Cutaneous malignant melanoma is a common malignant tumor. Accurate segmentation of the lesion area is extremely important for early diagnosis of the disease. In order to achieve more effective and accurate segmentation of skin lesions, a parallel network architecture based on Transformer is proposed in this paper. This network is composed of two parallel branches: the former is the newly constructed multiple residual frequency channel attention network (MFC), and the latter is the visual transformer network (ViT). First, in the MFC network branch, the multiple residual module and the frequency channel attention module (FCA) module are fused to improve the robustness of the network and enhance the capability of extracting image detailed features. Second, in the ViT network branch, multiple head self-attention (MSA) in Transformer is used to preserve the global features of the image. Finally, the feature information extracted from the two branches are combined in parallel to realize image segmentation more effectively. To verify the proposed algorithm, we conducted experiments on the dermoscopy image dataset published by the International Skin Imaging Collaboration (ISIC) in 2018. The results show that the intersection-over-union (IoU) and Dice coefficients of the proposed algorithm achieve 90.15% and 94.82%, respectively, which are better than the latest skin melanoma segmentation networks. Therefore, the proposed network can better segment the lesion area and provide dermatologists with more accurate lesion data.
Objective To study the mutations at 1 573 fragment of TNF receptor II (TNFR-II) gene in patients with keloid. Methods The tissue DNA was extracted from 22 samples of keloids donated by 22 patients (6 males and 16 females, aged 18-53 years), and all keloids were examined and classified by pathologist. The peri pheral blood DNA was extracted from the same patients as the control. PCR was used to ampl ify the 1 573 fragment of TNFR-II gene from the keloid tissue DNA and peripheral blood DNA. The PCR products were sequenced directly and then compared with the GeneBankdata. Results All the concentration of the extracted DNA in trial were higher than 0.50 μg/μL and the purity (A260/A280) ofthe extracted DNA were higher than 1.5. It closed to the magnitude of the design DNA fragment by agarose gel electrophoresis examining, and corresponded with the test requirement. Mutations at 1 573 fragment of TNFR-II gene were detected in 13 out of 22 keloids. The mutation incidence was 59.1%. Among them, 9 had point mutation at codon 1 663, accounting 40.9%. No TNFR-II gene mutation was detected in all peripheral blood samples. There were significant difference between keloids DNA and peripheral blood DNA (P lt;0.01). The mutations involved point mutation, deletion and insertion as well as multisite and multitype. Conclusion There is a correlation between the mutation at 1 573 fragment of TNFR-II gene and keloid.