Local Feature Matters: Cascade Multi-Scale MLP for Edge Segmentation of Medical Images.

Convolution-based methods are increasingly being used in medical image segmentation tasks and have shown good performance, but there are always problems in segmenting edge parts. These methods all have the following challenges: 1) Previous methods do not highlight the relationship between foreground and background in segmented regions, which is helpful for complex segmentation edges, 2) inductive bias of the convolutional layer leads to the fact that the extracted information is mainly the main part of the segmented area, and cannot effectively perceive complex edge changes and the aggregation of small and many segmented areas,3) different regions around the segmentation edge have different reference values for segmentation, and the ordering of these values is more important when the segmentation task is more complex. To address these challenges, we propose the CM-MLP framework on Multi-scale Feature Interaction (MFI) block and Axial Context Relation Encoder (ACRE) block for accurate segmentation of the edge of medical image. In the MFI block, we propose the Cascade Multi-scale MLP (Cascade MLP) to process all local information from the deeper layers of the network simultaneously, using Squeeze and Excitation in Space(SES) to process and redistribute the weights of all windows in Cascade MLP and utilize a cascade multi-scale mechanism to fuse discrete local information gradually. Then, multiple ACRE blocks cooperate with the deep supervision mechanism to gradually explore the boundary relationship between the foreground and the background, and gradually fine-tune the edges of the medical image. The segmentation accuracy (Dice) of our proposed CM-MLP framework reaches 96.98%, 96.67%, and 83.83% on three benchmark datasets: CVC-ClinicDB dataset, sub-Kvasir dataset, and our in-house dataset, respectively, which significantly outperform the state-of-the-art method. The source code and trained models will be available at https://github.com/ProgrammerHyy/CM-MLP.

Electronic structure and second-order nonlinear optical properties of lemniscular [16]cycloparaphenylene compounds.

Chiral organic compounds are excellent second-order nonlinear optical (NLO) materials due to their inherent non-symmetric electronic structures combined with the advantages of organic compounds. At present, density functional theory (DFT) has become a powerful tool for predicting the properties of novel materials. In this paper, based on chiral lemniscular [16]cycloparaphenylene, three novel compounds are designed by introduction of donor/acceptor units and their combinations. The geometrical/electronic structure, electronic absorption, and the second-order NLO properties of these compounds have been systematically investigated by DFT/TDDFT theory. The simulated UV-Vis/CD spectra of compound 1 are in good agreement with the experimental ones, enabling us to assign their electronic transition characteristics and absolute configuration with high confidence. The investigations show that energy gaps, absorption wavelength and second-order NLO response may be effectively tuned by the introduction of the donor or acceptor units or their combinations. For instance, the second-order NLO value of compound 4 is about 207 times as large as the average second-order polarizability of the organic molecule urea. Thus, the studied compounds are expected to be potential large second-order NLO materials.

Theoretical study on the electronic structure and second-order nonlinear optical properties of benzannulated or selenophene-annulated expanded helicenes.

Currently, discovering new materials with superior second-order nonlinear optical (NLO) performance has become a very hot research topic in the fields of chemistry and materials science. Now, density functional theory (DFT) has become a powerful tool to predict the performance of novel materials. In this paper, based on benzannulated and selenophene-annulated expanded helicenes, twenty-six helicenes are designed by introduction donor/acceptor moieties and their combinations at different substituent positions. The geometrical/electronic structures, electronic transition, and second-order NLO properties of these helicenes are full investigated by DFT/TDDFT theory. The investigations show that these helicenes have large first hyperpolarizability values (ß HRS). For instance, the ß HRS value (29.95 × 10-30 esu) of helicene H24 is about 7 times larger than that of the highly π-delocalized phenyliminomethyl ferrocene complex. In addition, the introduction of acceptor NO2 unit at R7 and R8 positions for helicenes H1 and H15 can obtain the largest ß HRS value, which is attributed to the enhancement of electron acceptor ability. In view of large NLO response and intrinsic asymmetric structures, the studied helicenes have the possibility to be excellent second-order NLO materials.