In deep learning-based image registration, the deformable region with complex anatomical structures is an important factor affecting the accuracy of network registration. However, it is difficult for existing methods to pay attention to complex anatomical regions of images. At the same time, the receptive field of the convolutional neural network is limited by the size of its convolution kernel, and it is difficult to learn the relationship between the voxels with far spatial location, making it difficult to deal with the large region deformation problem. Aiming at the above two problems, this paper proposes a cascaded multi-level registration network model based on transformer, and equipped it with a difficult deformable region perceptron based on mean square error. The difficult deformation perceptron uses sliding window and floating window techniques to retrieve the registered images, obtain the difficult deformation coefficient of each voxel, and identify the regions with the worst registration effect. In this study, the cascaded multi-level registration network model adopts the difficult deformation perceptron for hierarchical connection, and the self-attention mechanism is used to extract global features in the basic registration network to optimize the registration results of different scales. The experimental results show that the method proposed in this paper can perform progressive registration of complex deformation regions, thereby optimizing the registration results of brain medical images, which has a good auxiliary effect on the clinical diagnosis of doctors.
Objective To compare the effectiveness and advantages of the double reverse traction reduction technique versus open reduction internal fixation for treating complex tibial plateau fractures. Methods A clinical data of 25 patients with Schatzker type Ⅴ or Ⅵ tibial plateau fractures, who met the selection criteria and were admitted between January 2019 and January 2023, was retrospectively analyzed. Thirteen patients underwent double reverse traction reduction and internal fixation (double reverse traction group), while 12 patients underwent open reduction and internal fixation (traditional open group). There was no significant difference in the baseline data (age, gender, injury mechanism, Schatzker classification, interval between injury and operation) between the two groups (P>0.05). The effectiveness were evaluated and compared between the two groups, included operative time, intraoperative blood loss, incision length, hospital stay, full weight-bearing time, complications, fracture healing, Rasmussen radiological score (reduction quality), knee Hospital for Special Surgery (HSS) score, and knee flexion/extension range of motion. Results The double reverse traction group demonstrated superior outcomes in operative time, blood loss, hospital stay, incision length, and time to full weight-bearing (P<0.05). Two patients in traditional open group developed incisional complications, while the double reverse traction group had no complications. There was no significant difference in the incidence of complication between the two groups (P>0.05). All patients were followed up 24-36 months (mean, 30 months), with no intergroup difference in follow-up duration (P>0.05). Fractures healed in both groups with no significant difference in healing times (P>0.05). At 6 months after operation, Rasmussen radiological scores and grading showed no significant difference (P>0.05); the double reverse traction group had significantly higher HSS scores and grading compared to the traditional open group (P<0.05). At 12 months after operation, knee flexion/extension range of motion were significantly greater in double reverse traction group than in traditional open group (P<0.05). Conclusion Double reverse traction reduction offers advantages over traditional open reduction internal fixation, including shorter operative time, reduced blood loss, minimized soft tissue trauma, and improved joint functional recovery. It is a safe and reliable method for complex tibial plateau fractures.