, average, satisfied and very satisfied, satisfaction rate = (very satisfied + satisfied)/ total number of patients × 100%] were statistically analyzed in the two groups. The differences in the postoperative symmetry of the zygomatic complex between the digital group and the control group were analyzed by three-dimensional cephalometry. The accuracy of VSP in L-shaped reduction malarplasty was evaluated by comparing the preoperative design model with the actual postoperative model in the digital group. The statistical analyses were conducted using SPSS 24.0 software. The chi-square test was used in the comparison of surgical complications and patient satisfaction rates. The symmetry of bilateral landmarks in the three-dimensional direction between the two groups was evaluated using the independent t-test, and the pre- and post-operative measurements in the digital group were compared using paired t-test. Results:A total of 78 patients were included, with 36 in the digital group, aged (25.2±3.6) years, and 42 in the control group, aged (24.3±2.8) years. Satisfactory reduction of zygomatic protrusion or hypertrophy was recognized among all patients. Compared with the control group, the digital group had lower percentage of complications [25% (9/36) vs. 55% (23/42)] and higher postoperative satisfaction [78% (28/36) vs. 48% (20/42)], both of which were statistically significant (all P<0.01). Regarding the symmetry of bilateral zygomatic complexes, the average deviations of ΔZb (bottom point of zygoma) in the digital group in the horizontal, vertical, and sagittal directions [(1.05±0.24), (1.05±0.24), (1.00±0.88) mm] were significantly smaller than those in the control group [(2.03±0.58), (1.32±0.68), (1.47±0.47) mm], with statistically significant differences (all P<0.05). The bone segment movements of virtual plans and actual result in the digital surgery group were measured and showed no obvious difference for the inward movement [(5.42±0.98) mm vs. (5.33±0.93) mm] and the sagittal overlap [(4.87±1.21) mm vs. (4.77±1.32) mm] at the zygoma roots, along with the step length at the long-arm of the L-shaped osteotomy line [(2.43±1.11) mm vs. (2.39±0.89) mm] (all P>0.05). The mean differences of facial width and protrusion measurements between virtual simulations and actual result in the digital group ranged from (1.13±0.47) mm to (2.07±0.88) mm, with no significant differences( P>0.05). Meanwhile, the high resemblance between virtual plans and actual result was depicted via superimposition models, with a deviation controlled within ±0.5 mm. Conclusion:The application of VSP in reduction malarplasty significantly improved surgical accuracy and reduced difficulties in the operation, which would improve patients’ postoperative satisfaction.

Objective:In this retrospective study, the accuracy and outcomes of segmental Le Fort I surgery with the aid of 3D-printed surgical templates and occlusal splints and dental model surgery were evaluated.Methods:Clinical data of patients receiving segmental Le Fort I surgery in the Department of Orthognathic and Temporo-Mandibular Joint Surgery of West China Stomatological Hospital of Sichuan University from January 2014 to June 2019 were retrospectively analyzed. The accuracy of virtual surgical planning(VSP) and the difference between VSP and dental model surgery were evaluated by postoperative complications, color distance maps, and quantitative accuracy analysis.The amount of surgical displacement of the maxilla in the three-dimensional direction before and after surgery, the occurrence of postoperative complications and the patients'satisfaction survey were analyzed in both groups. Paired t-tests were used for the linear distance and angle between the preoperative design model and the final virtual surgery model in the digital surgery group. Independent samples t-test was used for each marker point’s preoperative and postoperative displacements in the three-dimensional direction between the digital surgery group and the dental model group. The proportion of postoperative complications in the 2 groups was tested using the Pearson chi-square test, and the difference was considered statistically significant at P<0.05. Results:There were 129 patients in the digital surgery group, 35 males and 94 females, aged (24.5±6.5) years, and 92 patients in the dental model surgery group, 28 males and 64 females, aged (27.7±5.4) years.The overall mean linear difference was 1.23±0.35 mm, and the overall mean angular difference was 2.48°±0.31°. The vertical displacement of U3R, U6L in the digital surgery group was (6.72±1.57)mm and (4.73±2.07)mm. The vertical displacement of U3R, U6L in the group of dental model surgery was (4.07±2.14)mm and (1.62±1.82)mm.The significant deviation difference in U3R-Y and U6L-Y between two groups could be detected. The complications in two groups showed a significant difference. Except for one case of root injury, there was no serious complication recorded in the digital surgery group. However, there were three cases of palatal fistulas, four cases of root injury and two cases of bone dehiscence in the dental model group. 94.5% of patients in the digital surgery group are satisfied with the surgical results, while 89.1% in the dental model group.Conclusion:Compared with dental model surgery, segmental Le Fort I surgery is highly accurate under the guidance of surgical templates and occlusal splint which has better postoperative results and effectively reduces the occurrence of surgical complications.

Objective:To evaluate the stability of the zygomatic complex in reduction malarplasty (RM) with different fixation method.Methods:The clinical data of patients with zygomatic arch protrusion at the Department of Orthognathic and Temporomandibular Joint Surgery, West China Hospital of Stomatology, Sichuan University from January 2018 to January 2021 were analyzed retrospectively. All patients underwent L-shaped osteotomy reduction malarplasty which were divided into zygomatic body fixation (ZBF) and zygomatic arch fixation (ZAF) according to fixation technique. As for ZBF, there were 4 different groups including two bicortical screws (2LS), an L-shaped plate with one bicortical screw (LPLS), an L-shaped plate with short-wing on the zygoma (LPwZ) and an L-shaped plate with short-wing on the maxilla (LPwM). As for ZAF, there were 3 different groups including mortice-tenon (MT), 3-hole plate (3HP) and short screw (SS). CT imaging data of two postoperative periods (1 week later; 6 months later) were collected. ITK-SNAP and 3D Slicer software were applied to evaluate the difference in the displacement distance of relevant landmarks of the zygomatic complex, so as to compare the postoperative stability of RM under different fixation methods. Statistical analyses were performed using IBM SPSS Statistics, version 25.0, and Kruskal-Wallis method was used to compare the difference of relevant landmarks displacement distance between ZBF group and ZAF group. P<0.05 was considered statistically significant. Results:60 patients (120 zygomatic arches) who were composed of 21 men and 39 women, aged (27.1±4.9) years were included. There were 30 samples in each group of ZBF and 40 samples in each group of ZAF. Compared with the single L-shaped plate (LPwZ, LPwM) group, the displacement distance of zygomatic complex in 2LS and LPLS groups was shorter ( P<0.05). The three fixation method of zygomatic arch (MT, 3HP, SS) had similar effects on the displacement of zygomatic complex ( P>0.05). Conclusion:After RM, the "two-bridge" fixation method (2LS and LPLS) provides better stability than the single L-shaped plate. The stability of all ZAF is similar when combined with 2LS or LPLS.

Objective To investigate the effects of volumetric modulated arc therapy (VMAT) with 6 MV and 10 MV X-ray photon energies in patients with cervical cancer. Methods From March 2019 to May 2020, 24 patients with cervical cancer who underwent radiation therapy in the Oncology Radiotherapy Department of our hospital were selected. VMAT plans with 6 MV and 10 MV photon energies were re-designed for each patient. The target parameters (D_98%, D_2%, D_mean), conformal index, and homogeneity index of the two groups were compared. The radiation doses received by the bladder, rectum, small intestine, left femoral head, right femoral head, and normal tissue other than planning target volume (Body-PTV), as well as monitor units and estimated total delivery time, were also compared. Results D_2%, D_mean, homogeneity index, and monitor units were significantly lower in the 10 MV group than in the 6 MV group (50.78 ± 0.33 Gy vs. 50.35 ± 0.29 Gy; 49.05 ± 0.2 Gy vs. 48.93 ± 0.17 Gy; 0.08 ± 0.01 vs. 0.07 ± 0.01; 1179.26 ± 110.55 vs. 1099.3 ± 80.9). Comparison of organs at risk showed that compared with the 10 MV group, the 6 MV group demonstrated significantly lower V_40Gy of the bladder, D_5% of the right femoral head, and D_2% and V_5Gy of Body-PTV (60.37 ± 13.66 vs. 60.84 ± 13.88; 37.09 ± 5.43 Gy vs. 38.03 ± 5.68 Gy; 41.71 ± 1.39 Gy vs. 42.16 ± 1.31 Gy; 47.88 ± 9.75 vs. 48.23 ± 9.74). There were no significant differences in other parameters between the two groups. Conclusion The VMAT plans with 6 MV and 10 MV X-ray photon energies both meet the clinical needs of cervical cancer radiotherapy. The cervical cancer VMAT plan with 6 MV photon energy is recommended due to better protection of the organs at risk.

Objective To investigate the effects of volumetric modulated arc therapy (VMAT) with 6 MV and 10 MV X-ray photon energies in patients with cervical cancer. Methods From March 2019 to May 2020, 24 patients with cervical cancer who underwent radiation therapy in the Oncology Radiotherapy Department of our hospital were selected. VMAT plans with 6 MV and 10 MV photon energies were re-designed for each patient. The target parameters (D_98%, D_2%, D_mean), conformal index, and homogeneity index of the two groups were compared. The radiation doses received by the bladder, rectum, small intestine, left femoral head, right femoral head, and normal tissue other than planning target volume (Body-PTV), as well as monitor units and estimated total delivery time, were also compared. Results D_2%, D_mean, homogeneity index, and monitor units were significantly lower in the 10 MV group than in the 6 MV group (50.78 ± 0.33 Gy vs. 50.35 ± 0.29 Gy; 49.05 ± 0.2 Gy vs. 48.93 ± 0.17 Gy; 0.08 ± 0.01 vs. 0.07 ± 0.01; 1179.26 ± 110.55 vs. 1099.3 ± 80.9). Comparison of organs at risk showed that compared with the 10 MV group, the 6 MV group demonstrated significantly lower V_40Gy of the bladder, D_5% of the right femoral head, and D_2% and V_5Gy of Body-PTV (60.37 ± 13.66 vs. 60.84 ± 13.88; 37.09 ± 5.43 Gy vs. 38.03 ± 5.68 Gy; 41.71 ± 1.39 Gy vs. 42.16 ± 1.31 Gy; 47.88 ± 9.75 vs. 48.23 ± 9.74). There were no significant differences in other parameters between the two groups. Conclusion The VMAT plans with 6 MV and 10 MV X-ray photon energies both meet the clinical needs of cervical cancer radiotherapy. The cervical cancer VMAT plan with 6 MV photon energy is recommended due to better protection of the organs at risk.

Objective:In this retrospective study, the accuracy and outcomes of segmental Le Fort I surgery with the aid of 3D-printed surgical templates and occlusal splints and dental model surgery were evaluated.Methods:Clinical data of patients receiving segmental Le Fort I surgery in the Department of Orthognathic and Temporo-Mandibular Joint Surgery of West China Stomatological Hospital of Sichuan University from January 2014 to June 2019 were retrospectively analyzed. The accuracy of virtual surgical planning(VSP) and the difference between VSP and dental model surgery were evaluated by postoperative complications, color distance maps, and quantitative accuracy analysis.The amount of surgical displacement of the maxilla in the three-dimensional direction before and after surgery, the occurrence of postoperative complications and the patients'satisfaction survey were analyzed in both groups. Paired t-tests were used for the linear distance and angle between the preoperative design model and the final virtual surgery model in the digital surgery group. Independent samples t-test was used for each marker point’s preoperative and postoperative displacements in the three-dimensional direction between the digital surgery group and the dental model group. The proportion of postoperative complications in the 2 groups was tested using the Pearson chi-square test, and the difference was considered statistically significant at P<0.05. Results:There were 129 patients in the digital surgery group, 35 males and 94 females, aged (24.5±6.5) years, and 92 patients in the dental model surgery group, 28 males and 64 females, aged (27.7±5.4) years.The overall mean linear difference was 1.23±0.35 mm, and the overall mean angular difference was 2.48°±0.31°. The vertical displacement of U3R, U6L in the digital surgery group was (6.72±1.57)mm and (4.73±2.07)mm. The vertical displacement of U3R, U6L in the group of dental model surgery was (4.07±2.14)mm and (1.62±1.82)mm.The significant deviation difference in U3R-Y and U6L-Y between two groups could be detected. The complications in two groups showed a significant difference. Except for one case of root injury, there was no serious complication recorded in the digital surgery group. However, there were three cases of palatal fistulas, four cases of root injury and two cases of bone dehiscence in the dental model group. 94.5% of patients in the digital surgery group are satisfied with the surgical results, while 89.1% in the dental model group.Conclusion:Compared with dental model surgery, segmental Le Fort I surgery is highly accurate under the guidance of surgical templates and occlusal splint which has better postoperative results and effectively reduces the occurrence of surgical complications.