In dentistry, panoramic X-ray images are extensively used by dentists for tooth structure analysis and disease diagnosis. However, the manual analysis of these images is time-consuming and prone to misdiagnosis or ove...In dentistry, panoramic X-ray images are extensively used by dentists for tooth structure analysis and disease diagnosis. However, the manual analysis of these images is time-consuming and prone to misdiagnosis or overlooked. While deep learning techniques have been employed to segment teeth in panoramic X-ray images, accurate segmentation of individual teeth remains an underexplored area. In this study, we propose an end-to-end deep learning method that effectively addresses this challenge by employing an improved combinatorial loss function to separate the boundaries of adjacent teeth, enabling precise segmentation of individual teeth in panoramic X-ray images. We validate the feasibility of our approach using a challenging dataset. By training our segmentation network on 115 panoramic X-ray images, we achieve an intersection over union (IoU) of 86.56% for tooth segmentation and an accuracy of 65.52% in tooth counting on 87 test set images. Experimental results demonstrate the significant improvement of our proposed method in single tooth segmentation compared to existing methods.展开更多
Lung cancer is one of the greatest threats to human health. It is a very effective way to detect lung cancer by pathological pictures of lung cancer cells. Therefore, improving the accuracy and stability of diagnosis ...Lung cancer is one of the greatest threats to human health. It is a very effective way to detect lung cancer by pathological pictures of lung cancer cells. Therefore, improving the accuracy and stability of diagnosis is very important. In this study, we develop an automatic detection scheme for lung cancer cells based on convolutional neural networks and Swin Transformer. Microscopic images of patients’ lung cells are first segmented using a Mask R-CNN-based network, resulting in a separate image for each cell. Part of the background information is preserved by Gaussian blurring of surrounding cells, while the target cells are highlighted. The classification model based on Swin Transformer not only reduces the computation but also achieves better results than the classical CNN model, ResNet50. The final results show that the accuracy of the method proposed in this paper reaches 96.16%. Therefore, this method is helpful for the detection and classification of lung cancer cells.展开更多
文摘In dentistry, panoramic X-ray images are extensively used by dentists for tooth structure analysis and disease diagnosis. However, the manual analysis of these images is time-consuming and prone to misdiagnosis or overlooked. While deep learning techniques have been employed to segment teeth in panoramic X-ray images, accurate segmentation of individual teeth remains an underexplored area. In this study, we propose an end-to-end deep learning method that effectively addresses this challenge by employing an improved combinatorial loss function to separate the boundaries of adjacent teeth, enabling precise segmentation of individual teeth in panoramic X-ray images. We validate the feasibility of our approach using a challenging dataset. By training our segmentation network on 115 panoramic X-ray images, we achieve an intersection over union (IoU) of 86.56% for tooth segmentation and an accuracy of 65.52% in tooth counting on 87 test set images. Experimental results demonstrate the significant improvement of our proposed method in single tooth segmentation compared to existing methods.
文摘Lung cancer is one of the greatest threats to human health. It is a very effective way to detect lung cancer by pathological pictures of lung cancer cells. Therefore, improving the accuracy and stability of diagnosis is very important. In this study, we develop an automatic detection scheme for lung cancer cells based on convolutional neural networks and Swin Transformer. Microscopic images of patients’ lung cells are first segmented using a Mask R-CNN-based network, resulting in a separate image for each cell. Part of the background information is preserved by Gaussian blurring of surrounding cells, while the target cells are highlighted. The classification model based on Swin Transformer not only reduces the computation but also achieves better results than the classical CNN model, ResNet50. The final results show that the accuracy of the method proposed in this paper reaches 96.16%. Therefore, this method is helpful for the detection and classification of lung cancer cells.
