ObjectiveTo discuss the feasibility and accuracy of distal femoral patient-specific cutting guide in total knee arthroplasty (TKA) based on knee CT and full-length X-ray film of lower extremities. MethodsBetween July 2016 and February 2017, 20 patients with severe knee joint osteoarthritis planned to undergo primary TKA were selected as the research object. There were 9 males and 11 females; aged 53-84 years, with an average of 69.4 years. The body mass index was 22.1-31.0 kg/m2, with an average of 24.8 kg/m2. The preoperative range of motion (ROM) of the knee joint was (103.0±19.4)°, the pain visual analogue scale (VAS) score was 5.4±1.3, and the American Hospital of Special Surgery (HSS) score was 58.1±11.3. Before operation, a three-dimensional model of the knee joint was constructed based on the full-length X-ray film of lower extremities and CT of the knee joint. The distal femoral patient-specific cutting guide was designed and fabricated, and the thickness of the distal femoral osteotomy was determined by digital simulation. The thickness of the internal and external condyle of the distal femur osteotomy before operation and the actual thickness of the intraoperative osteotomy were compared. The intraoperative blood loss, postoperative drainage loss, and hidden blood loss were recorded. The ROM of knee joint, VAS score, and HSS score at 3 months after operation were recorded to evaluate effectiveness. The position of the coronal and sagittal plane of the distal femoral prosthesis were assessed by comparing the femoral mechanical-anatomical angle (FMAA), anatomical lateral distal femoral angle (aLDFA), mechanical femoral tibial angle (mFTA), distal femoral flexion angle (DFFA), femoral prosthesis flexion angle (FPFA), anatomical lateral femoral component angle (aLFC), and the angle of the femoral component and femoral shaft (α angle) between pre- and post-operation.ResultsTKA was successfully completed with the aid of the distal femoral patient-specific cutting guide. There was no significant difference between the thickness of the internal and lateral condyle of the distal femur osteotomy before operation and the actual thickness of the intraoperative osteotomy (P>0.05). All patients were followed up 3 months. All incisions healed by first intention, and there was no complications such as periarticular infection and deep vein thrombosis. Except for 1 patient who was not treated with tranexamic acid, the intraoperative blood loss of the rest 19 patients ranged from 30 to 150 mL, with an average of 73.2 mL; the postoperative drainage loss ranged from 20 to 500 mL, with an average of 154.5 mL; and the hidden blood loss ranged from 169.2 to 1 400.0 mL, with an average of 643.8 mL. At 3 months after operation, the ROM of the knee was (111.5±11.5)°, and there was no significant difference when compared with the preoperative one (t=–1.962, P=0.065). The VAS score was 2.4±0.9 and HSS score was 88.2±7.5, showing significant differences when compared with the preoperative ones (t=7.248, P=0.000; t=–11.442, P=0.000). Compared with the preoperative measurements, there was a significant difference in mFTA (P<0.05), and there was no significant difference in aLDFA, FMAA, or DFFA; compared with the preoperative plan, there was no significant difference in FPFA, aLFC, or α angle (P>0.05). ConclusionThe use of distal femoral patient-specific cutting guide based on knee CT and full-length X-ray film of lower extremity can achieve precise osteotomy, improve coronal and sagittal limb alignment, reduce intraoperative blood loss, and obtain satisfactory short-term effectiveness.
Conducting research on patient-specific electroencephalography-based epilepsy seizure prediction methods enables early identification of seizure risk, providing a basis for timely intervention and treatment. However, existing methods fail to simultaneously account for the dynamic temporal feature differences of electroencephalography signals and the spatial correlations between leads when representing spatio-temporal features, limiting the representation of preictal electroencephalography features and consequently affects prediction performance. To address this issue, this paper proposes a patient-specific electroencephalography seizure prediction method based on global dynamic multi-scale spatio-temporal features. By designing a dynamic temporal attention (DTA) branch, it captures instantaneous dynamic features through convolutional extraction of feature differences between adjacent sampling points, and by designing a multi-scale spatial attention (MSSA) branch, it represents multi-scale spatial features among channels using receptive fields of convolution kernels of different sizes. Furthermore, considering the limited local receptive field of convolution operations, attention modules are introduced into the aforementioned branches to represent global information. Finally, a feature fusion (FF) branch is used to represent global dynamic multi-scale spatio-temporal features, aiming to achieve high-precision epilepsy seizure prediction. The accuracy on two public epilepsy electroencephalography datasets reached 95.36% and 72.98%, with sensitivities of 94.08% and 66.40%, and specificities of 96.91% and 79.55%, respectively. Experimental results indicate that the proposed global dynamic multi-scale spatio-temporal features can effectively characterize the dynamic temporal variations and inter-channel spatial correlations of electroencephalography signals, providing strong support for early warning of epileptic seizures.