Cranial defects may result from clinical brain tumor surgery or accidental trauma. The defect skulls require hand-designed skull implants to repair. The edge of the skull implant needs to be accurately matched to the boundary of the skull wound with various defects. For the manual design of cranial implants, it is time-consuming and technically demanding, and the accuracy is low. Therefore, an informer residual attention U-Net (IRA-Unet) for the automatic design of three-dimensional (3D) skull implants was proposed in this paper. Informer was applied from the field of natural language processing to the field of computer vision for attention extraction. Informer attention can extract attention and make the model focus more on the location of the skull defect. Informer attention can also reduce the computation and parameter count from N2 to log(N). Furthermore,the informer residual attention is constructed. The informer attention and the residual are combined and placed in the position of the model close to the output layer. Thus, the model can select and synthesize the global receptive field and local information to improve the model accuracy and speed up the model convergence. In this paper, the open data set of the AutoImplant 2020 was used for training and testing, and the effects of direct and indirect acquisition of skull implants on the results were compared and analyzed in the experimental part. The experimental results show that the performance of the model is robust on the test set of 110 cases fromAutoImplant 2020. The Dice coefficient and Hausdorff distance are 0.940 4 and 3.686 6, respectively. The proposed model reduces the resources required to run the model while maintaining the accuracy of the cranial implant shape, and effectively assists the surgeon in automating the design of efficient cranial repair, thereby improving the quality of the patient’s postoperative recovery.
Objective To investigate the feasibility and efficacy of transcatheter directed thrombolysis （TDT） approach in treatment for deep venous thrombosis （DVT） of lower limbs and as compared with trans-dorsal pedis vein thrombolysis （TPVT） approach. Methods The clinical data of 437 patients with acute DVT （184 males and 253 females） at the age of （43±12） years （range 19-76 years） from July 2008 to January 2012 in the First Affiliated Hospital of Zhengzhou University were analyzed retrospectively. Patients in the group TDT received TDT were 293 cases， 32 inferior vena cava filters were implanted. Patients in the group TPVT received TPVT were 65 cases， 4 inferior vena cava filters were implanted. Results The resolution time of thrombus in the group TDT was shorter than that in the group TPVT （6 d versus 9 d， P＜0.05）. The circumference difference of leg or upper leg before and after treatment in the TDT group was significantly greater than that in the TPVT group （P＜0.05）. The rate of venous patency was （65.2±15.4）% and preservation rate of valvular function was （78.2±12.6）% in the group TDT， and which was （63.8±16.3）% and （91.1±10.7）% in the group TPVT， respectively. The differences of venous patency rate was not statistically significant（P＞0.05） between two groups， but the prevervation rate of valvular function was significant difference （P＜0.05） .Hematomas in 3 cases and gross hematuria in 4 cases were observed， and displacement of inferior vena cava filter occurred in 1 patient in the group TDT. The gums bleed or gross hematuria in 5 cases were observed in the group TPVT. Conclusions Both TDT and TPVT can effectively relieve symptoms. TDT can shorten the course of disease， but itincreases functional damage of the deep vein valvular.