Convolutional neural networksTransformerWhite blood cellWhite blood cell (WBC) detection is pivotal in medical diagnostics, crucial for diagnosing infections, inflammations, and certain cancers. Traditional WBC
(2020) proposed an IAN automatic segmentation method based on 3D fully convolutional network (FCN), demonstrating superior performance over SSM methods, but the Dice score on CBCT images only reached 57%. Kwak et al. (2020) explored UNet-based IAN segmentation on both 2D and 3D images, ...
Convolutional neural network DC: Dilated convolution DMS: Multiscale dilated convolution EMD: Empirical mode decomposition Improved SE: Improved attention mechanism LR: Learning rate ODC: One-dimensional convolution PSNR: P-wave signal-to-noise ratio \(r\) : Correlation coefficient RMSE:...
A novel multiscale dilated convolutional network (MSDC-Net) is proposed against the scale difference of lesions and the low contrast between lesions and normal tissues in CT images. In our MSDC-Net, we propose a multiscale feature capture block (MSFCB) to effectively capture multiscale features...
A spatial-temporal attention-based method and a new dataset for remote sensing image change detection Remote Sens. (2020) Chen, H., Wu, C., Du, B., Zhang, L., 2019a. Deep Siamese multi-scale convolutional network for change detection in... ChenH. et al. Change detection in multisour...
Melanoma segmentation based on a convolutional neural network (CNN) has recently attracted extensive attention. However, the features captured by CNN are always local that result in discontinuous fea...
2.2. Convolutional Neural Network (CNN) CNN was developed by Lecun and Bengio [38] in the 1990s as a neural network structure that classifies handwritten numbers and received great attention. It is one of the most popular deep learning algorithms. CNN is a model that reduces the number of ...
Wu et al. (2018) proposed a multi-constraint, fully convolutional network for building segmentation, which adopts U-Net (Ronneberger et al., 2015) architecture with scale constraints for the intermediate layers. These constraints are computed based on the prediction at different layers in the ...
One of the earliest and most powerful DL-based convolutional neural network (CNN) models for image classification is residual networks (ResNets)31. In this study, we proposed a model by reformulating the layers as learning residual functions with reference to the layer inputs instead of learning...
The main methods include CNN (convolutional neural network) (Yanai and Kawano, 2015), Vision Transformer, dual-teacher model fusing CNN and Transformer (Xiao et al., 2022), 3D lightweight network using multiscale convolution attention and vision Transformer (Xiao et al., 2024), etc. Ródenas ...