Regarding to the channel selection problem during the classification of electroencephalogram (EEG) signals, we proposed a novel method, Relief-SBS, in this paper. Firstly, the proposed method performed EEG channel selection by combining the principles of Relief and sequential backward selection (SBS) algorithms. And then correlation coefficient was used for classification of EEG signals. The selected channels that achieved optimal classification accuracy were considered as optimal channels. The data recorded from motor imagery task experiments were analyzed, and the results showed that the channels selected with our proposed method achieved excellent classification accuracy, and also outperformed other feature selection methods. In addition, the distribution of the optimal channels was proved to be consistent with the neurophysiological knowledge. This demonstrates the effectiveness of our method. It can be well concluded that our proposed method, Relief-SBS, provides a new way for channel selection.
A new method based on convolution kernel compensation (CKC) for decomposing multi-channel surface electromyogram (sEMG)signals is proposed in this paper. Unsupervised learning and clustering function of self-organizing map (SOM) neural network are employed in this method. An initial innervations pulse train (IPT) is firstly estimated, some time instants corresponding to the highest peaks from the initial IPT are clustered by SOM neural network. Then the final IPT can be obtained from the observations corresponding to these time instants. In this paper, the proposed method was tested on the simulated signal, the influence of signal to noise ratio (SNR), the number of groups clustered by SOM and the number of highest peaks selected from the initial pulse train on the number of reconstructed sources and the pulse accuracy were studied, and the results show that the proposed approach is effective in decomposing multi-channel sEMG signals.
ObjectiveTo explore the feasibility and technical essentials of soft tissue defect reconstruction of the lower extremity using the distally based anteromedial thigh flap (dAMT) pedicled with perforating vessels from rectus femoris branch. MethodsBetween July 2008 and December 2015, 6 patients underwent defect reconstruction of the lower extremity using the dAMT flap pedicled with perforating vessels from rectus femoris branch. There were 4 males and 2 females with an average age of 34 years (range, 4-55 years). The etiologies included liposarcoma in 1 case, malignant fibrous histocytoma in 1 case, post-burn scar contracture around the ankle in 1 case, and post-burn scar contracture around the knee in 3 cases. The disease duration ranged from 3 to 28 months (mean, 13 months). After resection of lesion tissues, the defect size ranged from 13 cm×7 cm to 24 cm×12 cm. The flap size ranged from 15 cm×8 cm to 24 cm×12 cm. The length of the pedicle ranged from 10 to 25 cm (mean, 19.8 cm). The distance from the flap pivot point to the superolateral border of the patella ranged from 8 to 13 cm (mean, 11.3 cm). The donor sites were directly sutured. ResultsAll flaps survived postoperatively without any complications. All wounds at the donor and the recipient sites healed primarily. The patients were followed up from 5 to 36 months (mean, 17.8 months). The color, texture, and thickness of the flaps were similar to those of the surrounding skin. No tumor recurrence was observed. The range of motion of flexion and extension of the joint were greatly improved in the patients with scar contracture. ConclusionIf the rectus femoris branch gives off cutaneous branch to the anteromedial thigh region and arises from the descending branch of the lateral circumflex femoral artery, a dAMT flap could be raised to reconstruct soft tissue defects of the lower extremity.
ObjectiveTo explore the feasibility and technical essentials of soft tissue defect reconstruction following malignant tumor removal of limbs using perforator propeller flaps. MethodBetween July 2008 and July 2015, 19 patients with malignant limb tumor underwent defect reconstruction following tumor removal using the perforator propeller flaps. There were 13 males and 6 females with an average age of 53.4 years (range, 20-82 years). The disease duration ranged from 1 to 420 months (mean, 82 months). The tumors located at the thigh in 10 cases, at the leg in 2 cases, at the arm in 1 case, at the forearm in 1 case, around the knee in 2 cases, and around the elbow joint in 3 cases. Totally 23 flaps (from 8 cm×3 cm to 30 cm×13 cm in size) were used to reconstruct defects (from 4 cm×4 cm to 24 cm×16 cm in size). The potential source arteries included the femoral artery (n=2) , profunda femoral artery (n=3) , superficial circumflex iliac artery (n=1) , lateral circumflex femoral artery (n=6) , superior lateral genicular artery (n=2) , peroneal artery (n=2) , anterior tibial artery (n=1) , brachial artery (n=4) , and radial artery (n=1) . The remaining one was a free style perforator flap. ResultsPartial distal flap necrosis occurred in 3 cases after surgery with rotation angles of 180, 150, and 100° respectively, which were reconstructed after debridement using a free-style perforator flap in 1 case and using free skin grafting in the other 2 cases. The other 20 flaps survived completely after surgery. Primary healing of incisions was obtained at the donor and recipient sites. There was no severe complication such as infection, hematoma, and total flap failure. All patients were followed up 3 months to 5 years (mean, 19 months). One patient with malignant melanoma around the elbow joint had tumor recurrence, and underwent secondary tumor resection. The appearance, texture, and color of the flaps were similar to those at the recipient site. ConclusionsFor patients with malignant tumor of the limb, the perforator propeller flap can be an alternative option for soft tissue defect reconstruction after tumor resection, with the advantages of relatively simple operation and remaining the main vessels.