Removing noise and artifacts from low-dose computed tomography (LDCT) is a challenging task, and most existing image-based algorithms tend to blur the results. To improve the resolution of denoising results, we combine convolutional dictionary learning and convolutional neural network (CNN), and propose a transfer learning densely connected convolutional dictionary learning (TLD-CDL) framework. In detail, we first introduce the dense connections and multi-scale Inception structure to the network, and train the pre-model on the natural image dataset, then fit the model to the post-processing of LDCT images in the way of transfer learning. In addition, considering that a single pixel-level loss is difficult to achieve satisfactory results both in the index and visual perception, we use the compound loss function of L1 loss and SSIM loss to guide the training. The experimental result shows that TLD-CDL has a good balance between noise reduction and the preservation of details, and acquires inspiring effectiveness in terms of qualitative and quantitative perspective.

Automatic and accurate cervical nucleus segmentation is important because nuclei carry substantial diagnostic information for automatic computer-assisted cervical cancer screening and diagnosis systems. In this paper, we propose a cervical nucleus segmentation method in which pixel-level prior information is utilized to provide the supervisory information for the training of a mask regional convolutional neural network (Mask-RCNN), which is then employed to extract the multi-scale features of the nuclei, and the coarse segmentation and bounding box of the nuclei are obtained by forward propagation of the Mask-RCNN. To refine the segmentation, a local fully connected conditional random field (LFCCRF) that contains unary and pairwise energy terms is employed. The nuclear region of interest is determined by extending the bounding box, the coarse segmentation in the nuclear region is used to construct the unary energy, and the pairwise energy is contributed by the position and intensity information of all of the pixels in the nuclear region. By minimizing the energy of the LFCCRF, the final segmentation is realized. We evaluated our method by using cervical nuclei from the Herlev Pap smear data set in this paper, and the precision, recall, and Zijdenbos similarity index were all found to be greater than 0.95 with low standard deviations, demonstrating that our method enables more accurate and stable cervical nucleus segmentation than the current state-of-the-art methods.

As new fluorescent materials, light wavelength conversion materials (light conversion agents) have attracted increasing attention from scientific researchers and agricultural materials companies due to their potential advantages in efficiently utilizing solar energy and increasing crop yield. According to the material properties, the light conversion agents can be divided into fluorescent dyes, organic rare-earth complexes, and inorganic rare-earth complexes. The current researches indicates that the fluorescent dyes have relatively high production costs, poor light stability, difficult degradation processes, and easily cause pollution to the ecological environment. The organic rare-earth complexes have short luminescence times, high production costs, and suffer from rapid decreases in luminescence intensity. Compared with fluorescent dyes and organic rare-earth complexes, although rare-earth inorganic complexes have high luminous efficiency, stable chemical properties, and better spectral matching performance, the existing inorganic light conversion agents have relatively poor dispersibility in agricultural films. According to the research on light conversion agents at home and abroad in recent years, this paper first introduces the three common light conversion agents, namely fluorescent dyes, organic rare-earth complexes, and inorganic rare-earth complexes, as well as their uses in agricultural films and their mechanisms of light conversion. At the same time, the preparation methods, advantages, disadvantages, and existing problems of various light conversion agents are classified and explained. Finally, we predict the development trends for light conversion agents in the future by considering six aspects, namely efficiency, cost, compatibility with greenhouse films, light matching, and light transmittance, in order to provide a reference for the preparation of stable and efficient light conversion agent materials.

A high-sensitivity, low-cost, ultrathin, hollow fiber micro bubble structure was proposed; such a bubble can be used to develop a high-sensitivity strain sensor based on a Fabry–Perot interferometer (FPI). The micro bubble is fabricated at the fiber tip by splicing a glass tube to a single mode fiber (SMF) and then the glass tube is filled with gas in order to expand and form a micro bubble. The sensitivity of the strain sensor with a cavity length of about 155 μm and a bubble wall thickness of about 6 μm was measured to be up to 8.14 pm/μϵ.

Convolutional neural network (CNN)-based deep learning techniques have enjoyed many successful applications in the field of medical imaging. However, the complicated between-manifold projection from the projection domain to the spatial domain hinders the direct application of CNN techniques in computed tomography (CT) reconstruction. In this work, we proposed a novel CT reconstruction framework based on a CNN, i.e., an intelligent back-projection network (iBP-Net). The proposed iBP-Net method fused a pre-CNN, a back-projection layer, and a post-CNN into an end-to-end network. The pre-CNN adopted CNN techniques to model a filtering operation in the projection domain. In the back-projection layer, a back-projection operation was employed to perform between-manifold projection. Based on CNN techniques, the post-CNN worked together with the pre-CNN to recover reconstructed images from the outputs of the back-projection layer in the spatial domain while maintaining high visual sensitivity. The experimental results demonstrate the feasibility of the proposed iBP-Net framework for CT reconstruction.

The classic K-SVD based sparse representation denoising algorithm trains the dictionary only with one fixed atom size for the whole image, which is limited in accurately describing the image. To overcome this shortcoming, this paper presents an effective image denoising algorithm with the improved dictionaries. First, according to both geometrical and photometrical similarities, image patches are clustered into different groups. Second, these groups are classified into the flat category, the texture category, and the edge category. In different categories, the atom sizes of dictionaries are designed differently. Then, the dictionary of each group is trained with the atom size determined by the category that the group belongs to and the noisy level. Finally, the denoising method is presented by using sparse representation over the constructed grouped dictionaries with adaptive atom size. Experimental results show that the proposed method achieves better denoising performance than related denoising algorithms, especially in image structure preservation.