The accurate segmentation of breast ultrasound images is an important precondition for the lesion determination. The existing segmentation approaches embrace massive parameters, sluggish inference speed, and huge memory consumption. To tackle this problem, we propose T ²KD Attention U-Net (dual-Teacher Knowledge Distillation Attention U-Net), a lightweight semantic segmentation method combined double-path joint distillation in breast ultrasound images. Primarily, we designed two teacher models to learn the fine-grained features from each class of images according to different feature representation and semantic information of benign and malignant breast lesions. Then we leveraged the joint distillation to train a lightweight student model. Finally, we constructed a novel weight balance loss to focus on the semantic feature of small objection, solving the unbalance problem of tumor and background. Specifically, the extensive experiments conducted on Dataset BUSI and Dataset B demonstrated that the T ²KD Attention U-Net outperformed various knowledge distillation counterparts. Concretely, the accuracy, recall, precision, Dice, and mIoU of proposed method were 95.26%, 86.23%, 85.09%, 83.59%and 77.78% on Dataset BUSI, respectively. And these performance indexes were 97.95%, 92.80%, 88.33%, 88.40% and 82.42% on Dataset B, respectively. Compared with other models, the performance of this model was significantly improved. Meanwhile, compared with the teacher model, the number, size, and complexity of student model were significantly reduced (2.2×10 ⁶ vs. 106.1×10 ⁶, 8.4 MB vs. 414 MB, 16.59 GFLOPs vs. 205.98 GFLOPs, respectively). Indeedy, the proposed model guarantees the performances while greatly decreasing the amount of computation, which provides a new method for the deployment of clinical medical scenarios.
Humans ; Breast Neoplasms/diagnostic imaging* ; Female ; Ultrasonography, Mammary/methods* ; Image Processing, Computer-Assisted/methods* ; Algorithms ; Neural Networks, Computer ; Breast/diagnostic imaging*

Objective:To evaluate the expression of semaphorin 5B (SEMA5B) in gastric adenocarcinoma and its relationship with prognosis.Methods:In November 2019, the clinicopathological characteristics and SEMA5B mRNA expression data of 341 patients with gastric adenocarcinoma were collected through TCGA database. The relationship between SEMA5B expression in gastric adenocarcinoma tissues and clinical pathologic features and overall survival were analyzed. Gene Set Enrichment Analysis (GSEA) was used to analyze the signaling pathways regulated by SEMA5B.Results:The expression level of SEMA5B mRNA in 341 gastric adenocarcinoma tissues was 0.577±0.587, in adjacent normal tissues was 0.132±0.075, the difference was statistically significant ( P<0.001). The median survival time of 109 patients with high expression of SEMA5B mRNA was 14.5 months, 232 patients with low expression of SEMA5B mRNA was 17.9 months ( P=0.047). Univariate analysis showed that the expression of SEMA5B mRNA was correlated with histological grade and T stage ( P<0.05). The multivariate analysis revealed that age<65 years remained independently associated with overall survival, with a hazard ratio( HR) of 1.042 (95% CI: 1.021-1.064). The multivariate analysis revealed that high expression of SEMA5b mRNA remained independently associated with overall survival, with a HR of 1.195 (95% CI: 0.925-2.551). GSEA showed that malignant tumor signaling pathways ( P=0.008), MAPK signaling pathways ( P=0.047) and Notch signaling pathways ( P=0.029) were differentially enriched in SEMA5B highly expressed phenotype. Conclusions:SEMA5B expression may be a potential prognostic molecular marker for prognosis of GAC patients. Moreover, malignant tumor signaling pathway, MAPK signaling pathway and Notch signaling pathway may be the key pathway regulated by SEMA5B in GAC.

Objective:To evaluate the expression of semaphorin 5B (SEMA5B) in gastric adenocarcinoma and its relationship with prognosis.Methods:In November 2019, the clinicopathological characteristics and SEMA5B mRNA expression data of 341 patients with gastric adenocarcinoma were collected through TCGA database. The relationship between SEMA5B expression in gastric adenocarcinoma tissues and clinical pathologic features and overall survival were analyzed. Gene Set Enrichment Analysis (GSEA) was used to analyze the signaling pathways regulated by SEMA5B.Results:The expression level of SEMA5B mRNA in 341 gastric adenocarcinoma tissues was 0.577±0.587, in adjacent normal tissues was 0.132±0.075, the difference was statistically significant ( P<0.001). The median survival time of 109 patients with high expression of SEMA5B mRNA was 14.5 months, 232 patients with low expression of SEMA5B mRNA was 17.9 months ( P=0.047). Univariate analysis showed that the expression of SEMA5B mRNA was correlated with histological grade and T stage ( P<0.05). The multivariate analysis revealed that age<65 years remained independently associated with overall survival, with a hazard ratio( HR) of 1.042 (95% CI: 1.021-1.064). The multivariate analysis revealed that high expression of SEMA5b mRNA remained independently associated with overall survival, with a HR of 1.195 (95% CI: 0.925-2.551). GSEA showed that malignant tumor signaling pathways ( P=0.008), MAPK signaling pathways ( P=0.047) and Notch signaling pathways ( P=0.029) were differentially enriched in SEMA5B highly expressed phenotype. Conclusions:SEMA5B expression may be a potential prognostic molecular marker for prognosis of GAC patients. Moreover, malignant tumor signaling pathway, MAPK signaling pathway and Notch signaling pathway may be the key pathway regulated by SEMA5B in GAC.

This paper proposes algorithm in predicting the RNA secondary structure that combines several sequence comparisons, searches the eigenvalue for subsequence division with dynamic programing, utilizing the minimum free energy method. Moreover, the paper assesses the results derived from this new algorithm based on base-pairs distance, climbing distance and morphology distance. The paper also compares the assessment result and the prediction results of different prediction tools, and analyzes the advantages of the new method and its improvement direction.
Algorithms ; Nucleic Acid Conformation ; RNA ; chemistry

OBJECTIVE:To identify Gleditsia sinensis.METHODS:The property,microscopic and TLC characteristics of Gleditsia sinensis were identified.RESULTS:The appearance,microscopic and TLC characteristics of Gleditsia sinensis were obtained.CONCLUSION:The established method is effective for the quality control of the Gleditsia sinensis.

AimTo study the effects of aspirin (Asp) and verapamil(Ver)alone or in combination on mesenteric microcirculation of rats. MethodsAcute microcirculation disturbance(AMD) was produced by highmolecular weight dextran(Mr 480, 000) 360 mg· kg-1 iv. Arteriol and venul blood flow velocity and diameter (ABFV, VBFV, AD, VD) and blood flow state(BFS) were observed by intravital microcirculation method. Results Asp 2.5, 5 mg · kg-i, Ver 0.3, 0.6 mg · kg-1,Asp+ Ver(1 + 0.15), (2. 5+ 0. 3) mg· kg-1 iv significant increase ABFV by 11.1%, 31.3%, 18.7%,19.5%, 26.5%, 37.3%, VBFV by 12.5%, 5.7%, 2.5%, 3.7%, 30%, 34.7%,AD by 4.3%, 17.9%, 31.5%, 35%, 20%, 38.1% and VDby 2.2%,4.2%, 25%, 31.5%,5.8%,23.5%espectively, and got a raise in the number of capillaries and a marked improvement of BFS. Asp + Ver(1+0.15, 2.5+0.3) mg · kg-1 iv could reverse AMD. Conclusion Asp is superior to Ver in the increase of BFV, but Ver is superior to Asp in expansion of blood vessel. Asp in combination with Ver produces marked synergistic action and protection againist AMD.