Leukemia is a common, multiple and dangerous blood disease, whose early diagnosis and treatment are very important. At present, the diagnosis of leukemia heavily relies on morphological examination of blood cell images by pathologists, which is tedious and time-consuming. Meanwhile, the diagnostic results are highly subjective, which may lead to misdiagnosis and missed diagnosis. To address the gap above, we proposed an improved Vision Transformer model for blood cell recognition. First, a faster R-CNN network was used to locate and extract individual blood cell slices from original images. Then, we split the single-cell image into multiple image patches and put them into the encoder layer for feature extraction. Based on the self-attention mechanism of the Transformer, we proposed a sparse attention module which could focus on the discriminative parts of blood cell images and improve the fine-grained feature representation ability of the model. Finally, a contrastive loss function was adopted to further increase the inter-class difference and intra-class consistency of the extracted features. Experimental results showed that the proposed module outperformed the other approaches and significantly improved the accuracy to 91.96% on the Munich single-cell morphological dataset of leukocytes, which is expected to provide a reference for physicians’ clinical diagnosis.
In order to address the issues of spatial induction bias and lack of effective representation of global contextual information in colon polyp image segmentation, which lead to the loss of edge details and mis-segmentation of lesion areas, a colon polyp segmentation method that combines Transformer and cross-level phase-awareness is proposed. The method started from the perspective of global feature transformation, and used a hierarchical Transformer encoder to extract semantic information and spatial details of lesion areas layer by layer. Secondly, a phase-aware fusion module (PAFM) was designed to capture cross-level interaction information and effectively aggregate multi-scale contextual information. Thirdly, a position oriented functional module (POF) was designed to effectively integrate global and local feature information, fill in semantic gaps, and suppress background noise. Fourthly, a residual axis reverse attention module (RA-IA) was used to improve the network’s ability to recognize edge pixels. The proposed method was experimentally tested on public datasets CVC-ClinicDB, Kvasir, CVC-ColonDB, and EITS, with Dice similarity coefficients of 94.04%, 92.04%, 80.78%, and 76.80%, respectively, and mean intersection over union of 89.31%, 86.81%, 73.55%, and 69.10%, respectively. The simulation experimental results show that the proposed method can effectively segment colon polyp images, providing a new window for the diagnosis of colon polyps.
The synergistic effect of drug combinations can solve the problem of acquired resistance to single drug therapy and has great potential for the treatment of complex diseases such as cancer. In this study, to explore the impact of interactions between different drug molecules on the effect of anticancer drugs, we proposed a Transformer-based deep learning prediction model—SMILESynergy. First, the drug text data—simplified molecular input line entry system (SMILES) were used to represent the drug molecules, and drug molecule isomers were generated through SMILES Enumeration for data augmentation. Then, the attention mechanism in the Transformer was used to encode and decode the drug molecules after data augmentation, and finally, a multi-layer perceptron (MLP) was connected to obtain the synergy value of the drugs. Experimental results showed that our model had a mean squared error of 51.34 in regression analysis, an accuracy of 0.97 in classification analysis, and better predictive performance than the DeepSynergy and MulinputSynergy models. SMILESynergy offers improved predictive performance to assist researchers in rapidly screening optimal drug combinations to improve cancer treatment outcomes.
Manual segmentation of coronary arteries in computed tomography angiography (CTA) images is inefficient, and existing deep learning segmentation models often exhibit low accuracy on coronary artery images. Inspired by the Transformer architecture, this paper proposes a novel segmentation model, the double parallel encoder u-net with transformers (DUNETR). This network employed a dual-encoder design integrating Transformers and convolutional neural networks (CNNs). The Transformer encoder transformed three-dimensional (3D) coronary artery data into a one-dimensional (1D) sequential problem, effectively capturing global multi-scale feature information. Meanwhile, the CNN encoder extracted local features of the 3D coronary arteries. The complementary features extracted by the two encoders were fused through the noise reduction feature fusion (NRFF) module and passed to the decoder. Experimental results on a public dataset demonstrated that the proposed DUNETR model achieved a Dice similarity coefficient of 81.19% and a recall rate of 80.18%, representing improvements of 0.49% and 0.46%, respectively, over the next best model in comparative experiments. These results surpassed those of other conventional deep learning methods. The integration of Transformers and CNNs as dual encoders enables the extraction of rich feature information, significantly enhancing the effectiveness of 3D coronary artery segmentation. Additionally, this model provides a novel approach for segmenting other vascular structures.
Objective To explore whether the polymorphism of transforming growth factor β1 (TGF β1) gene at 869T/C and 915G/C loci contributes to the genetic susceptibility to hypertension. Methods Assessed under the same criteria, all case control studies on relationship between the polymorphism of TGF β1 gene and hypertension were searched in both English and Chinese databases. All articles retrieved were screened and evaluated, and meta-analyses were conducted with RevMan 5.1 software. Results A total of 14 case control studies were included. The results of meta-analyses showed TGF β1 gene C allele was related to hypertension (OR=1.37, 95%CI 1.21 to 1.54). It was noted that individuals with CC genotype and TT genotype had a significant increased risk of hypertension (OR=1.43, 95%CI 1.27 to 1.60; OR=0.64, 95%CI 0.53 to 0.78, respectively). And there was no b evidence showing that TGF β1 915G/C genetic polymorphism was related to hypertension. The results from meta-analyses of the studies based on Chinese population on the two loci were in consistent with the outcomes of overall meta-analyses. Sensitivity analyses indicated the results were stable. And publication bias was not present, reflected by P values from Egger’s regression asymmetry test and Begg’s adjusted rank correction test. Conclusions 869T/C polymorphism of TGF β1 gene is associated with hypertension. C allele is potentially one of the genetic risk factors for hypertension. Present studies do not support a direct relationship between 915G/C polymorphism TGF β1 gene and hypertension.
ObjectiveTo explore the expressions of prostaglandin F2α receptor (PTGFR) and cyclooxygenase-2 (COX-2) in tissues of benign bile duct scar and their significances, and investigate the regulating effect of transforming growth factor-β1 (TGF-β1) on the expression of PTGFR in human bile duct fibroblasts cultured in vitro. MethodsThe samples of common bile duct (CBD) scars were collected from 18 patients with benign bile duct scar stricture and 6 cases of normal CBD tissues from liver transplantation donor were collected as control. The expressions of PTGFR and COX-2 were detected by immunohistochemical strept-avidin-biotin complex (SABC) method. Semiquantitative RT-PCR and ELISA methods were used to detect the mRNA and protein levels of PTGFR in bile duct fibroblasts which were effected by TGF-β1 with different concentrations (0, 10, 20, and 30 ng/ml) for 24 h. ResultsThe positive rates of PTGFR and COX-2 were 88.9% (16/18) and 83.3% (15/18) in tissues of benigh CBD scar and 33.3% (2/6) and 0 (0/6) in normal CBD tissues (Plt;0.05). The expressions of the PTGFR mRNA and protein levels became upregulated when the concentrations of the TGF-β1 became higher in human bile duct fibroblasts (Plt;0.05). And the effect was concentration dependant to some extent. ConclusionsThe high expressions of PTGFR and COX-2 play important roles in the process of benign bile duct stricture formation. TGF-β1 is able to induce higher expressions of PTGFR mRNA level and the PTGFR protein level in a concentration dependent manner, and regulate the formation of benign bile duct stricture.
【Abstract】ObjectiveTo detect p27 expression in rectal carcinoma and serum transforming growth factor-β1 (TGF-β1) level in these patients, and to elucidate the modulatory effect of serum TGF-β1 on p27 expression in rectal carcinoma. MethodsExpression of p27 was measured in 37 cases of rectal carcinoma, 22 of rectal adenoma and 19 of normal control specimens by immunohistochemical staining using antibodies to p27. Serum level of TGFβ1 was measured in these patients by enzymelinked immunosorbent assay (ELISA) method. Resultsp27 protein was expressed in normal rectal tissue, rectal adenoma and rectal carcinoma, and the positive rate was 89.47%, 90.91% and 64.87%, respectively. The positive rate of p27 in rectal carcinoma was significantly lower than that of normal rectal tissue and rectal adenoma (P=0.025). p27 was mainly located in nucleolus of normal rectal tissue and rectal adenoma, and the positive rate of p27 in cytoplasm of rectal carcinoma was higher than that of normal and rectal adenoma. The positives rates of serum TGF-β1 in normal group, rectal adenoma group and rectal carcinoma group were 21.05%, 27.27% and 51.35%(P=0.045),respectively. The expression of p27 related to histological differentiation, lymph node metastasis and infiltration depth. Serum level of TGF-β1 related to lymph node metastasis, infiltrated depth and CEA level. The positive rate of p27 in TGF-β1 negative group and positive group was 88.89% and 42.11%(MantelHaenszel χ2=6.755,P=0.009), respectively. ConclusionTGF-β1 may be useful in assessment of malignance and prognosis of rectal carcinoma. TGF-β1 can downregulate p27 expression in rectal carcinoma.
ObjectiveTo introduce transforming growth factor β(TGFβ) and the relationship between TGFβ and graft rejection. Methods Relevent articles in recent years were reviewed.ResultsThe immunodepressive function of TGFβ could resist transplant organ rejection injury in early postoperative period ; meanwhile TGFβ also caused fibroblast migration and promoted matrix deposition by increasing collagen production and decreasing collagen breakdown via inhibition of collagenases,which resulted in transplant organ fibrosis and arteriosclerosis, gene polymorphisms of the TGFβ were associated with it. Moreover,ischemia reperfusion injury and immunodepressive drug also affected production of TGFβ.ConclusionTGFβ as a pleiotropic and multifunctional cytokine contributes to the development of acute and chronic rejection.
The expressions and significance of c-met oncoprotein and transforming growth factor-α (TGF-α) were studied by immunohistochemical method in 50 cases of breast cancer (BC) and 12 cases of benign lesions of breast (BL). The positive rate of c-met, TGF-α in BC was 26.0% and 25.0% respectively, in BL was 8.3% and 25.0% respectively. The positive rate of c-met oncoprotein was lower in the cases of histologic Grade Ⅰ, positive of ER and PR or CEA than that of histologic Grade Ⅲ, negative of ER and PR or CEA. The positive rate of TGF-α was lower in the cases of histologic Grade Ⅰ, negative of ER and PR or CEA than that of histologic Grade Ⅲ, positive of ER and PR or CEA. These results suggest the expression of c-met and TGF-α might be related to the carcinogenesis and development or endocrine state of BC.
Objective To investigate the effects of sodium ferulate on lung mRNA expression of TGF-β1 signal transduction molecule in rats with pulmonary fibrosis，and explore the mechanism of sodium ferulate on pulmonary fibrosis.Methods A rat model of pulmonary fibrosis was induced by intratracheal injection of bleomycin (5 mg/kg).Thirty SD rats were randomly divided into three groups (n=10 in each group)，ie.a control group，a pulmonary fibrosis model group，and a sodium ferulate group.The lung histopathology and the expression of collagen was examined by HE staining and collagen fibril staining respectively.The expressions of TGF-βRII and Smad4 mRNA in the lung tissue were detected by situ hybridization.And the expression of TGF-β1 mRNA was detected by real-time fluorescence-quantification RT-PCR.Results Collagen fibril staining indicated that the expression of pulmonary collagen in the model group was significantly higher than that in the control group and sodium ferulate group (Plt;0.001).The mRNA expressions of pulmonary TGF-β1，TGF-βRII and Smad4 were significantly higher in the model group than those in the control group (all Plt;0.01)，and were significantly lower in the sodium ferulate group than those in the model group (all Plt;0.05).Conclusions Sodium ferulate can effectively reduce pulmonary fibrosis through inhibition of the mRNA expression of TGF-β1，TGF-βRII and Smad4 in the lung tissue，thus influence the TGF-β1/Smad4 signal transduction way and inhibit the target gene activation.