COVID-19 CT image segmentation method based on swin transformer

SwinDAF3D: Pyramid Swin Transformers with Deep Attentive Features for Automated Finger Joint Segmentation in 3D Ultrasound Images for Rheumatoid Arthritis Assessment

Rheumatoid arthritis (RA) is a chronic autoimmune disease that can cause severe joint damage and functional impairment. Ultrasound imaging has shown promise in providing real-time assessment of synovium inflammation associated with the early stages of RA. Accurate segmentation of the synovium region and quantification of inflammation-specific imaging biomarkers are crucial for assessing and grading RA. However, automatic segmentation of the synovium in 3D ultrasound is challenging due to ambiguous boundaries, variability in synovium shape, and inhomogeneous intensity distribution. In this work, we introduce a novel network architecture, Swin Transformers with Deep Attentive Features for 3D segmentation (SwinDAF3D), which integrates Swin Transformers into a Deep Attentive Features framework. The developed architecture leverages the hierarchical structure and shifted windows of Swin Transformers to capture rich, multi-scale and attentive contextual information, improving the modeling of long-range dependencies and spatial hierarchies in 3D ultrasound images. In a six-fold cross-validation study with 3D ultrasound images of RA patients' finger joints (n = 72), our SwinDAF3D model achieved the highest performance with a Dice Score (DSC) of 0.838 ± 0.013, an Intersection over Union (IoU) of 0.719 ± 0.019, and Surface Dice Score (SDSC) of 0.852 ± 0.020, compared to 3D UNet (DSC: 0.742 ± 0.025; IoU: 0.589 ± 0.031; SDSC: 0.661 ± 0.029), DAF3D (DSC: 0.813 ± 0.017; IoU: 0.689 ± 0.022; SDSC: 0.817 ± 0.013), Swin UNETR (DSC: 0.808 ± 0.025; IoU: 0.678 ± 0.032; SDSC: 0.822 ± 0.039), UNETR++ (DSC: 0.810 ± 0.014; IoU: 0.684 ± 0.018; SDSC: 0.829 ± 0.027) and TransUNet (DSC: 0.818 ± 0.013; IoU: 0.692 ± 0.017; SDSC: 0.815 ± 0.016) models. This ablation study demonstrates the effectiveness of combining a Swin Transformers feature pyramid with a deep attention mechanism, improving the segmentation accuracy of the synovium in 3D ultrasound. This advancement shows great promise in enabling more efficient and standardized RA screening using ultrasound imaging.

Comparative analysis for accurate multi-classification of brain tumor based on significant deep learning models

Brain tumours are a significant health concern, often resulting in severe cognitive and physiological impairments. Accurate detection and classification of brain tumours, including glioma, meningioma, and pituitary tumours, are crucial for effective treatment. In this study, we present a comprehensive approach for brain tumor classification using MRI scans and deep learning models, specifically focusing on the use of Convolutional Neural Networks (CNN), Swin Transformer, and EfficientNet. MRI scans from four categories, including healthy brains, underwent pre-processing using normalisation, resizing, and data augmentation to mitigate problems associated with variability in image quality and tumor manifestation. Every deep learning model was trained on the pre-processed dataset, and their performance was assessed using accuracy, sensitivity, and specificity measures. The findings demonstrate that the Swin Transformer and EfficientNet models achieved superior classification testing accuracy, which are 98.08 % and 98.72 % respectively, surpassing conventional CNNs, which achieve 95.16 % testing accuracy. EfficientNet exhibited an optimal combination between computational economy and classification performance, making it an exemplary choice for resource-limited settings. Our results underscore the capability of sophisticated deep learning architectures to enhance diagnostic precision in brain tumor classification tasks.

A novel real-time crayfish weight grading method based on improved Swin Transformer

This study proposed a novel detection method for crayfish weight classification based on an improved Swin-Transformer model. The model demonstrated a Mean Intersection over Union (MIOU) of 90.36% on the crayfish dataset, outperforming the IC-Net, DeepLabV3, and U-Net models by 17.44%, 5.55%, and 1.01%, respectively. Furthermore, the segmentation accuracy of the Swin-Transformer model reached 99.0%, surpassing the aforementioned models by 1.25%, 1.73%, and 0.46%, respectively. To facilitate weight prediction of crayfish from segmented images, this study also investigated the correlation between the projected area and the weight of each crayfish part, and developed a multiple regression model with a correlation coefficient of 0.983 by comparing the total projected area and the relationship between the projected area and the actual weight of each crayfish part. To validate this model, a test set of 40 samples was employed, with the average prediction accuracy reaching 98.34% based on 10 representative data points. Finally, grading experiments were carried out on the crayfish weight grading system, and the experimental results showed that the grading accuracy could reach more than 86.5%, confirming the system's feasibility. The detection method not only predicts the weight based on the area but also incorporates the proportional relationship of the area of each part to improve the accuracy of the prediction further. This innovation makes up for the limitations of traditional inspection methods and shows higher potential for application. This study has important applications in industrial automation, especially for real-time high-precision weight grading in the aquatic processing industry, which can improve production efficiency and optimize quality control.

Study on lung CT image segmentation algorithm based on threshold-gradient combination and improved convex hull method

Lung images often have the characteristics of strong noise, uneven grayscale distribution, and complex pathological structures, which makes lung image segmentation a challenging task. To solve this problems, this paper proposes an initial lung mask extraction algorithm that combines threshold and gradient. The gradient used in the algorithm is obtained by the time series feature extraction method based on differential memory (TFDM), which is obtained by the grayscale threshold and image grayscale features. At the same time, we also proposed a lung contour repair algorithm based on the improved convex hull method to solve the contour loss caused by solid nodules and other lesions. Experimental results show that on the COVID-19 CT segmentation dataset, the advanced lung segmentation algorithm proposed in this article achieves better segmentation results and greatly improves the consistency and accuracy of lung segmentation. Our method can obtain more lung information, resulting in ideal segmentation effects with improved accuracy and robustness.

SW-UNet: a U-Net fusing sliding window transformer block with CNN for segmentation of lung nodules

Medical images are information carriers that visually reflect and record the anatomical structure of the human body, and play an important role in clinical diagnosis, teaching and research, etc. Modern medicine has become increasingly inseparable from the intelligent processing of medical images. In recent years, there have been more and more attempts to apply deep learning theory to medical image segmentation tasks, and it is imperative to explore a simple and efficient deep learning algorithm for medical image segmentation. In this paper, we investigate the segmentation of lung nodule images. We address the above-mentioned problems of medical image segmentation algorithms and conduct research on medical image fusion algorithms based on a hybrid channel-space attention mechanism and medical image segmentation algorithms with a hybrid architecture of Convolutional Neural Networks (CNN) and Visual Transformer. To the problem that medical image segmentation algorithms are difficult to capture long-range feature dependencies, this paper proposes a medical image segmentation model SW-UNet based on a hybrid CNN and Vision Transformer (ViT) framework. Self-attention mechanism and sliding window design of Visual Transformer are used to capture global feature associations and break the perceptual field limitation of convolutional operations due to inductive bias. At the same time, a widened self-attentive vector is used to streamline the number of modules and compress the model size so as to fit the characteristics of a small amount of medical data, which makes the model easy to be overfitted. Experiments on the LUNA16 lung nodule image dataset validate the algorithm and show that the proposed network can achieve efficient medical image segmentation on a lightweight scale. In addition, to validate the migratability of the model, we performed additional validation on other tumor datasets with desirable results. Our research addresses the crucial need for improved medical image segmentation algorithms. By introducing the SW-UNet model, which combines CNN and ViT, we successfully capture long-range feature dependencies and break the perceptual field limitations of traditional convolutional operations. This approach not only enhances the efficiency of medical image segmentation but also maintains model scalability and adaptability to small medical datasets. The positive outcomes on various tumor datasets emphasize the potential migratability and broad applicability of our proposed model in the field of medical image analysis.

CCT: Lightweight compact convolutional transformer for lung disease CT image classification

Computed tomography (CT) imaging results are an important criterion for the diagnosis of lung disease. CT images can clearly show the characteristics of lung lesions. Early and accurate detection of lung diseases helps clinicians to improve patient care effectively. Therefore, in this study, we used a lightweight compact convolutional transformer (CCT) to build a prediction model for lung disease classification using chest CT images. We added a position offset term and changed the attention mechanism of the transformer encoder to an axial attention mechanism module. As a result, the classification performance of the model was improved in terms of height and width. We show that the model effectively classifies COVID-19, community pneumonia, and normal conditions on the CC-CCII dataset. The proposed model outperforms other comparable models in the test set, achieving an accuracy of 98.5% and a sensitivity of 98.6%. The results show that our method achieves a larger field of perception on CT images, which positively affects the classification of CT images. Thus, the method can provide adequate assistance to clinicians.