No abstract

No abstract

Coronavirus disease 2019 (COVID-19) has spread rapidly worldwide. The rapid and accurate automatic segmentation of COVID-19 infected areas using chest computed tomography (CT) scans is critical for assessing disease progression. However, infected areas have irregular sizes and shapes. Furthermore, there are large differences between image features. We propose a convolutional neural network, named 3D CU-Net, to automatically identify COVID-19 infected areas from 3D chest CT images by extracting rich features and fusing multiscale global information. 3D CU-Net is based on the architecture of 3D U-Net. We propose an attention mechanism for 3D CU-Net to achieve local cross-channel information interaction in an encoder to enhance different levels of the feature representation. At the end of the encoder, we design a pyramid fusion module with expanded convolutions to fuse multiscale context information from high-level features. The Tversky loss is used to resolve the problems of the irregular size and uneven distribution of lesions. Experimental results show that 3D CU-Net achieves excellent segmentation performance, with Dice similarity coefficients of 96.3% and 77.8% in the lung and COVID-19 infected areas, respectively. 3D CU-Net has high potential to be used for diagnosing COVID-19.

No abstract

No abstract

Hyperspectral images not only have high spectral dimension, but the spatial size of datasets containing such kind of images is also small. Aiming at this problem, we design the NG-APC (non-gridding multi-level concatenated Atrous Pyramid Convolution) module based on the combined atrous convolution. By expanding the receptive field of three layers convolution from 7 to 45, the module can obtain a distanced combination of the spectral features of hyperspectral pixels and solve the gridding problem of atrous convolution. In NG-APC module, we construct a 15layer Deep Convolutional Neural Networks (DCNN) model to classify each hyperspectral pixel. Through the experiments on the Pavia University dataset, the model reaches 97.9% accuracy while the parameter amount is only 0.25 M. Compared with other CNN algorithms, our method gets the best OA (Over All Accuracy) and Kappa metrics, at the same time, NG-APC module keeps good performance and high efficiency with smaller number of parameters.

No abstract

Active contour model (ACM) which has been extensively studied recently is one of the most successful methods in image segmentation. The present paper advances an improved hybrid model based on Region-Scalable Fitting Model by combining global convex segmentation method with edge detector operator. The proposed model not only inherits the ability of RSF model to deal with the images with intensity inhomogeneity, but also overcomes such a drawback: existence of local minima because of non-convexity that makes the segmentation result highly dependent of the initial position of the contour. In addition, the paper exploits two fast numerical implementation schemes to overcome a huge amount of level set methods. The duality projection method is implemented by introducing dual variables which lead to semi-implicit iterative scheme of dual variables as well as exact formulation of primal variables. The Split-Bregman method is implemented by introducing auxiliary variables which transform the relaxed convex model into solving simple poisson equations and exact soft thresholding formulation. Experimental results for synthetic and real medical images prove that the proposed model is featured by greater numerical accuracy and faster division speed.