Search

Low-dose computed tomography (CT) is a relatively safe method for disease screening. But low-dose CT images often contain severe noise and artifacts, which seriously affect the subsequent diagnosis. To solve this problem, this paper proposes a subspace projection and edge enhancement network (SPEENet). SPEENet hold an architecture of autoencoder, including two main modules: dual stream encoder and decoder. The dual stream encoder can be divided into two parts: noise image coding stream and edge information coding stream. The noise image coding stream removes the noise and artifacts in low-dose CT images by using the image features extracted from the low-dose CT images. The edge information coding stream mainly focuses on the edge information of low-dose CT images and fully utilize the edge information to preserve the structures. In order to make full use of the encoder features, this paper introduces the noise basis projection module to establish a basis based on the features of encoder and decoder, and uses this basis to project the features extracted by the encoder into the corresponding subspace to obtain better feature representation. In this paper, experiments are conducted on the public database to verify the effectiveness. The experimental results show that SPEENet can achieve better denoising performance than other low-dose CT denoising networks.

Employing deep learning models to design high-performance metasurfaces has garnered significant attention due to its potential benefits in terms of accuracy and efficiency. A deep learning-based metasurface design framework typically comprises a forward prediction path for predicting optical responses and a backward retrieval path for generating geometrical configurations. In the forward design path, a specific geometrical configuration corresponds to a unique optical response. However, in the inverse design path, a single performance metric can correspond to multiple potential designs. This one-to-many mapping poses a significant challenge for deep learning models and can potentially impede their performance. Although representing the inverse path as a probabilistic distribution is a widely adopted method for tackling this problem, accurately capturing the posterior distribution to encompass all potential solutions remains an ongoing challenge. Furthermore, in most pioneering works, the forward and backward paths are captured using separate models. However, the knowledge acquired from the forward path does not contribute to the training of the backward model. This separation of models adds complexity to the system and can hinder the overall efficiency and effectiveness of the design framework. Here, we utilized an invertible neural network (INN) to simultaneously model both the forward and inverse process. Unlike other frameworks, INN focuses on the forward process and implicitly captures a probabilistic model for the inverse process. Given a specific optical response, the INN enables the recovery of the complete posterior over the parameter space. This capability allows for the generation of novel designs that are not present in the training data. Through the integration of the INN with the angular spectrum method, we have developed an efficient and automated end-to-end metasurface design and evaluation framework. This novel approach eliminates the need for human intervention and significantly speeds up the design process. Utilizing this advanced framework, we have effectively designed high-efficiency metalenses and dual-polarization metasurface holograms. This approach extends beyond dielectric metasurface design, serving as a general method for modeling optical inverse design problems in diverse optical fields.

Although the face detection problem has been studied for decades, searching tiny faces in the whole image is still a challenging task, especially in low-resolution images. Traditional face detection methods are based on hand-crafted features, but the features of tiny faces are different from those of normal-sized faces, and thus the detection robustness cannot be guaranteed. In order to alleviate the problem in existing methods, we propose a pre-identification mechanism and a cascaded detector (PMCD) for tiny-face detection. This pre-identification mechanism can greatly reduce background and other irrelevant information. The cascade detector is designed with two stages of deep convolutional neural network (CNN) to detect tiny faces in a coarse-to-fine manner, i.e., the face-area candidates are pre-identified as region of interest (RoI) based on a real-time pedestrian detector and the pre-identification mechanism, the set of RoI candidates is the input of the second sub-network instead of the whole image. Benefiting from the above mechanism, the second sub-network is designed as a shallow network which can keep high accuracy and real-time performance. The accuracy of PMCD is at least 4% higher than the other state-of-the-art methods on detecting tiny faces, while keeping real-time performance.