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.
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.
Accurate detection of cephalometric landmarks is crucial for orthodontic diagnosis and treatment planning. Current landmark detection methods are mainly divided into heatmap-based and regression-based approaches. However, these methods often rely on parallel computation of multiple models to improve accuracy, significantly increasing the complexity of training and deployment. This paper presented a novel regression method that can simultaneously detect all cephalometric landmarks in high-resolution X-ray images. By leveraging the encoder module of Transformer, a dual-encoder model was designed to achieve coarse-to-fine localization of cephalometric landmarks. The entire model consisted of three main components: a feature extraction module, a reference encoder module, and a fine-tuning encoder module, responsible for feature extraction and fusion of X-ray images, coarse localization of cephalometric landmarks, and fine localization of landmarks, respectively. The model was fully end-to-end differentiable and could learn the intercorrelation relationships between cephalometric landmarks. Experimental results showed that the successful detection rate (SDR) of our algorithm was superior to other existing methods. It attained the highest 2 mm SDR of 89.51% on test set 1 of the ISBI2015 dataset and 90.68% on the test set of the ISBI2023 dataset. Meanwhile, it reduces memory consumption and enhances the model’s popularity and applicability, providing more reliable technical support for orthodontic diagnosis and treatment plan formulation.
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.
Protein lysine β-hydroxybutyrylation (Kbhb) is a newly discovered post-translational modification associated with a wide range of biological processes. Identifying Kbhb sites is critical for a better understanding of its mechanism of action. However, biochemical experimental methods for probing Kbhb sites are costly and have a long cycle. Therefore, a feature embedding learning method based on the Transformer encoder was proposed to predict Kbhb sites. In this method, amino acid residues were mapped into numerical vectors according to their amino acid class and position in a learnable feature embedding method. Then the Transformer encoder was used to extract discriminating features, and the bidirectional long short-term memory network (BiLSTM) was used to capture the correlation between different features. In this paper, a benchmark dataset was constructed, and a Kbhb site predictor, AutoTF-Kbhb, was implemented based on the proposed method. Experimental results showed that the proposed feature embedding learning method could extract effective features. AutoTF-Kbhb achieved an area under curve (AUC) of 0.87 and a Matthews correlation coefficient (MCC) of 0.37 on the independent test set, significantly outperforming other methods in comparison. Therefore, AutoTF-Kbhb can be used as an auxiliary means to identify Kbhb sites.
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 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.
Objective To construct recombinant lentiviral expression vectors of porcine transforming growth factor β1 (TGF-β1) gene and transfect bone marrow mesenchymal stem cells (BMSCs) so as to provide TGF-β1 gene-modified BMSCs for bone and cartilage tissue engineering. Methods The TGF-β1 cDNA was extracted and packed into lentiviral vector, and positive clones were identified by PCR and gene sequencing, then the virus titer was determined. BMSCs were isolated frombone marrow of the 2-month-old Bama miniature pigs (weighing 15 kg), and the 2nd and 3rd generations of BMSCs wereharvested for experiments. BMSCs were then transfected by TGF-β1 recombinant lentiviral vectors (TGF-β1 vector group)respectively at multi pl icity of infection (MOI) of 10, 50, 70, 100, and 150; then the effects of transfection were detected bylaser confocal microscope and Western blot was used to determine the optimal value of MOI. BMSCs transfected by empty vector (empty vector group) and non-transfected BMSCs (non-transfection group) were used as control group. RT-PCR, immunocytochemistry, and ELISA were performed to detect the expressions of TGF-β1 mRNA, TGF-β1 protein, and collagen type II. Results Successful construction of recombinant lentiviral vectors of porcine TGF-β1 gene was identified by PCR and gene sequencing, and BMSCs were successfully transfected by TGF-β1 recombinant lentiviral vectors. Green fluorescence was observed by laser confocal microscope. Western blot showed the optimal value of MOI was 70. The expression of TGF-β1 mRNA was significantly higher in TGF-β1 vector group than in empty vector group and non-transfection group (P lt; 0.05). Immunocytochemistry results revealed positive expression of TGF-β1 protein and collagen type II in BMSCs of TGF-β1 vector group, but negative expression in empty vector group and non-transfection group. At 21 days after transfection, high expression of TGF-β1 protein still could be detected by ELISA in TGF-β1 vector group. Conclusion TGF-β1 gene can be successfully transfected into BMSCs via lentiviral vectors, and long-term stable expression of TGF-β1 protein can be observed, prompting BMSCs differentiation into chondrocytes.
Objective To investigate the effects of adenovirus-mediated melanoma differentiation-associated gene-7 (mda-7)/IL-24 and/or adriamycin (ADM) on transplanted human hepatoma in nude mice and to explore a new way for hepatoma gene therapy combined with chemotherapy. Methods The recombinant adenovirus vector carrying Ad.mda-7 was constructed; Ad.mda-7 and/or ADM were injected into the tumor-bearing mice. Their effects on the growth of the tumor and the survival time of the mice were observed. The expressions of VEGF and TGF-β1 were detected by an immunohistochemistry method. Results Ad.mda-7 was constructed and expressed in vivo successfully. Compared with other three groups 〔control group (43.4±1.67) d, ADM group (64.2±4.14) d, Ad.mda-7 group (61.4±1.67) d〕, the mice treated with Ad.mda-7 combined with ADM had longer average survival time 〔(83.8±4.82) d, P＜0.01〕; the average size of tumor treated with Ad.mda-7 combined with ADM diminished significantly compared with that treated with ADM or Ad.mda-7 separately (P＜0.01). VEGF and TGF-β1 expressions of Ad.mda-7 group were (56.2±7.7)%, (35.2±4.5)%, respectively, and were lower than those in ADM group (VEGF: P＜0.05; TGF-β1: P＜0.01). VEGF expression of Ad.mda-7+ADM group was (37.3±5.0)%, and was significantly lower than that in other three groups (P＜0.01). TGF-β1 expression of Ad.mda-7+ADM group was (31.2±3.1)% and significantly lower than that in control group and ADM group (P＜0.01), however, there was no significant difference compared with Ad.mda-7 group (Pgt;0.05). Conclusion Ad.mda-7 combined with ADM has b antitumor potency and synergistic effects and suppresses the growth of human HCC xenograft in nude mice, possibly by inducing the apoptosis of hepatoma cell lines and suppressing tumor angiogenesis.
Objective To investigate the role of transforming growth factorβ3 (TGF-β3) on the amylase secretion of rat submandibular gland cells(RSGCs).Methods The RSGCs were cultured and identified. The expressions of CK 8.13, S100 and Vimentin in the RSGCs were examined by immunohistochemical staining. The experimental group was divided into 5 groups according to differentconcentrations of TGF-β3 (0.5, 1.0, 5.0, 10.0 and 25.0 ng/ml) and no TGF-β3 culture was used as control group. The effects ofTGF-β3 on the cell proliferation and amylase secretion were examined at the24th, the 48th, the 72nd and the 96th hour. MTT colorimetric method was used to estimate vital force of culture cells. Amylase protein was assayed by autobiochemistry equipment and Western blotting.Results The RSGCs were stained positively for CK 8.13 and S-100, but negatively for Vimentin. There were no significant differences in absorbency between the experimental groups and the control group(Pgt;0.05). Compared with the control group,TGF-β3 at concentrations of 0.5-10.0 ng/ml significantly stimulated the amylase secretion of RSGCs after 72 and 96 hours(Plt;0.01). But high concentration of TGF-β3 (25.0ng/ml) showed no stimulation. Western blotting demonstrated that the cultured RSGCs and submandibular gland had the same band of amylase electrophoresis.Conclusion TGF-β3 can stimulate RSGCs to differentiate and to secrete amylase, but TGF-β3 has no effect on proliferation ofRSGCs.