ABSTRACT
Objective:To develop a preoperative CT image segmentation algorithm based on artificial intelligence deep learning technology for total hip arthroplasty (THA) revision surgery, and to verify and preliminarily apply it.Methods:A total of 706 revision cases with clear CT data from April 2019 to October 2022 in Chinese PLA General Hospital were retrospectively analyzed, including 520 males, aged 58.45±18.13 years, and 186 females, aged 52.23±16.23 years. All of them were unilateral, and there were 402 hips on the left and 304 hips on the right. The transformer_unet convolutional neural network was constructed and trained using Tensorflow 1.15 to achieve intelligent segmentation of the revision THA CT images. Based on the developed three-dimensional planning system of total hip arthroplasty, an intelligent planning system for revision hip arthroplasty was preliminarily constructed. Dice overlap coefficient (DOC), average surface distance (ASD) and Hausdorff distance (HD) parameters were used to evaluate the segmentation accuracy of transformer_unet, full convolution network (FCN), 2D U-shaped Net and Deeplab v3 +, and segmentation time was used to evaluate the segmentation efficiency of these networks.Results:Compared with the FCN, 2D U-Net, and Deeplab v3+ learning curves, the transformer_unet network could achieve better training effect with less training amount.The DOC of transformer_unet was 95%±4%, the HD was 3.35±1.03 mm, and the ASD was 1.38±0.02 mm; FCN was 94%±4%, 4.83±1.90 mm, 1.42±0.03 mm; 2D U-Net was 93%±5%, 5.27±2.20 mm, and 1.46±0.02 mm, respectively. Deeplab v3+ was 92%±4%, 6.12±1.84 mm, 1.52±0.03 mm, respectively. The transformer_unet coefficients were better than those of the other three convolutional neural networks, and the differences were statistically significant (all P<0.05). The segmentation time of transformer_unet was 0.031±0.001 s, FCN was 0.038±0.002 s, 2D U-Net was 0.042±0.001 s, Deeplab v3+ was 0.048±0.002 s. The segmentation time of transformer_unet was less than that of the other three convolutional neural networks, and the difference was statistically significant ( P<0.05). Based on the results of previous studies, an artificial intelligence assisted preoperative planning system for THA revision surgery was initially constructed. Conclusion:Compared with FCN, 2D U-Net and Deeplab v3+, the transformer_unet convolutional neural network can complete the segmentation of the revision THA CT image more accurately and efficiently, which is expected to provide technical support for preoperative planning and surgical robots.
ABSTRACT
Objective:To investigate the clinical efficacy of preoperative three-dimensional (3D) reconstruction planning in total hip arthroplasty for development dysplasia of the hip secondary to osteoarthritis.Methods:A total of 80 patients with osteoarthritis secondary to Crowe I-III developmental dysplasia of the hip who underwent primary unilateral total hip arthroplasty from October 2019 to March 2021 were retrospectively analyzed, including 18 males and 62 females and the mean age was 55.7±10.4 years (range 41-72 years). Forty patients in the 3D group, the prosthesis type and installation angle were planed on the 3D reconstruction software based on the full-length CT scan data of the lower limbs, and the length difference of the lower limbs and hip offset were calculated. Forty patients in the control group underwent preoperative planning using conventional film measurement, and lower limb length was judged based on the preoperative measurement data and intraoperative comparison of both lower limbs. The difference of postoperative leg length, hip offset, hip function score, operating time, intraoperative blood loss, and incidence of complications were compared between the two groups.Results:All 80 patients completed the surgery successfully and the follow-up time was up to 3 months after operation. The 3D group was better than the control group in operation time (70.9±7.7 min vs. 81.6±13.3 min, t=-4.91, P<0.001), the difference of postoperative lower limb length (2.78±1.31 cm vs. 5.35±2.15 cm, t=-5.74, P<0.001), and hip function score at 1 week after operation (75.67±3.35 vs. 67.35±4.21, t=12.33, P=0.002), with statistically significant differences. In the 3D group, 95% of acetabular prosthesis and 90% of femoral stem components were consistent with the planned model, while the rate were only 75% and 68% in the control group, and the difference was statistically significant (χ 2=7.51, P=0.023; χ 2=14.92, P=0.005). There were no intraoperative complications such as vascular and nerve injury, and no postoperative complications such as dislocation or periprosthetic infection in all 80 patients. Conclusion:3D preoperative planning assisted total hip arthroplasty in the treatment of Crowe I-III developmental dysplasia of the hip secondary to osteoarthritis can improve the accuracy of the operation, and has a good clinical effect on restoring the leg length and hip offset.
ABSTRACT
Objective:To develop a set of algorithms that could predict the precise size of acetabular cup preoperatively by the deep learning neural network technology.Methods:Retrospective analysis was performed on 30 patients with femoral head necrosis from April 2019 to April 2020, including 15 males and 15 females. At the age of (54.8±10.5) years (range 33-72 years). Thirteen hips on the left and seventeen hips on the right, who underwent primary unilateral THA. Based on the manually segmented hip joint CT database, a deep learning convolutional neural network was trained to realize automatic segmentation. A customized algorithm was created to fit the surface of the acetabulum. By the application of another deep learning convolutional neural network, the identification of anatomical points of the pelvis and correction of the pelvic position were realized. So that the placement of the acetabulum cup could be done. DOC (dice overlap coefficients) as well as the average error parameter were adopted to evaluate the accuracy of the above steps. The novel algorithm and Orthoview software were retrospectively used to template the acetabular cup separately. The results of both groups were compared with the actual size and the coincidence rate was calculated to evaluate the accuracy of the novel algorithm. To verify this algorithm, the conformance rate was calculated respectively.Results:Compared with other classical segmentation networks, the G-NET network can segment the pelvic with femoral head necrosis more accurately (DOC 92.51%± 6.70%). It also has better robustness. The average error of the point recognition network is 0.87 pixels. Among the 30 patients, the AI-based algorithm group had a complete coincidence rate of 96.7% and the Orthoview group had a complete coincidence rate of 73.3%. The difference was statistically significant ( χ2=6.405, P=0.011). Conclusion:The artificial intelligence-based algorithm can segment the CT image series and identify the feature points of the patient's hip accurately. Compared with the conventional 2D preoperative planning method, the AI-based algorithm is relatively more accurate. This artificial intelligence-based 3D preoperative software has promising prospect to makeaccurate surgical plan efficiently.
ABSTRACT
Objective To investigate the anti-erythropoietin antibody level and its clinical significance in maintenance dialysis patients. Methods Eighty maintenance hemodialysis (HD) and 30 peritoneal dialysis (PD) patients were enrolled in the study. Serum anti-erythropoietin antibody levels of above 110 dialysis patients were measured by ELISA. Immunoreactive parathyroid hormone (iPTH), Scr, BUN, Hb, and CRP were determined by conventional methods at the same time. Correlations among these indexes were examined. Results The anti-erythropoietin antibody levels of the dialysis patients were significantly higher than those of healthy people (P＜0.05), but no significant difference was found between HD patients and PD patients. There were no significant differences of anti-erythropoietin antibody, Hb, BUN, Scr, iPTH and CRP among different primary diseases. Hb was negatively correlated with anti-erythropoietin antibody and CRP (r=-0.56, -0.20,P ＜0.05), but was not correlated with BUN, Scr, iPTH. There was no correlation of antierythropoietin antibody with BUN, Scr, CRP and iPTH. One patient receiving recombinant human erythropoietin (rHuEPO) treatment with anti-erythropoietin antibody 43.63 U/L developed pure red cell aplasia diagnosed by marrow biopsy. Conclusions The anti-erythropoietin antibody levels of the dialysis patients are significantly higher as compared to healthy people, but are not significantly different between HD and PD patients. Anti-erythropoietin antibody is not correlated with BUN, Scr,iPTH and CRP. Hb is negatively correlated with anti-erythropoietin antibody and CRP. The rHuEPO can induce the anti-erythropoietin antibody leading to pure red cell aplasia in dialysis patients.
ABSTRACT
This paper introduces the perioperative nursing of 47 patients undergoing intraperitoneal parastomal hernia repair.After the surgery,two cases suffered from incision infection and two cases with subcutaneous hydrops.Three patients suffered from chronic pain or foreign bodies sensation,which disappeared at 3-6 months later.No recurrence occurred at 6-24 months after the surgery.It is suggested that the key points of perioperative nursing were careful preoperative symptom care and bowel preparation,as well as postoperative observation and correct discharge instruction.
ABSTRACT
For decades, coping has undergone intensive investigation through different theoretical lens. In this paper, three theoretical standings in coping research were proposed:namely,the process theory, the trait theory and the situation theory. Relevant research and measurements were introduced. In the end, different perspectives were reevaluated and implication for further research was discussed.