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.
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.
The PET/CT imaging technology combining positron emission tomography (PET) and computed tomography (CT) is the most advanced imaging examination method currently, and is mainly used for tumor screening, differential diagnosis of benign and malignant tumors, staging and grading. This paper proposes a method for breast cancer lesion segmentation based on PET/CT bimodal images, and designs a dual-path U-Net framework, which mainly includes three modules: encoder module, feature fusion module and decoder module. Among them, the encoder module uses traditional convolution for feature extraction of single mode image; The feature fusion module adopts collaborative learning feature fusion technology and uses Transformer to extract the global features of the fusion image; The decoder module mainly uses multi-layer perceptron to achieve lesion segmentation. This experiment uses actual clinical PET/CT data to evaluate the effectiveness of the algorithm. The experimental results show that the accuracy, recall and accuracy of breast cancer lesion segmentation are 95.67%, 97.58% and 96.16%, respectively, which are better than the baseline algorithm. Therefore, it proves the rationality of the single and bimodal feature extraction method combining convolution and Transformer in the experimental design of this article, and provides reference for feature extraction methods for tasks such as multimodal medical image segmentation or classification.
In response to the issues of single-scale information loss and large model parameter size during the sampling process in U-Net and its variants for medical image segmentation, this paper proposes a multi-scale medical image segmentation method based on pixel encoding and spatial attention. Firstly, by redesigning the input strategy of the Transformer structure, a pixel encoding module is introduced to enable the model to extract global semantic information from multi-scale image features, obtaining richer feature information. Additionally, deformable convolutions are incorporated into the Transformer module to accelerate convergence speed and improve module performance. Secondly, a spatial attention module with residual connections is introduced to allow the model to focus on the foreground information of the fused feature maps. Finally, through ablation experiments, the network is lightweighted to enhance segmentation accuracy and accelerate model convergence. The proposed algorithm achieves satisfactory results on the Synapse dataset, an official public dataset for multi-organ segmentation provided by the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), with Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD95) scores of 77.65 and 18.34, respectively. The experimental results demonstrate that the proposed algorithm can enhance multi-organ segmentation performance, potentially filling the gap in multi-scale medical image segmentation algorithms, and providing assistance for professional physicians in diagnosis.