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.
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.
Medical cross-modal retrieval aims to achieve semantic similarity search between different modalities of medical cases, such as quickly locating relevant ultrasound images through ultrasound reports, or using ultrasound images to retrieve matching reports. However, existing medical cross-modal hash retrieval methods face significant challenges, including semantic and visual differences between modalities and the scalability issues of hash algorithms in handling large-scale data. To address these challenges, this paper proposes a Medical image Semantic Alignment Cross-modal Hashing based on Transformer (MSACH). The algorithm employed a segmented training strategy, combining modality feature extraction and hash function learning, effectively extracting low-dimensional features containing important semantic information. A Transformer encoder was used for cross-modal semantic learning. By introducing manifold similarity constraints, balance constraints, and a linear classification network constraint, the algorithm enhanced the discriminability of the hash codes. Experimental results demonstrated that the MSACH algorithm improved the mean average precision (MAP) by 11.8% and 12.8% on two datasets compared to traditional methods. The algorithm exhibits outstanding performance in enhancing retrieval accuracy and handling large-scale medical data, showing promising potential for practical applications.
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.
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.
In order to investigate the stability of Hydroxyapatite (HA) coated material, the plasma-sprayed coatings of HA were divided into four groups: 1. Keeping in water vapour at 125 degrees C, with a pressure of 0.15 MPa for 6 hr; 2. Heating at 650 degrees C in air for half an hr; 3. Keeping in water vapour at 490 degrees C, with a pressure of 0.01 MPa for 2 hr; and 4. The control. The XRD, FTIR analysis and the dissolution test were carried out. The results showed: 1. The degree of crystalization in XRD analysis was 3. gt; 1. gt; 2. gt; 4.; 2. The ampitude of OH- peak in FTIR analysis was 3. gt; 1. gt; 2. gt; 4. and 3. The dissolution rate in tris-HCl buffer was 3. lt; 1. lt; 2. lt; 4. The conclusions were 1. The treating with water vapour could decrease the transformation temperature which was needed to convert the amorphous phase into cystalline phase; 2. Water vapour treatment could accelerate the transformation of Z-TCP, TCPM into crystalline HA; 3. Water vapour treatment could promote the structural integrity of plasma--sprayed coated of and HA and 4. Water vapour treatment could lower the dissolution rate of HA coated in Tris-HCl buffer.
Objective To study the influence of transforming growth factor-β1(TGF-β1), dentin non-collagen proteins(dNCPs) and their complexon tissue engineering pulp system. Methods Collagen I and dentin powder were used to construct the system of pulp cells in 3dimensional culture, dentin powder was added in the gel. The tissue engineering pulp were divided TGF-β1 group, dNCPs group, TGF-β1/dNCPsgroup and control group.After3, 6 and 14 days, the appearance and the differentiation of pulp cells were observed by HE staining and immunohistochemical staining -respectively. Results Collagen I could form netted collagen gel construction. Growing condition of pulp cells in gel was similar to that of pulp cells in vivo. After the TGF-β1 and dNCPswere added, the pulp cells had some characteristics of odontoblasts and had unilateral cell process after culture 6 days. Pulp cells arranged with parallel columnar and form dentin-pulp-like complex after 14 days. Immunohistochemical staining showed dentin salivary protein(DSP) began to express in some cells.The number of positive cell was most in the TGF-β1 group. No positive cells were detected in the control group. Conclusion The transforming growth factor-β1 and noncollagen proteins can stimulate the pulp cells to transform into odontoblasts to some extent, which promote the formation of tissue engineering pulp.
Objective To evaluate the cell biological features and the effect of transplantation of transforming growth factor β3 (TGF-β3) gene-modified nucleus pulposus (NP) cells on the degeneration of lumbar intervertebral discs in vitro. Methods NP cells at passage 2 were infected by recombinant adenovirus carrying TGF-β3 (Ad-TGF-β3) gene (Ad-TGF-β3 group), and then the cell biological features were observed by cell vital ity assay, the expression of the TGF-β3 protein was determined by Western blot, the expression of collagen type II in logarithmic growth phase was determined by immunocytochemistry. The cells with adenovirus-transfected (Adv group) and the un-transfected cells (blank group) were used as controls. The model of lumbar disc degeneration was establ ished by needl ing L3, 4, L4, 5, and L5, 6 in 30 New Zealand rabbits (weighing 3.2-3.5 kg, male or female). Then Ad-TGF-β3-transfected rabbit degenerative nucleus pulposus cells (100 μL, 1 × 105/ mL, group A, n=12), no gene-modified nucleus pulposus cells (100 μL, 1 × 105/mL, group B, n=12), and phosphatebuffered sal ine (PBS, 100 μL, group C, n=6) were injected into degenerative lumbar intervertebral discs, respectively. L3, 4, L4, 5, and L5, 6 disc were harvested from the rabbits (4 in groups A and B, 2 in group C) at 6, 10, and 14 weeks respectively to perform histological observation and detect the expression of collagen type II and proteoglycan by RT-PCR. Results The viabil ity of nucleus pulposus cells was obviously improved after transfected by recombinant Ad-TGF-β3 gene. At 3, 7, and 14 days after transfected, TGF-β3 expression gradually increased in nucleus pulposus cells. The positive staining of collagen type II was seen in Ad-TGF-β3 group, and the positive rate was significantly higher than that of Adv group and blank group (P lt; 0.05). The disc degeneration in group A was sl ighter than that in groups B and C. The expressions of collagen type II mRNA and proteoglycan mRNA in group A were significantly higher than those in groups B and C at 6, 10, and 14 weeks (P lt; 0.05). Conclusion TGF-β3 can improve the biological activity of NP cells and promote the biosynthesis of collagen type II and proteoglycan in intervertebral discs, alleviate the degeneration of intervertebral discs after transplantation.
ObjectiveTo summarize the research advancement of peroxisome proliferator-activated receptor γ (PPARγ) agonists inhibiting transforming growth factor-β (TGF-β)-induced organ fibrosis. MethodsThe related literatures on PPARγ agonists inhibiting TGF-β-induced organ fibrosis were reviewed. ResultsTGF-β was a major fibrosispromoting cytokine, which could promote a variety of organ fibrosis. PPARγ agonists could effectively block TGFβ signal transduction, and then suppressed organ fibrosis well. ConclusionsThe main antifibrotic mechanism of PPARγ agonists is to inhibit TGF-β signal transduction. The studies on this mechanism will help promoting the clinical application of PPARγ agonists, and provide a new way of the treatment for organ fibrosis.
OBJECTIVE: To explore the relationship between characteristics of transformed cell and tumorigenicity. METHODS: Documents about transformed cell and tumorigenicity were reviewed in detail. RESULTS: Normal biological characteristics and cell function could be maintained in non-tumorigenic transformed cell, but it was changed markedly in malignant transformed cell. CONCLUSION: Non-tumorigenic transformed cell can be served as a standard cell line to study the function and growth characteristics of normal cell.