Dynamic graph transformer network via dual-view connectivity for autism spectrum disorder identification.

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder that requires objective and accurate identification methods for effective early intervention. Previous population-based methods via functional connectivity (FC) analysis ignore the differences between positive and negative FCs, which provide the potential information complementarity. And they also require additional information to construct a pre-defined graph. Meanwhile, two challenging demand attentions are the imbalance of performance caused by the class distribution and the inherent heterogeneity of multi-site data. In this paper, we propose a novel dynamic graph Transformer network based on dual-view connectivity for ASD Identification. It is based on the Autoencoders, which regard the input feature as individual feature and without any inductive bias. First, a dual-view feature extractor is designed to extract individual and complementary information from positive and negative connectivity. Then Graph Transformer network is innovated with a hot plugging K-Nearest Neighbor (KNN) algorithm module which constructs a dynamic population graph without any additional information. Additionally, we introduce the PolyLoss function and the Vrex method to address the class imbalance and improve the model's generalizability. The evaluation experiment on 1102 subjects from the ABIDE I dataset demonstrates our method can achieve superior performance over several state-of-the-art methods and satisfying generalizability for ASD identification.

Microfluidics-aided fabrication of 3D micro-nano hierarchical SERS substrate for rapid detection of dual hepatocellular carcinoma biomarkers.

The simultaneous analysis of trace amounts of dual biomarkers is crucial in the early diagnosis, treatment, and prognosis of hepatocellular carcinoma (HCC). In this study, we prepared SERS-active hydrogel microparticles (SAHMs) with 3D hierarchical gold nanoparticles (AuNPs) micro-nanostructures by microdroplet technology and in situ synthesis, which demonstrated high reproducibility and sensitivity. Compared with traditional 2D SERS substrates, this newly prepared 3D SERS substrate provided a high density of nano-wrinkled structures and numerous AuNPs. Furthermore, a newly designed SERS-active substrate was proposed for the simultaneous microfluidic detection of AFP and AFU. The Raman signals of sandwich immunocomplexes on the surface of the SAHMs were measured for the trace analysis of these biomarkers. The proposed microfluidic platform achieved AFP and AFU detection in the range of 0.1-100 ng mL-1 and 0.01-100 ng mL-1, respectively, which represents a good response. Indeed, this platform is easy to fabricate, of low cost and has short detection time and comparable detection limits to other methods. As far as we know, this is the first study to achieve the simultaneous detection of AFP and AFU on a microfluidic platform. Therefore, we proposed a new simultaneous detection platform for dual HCC biomarkers that shows strong potential for the early diagnosis of HCC.

Donor-π-Acceptor Porphyrin-Assisted Bifunctional Defect Passivation for Enhanced Temporal Domain-/Wavelength-Dependent Nonlinear Absorption Properties in Perovskite Films.

Perovskite layer defects are a primary inhibiting factor for their optical nonlinearity, which restricts their use in nonlinear photonics devices. Nevertheless, due to the variety of defect types, the passivation and repair of these defects remain challenging. Herein, a novel bifunctional passivation strategy was proposed, and the porphyrin with a donor-π-acceptor structure was designed to bifunctionally repair perovskite defects by linking different types of functional groups via acetylenic π-conjugated linkage bridges on both sides, thus improving the nonlinear optical (NLO) absorption properties of porphyrin-perovskite hybrid materials. Research results indicate that the amino and carboxyl groups of porphyrins endow the ability to bifunctionally passivate charged defects via effective coordination interactions. The nonlinear absorption properties of all porphyrin-passivated MAPbI3 films were remarkably enhanced compared to that of the MAPbI3 film across multiple wavelengths and temporal domains. Particularly, the Por3-passivated perovskite film (MAPbI3/Por3) exhibited optimized strongest NLO performance, including reverse saturable absorption (RSA) under 800 nm femtosecond (fs) and 1064 nm nanosecond (ns) laser irradiations, as well as saturable absorption (SA) with 515 and 532 nm ns laser excitations. The value of the NLO absorption coefficient (ß = 266.23 cm GW-1) is 1 order of magnitude higher than that of the pristine perovskite film (ß = 12.93 cm GW-1), also outperforming other porphyrin-passivated perovskite films and some reported materials. The bifunctional passivation mechanism of porphyrin not only intensifies the perovskite's photoinduced ground-state dipole moment in the two-photon absorption (TPA) process and the free carrier absorption ability to deepen the RSA properties under 800 nm fs and 1064 nm ns lasers, respectively, but also enables the improvement of SA responses under 515 nm fs and 532 nm ns lasers by expediting the Pauli blocking effect of perovskite. Our study offers a viable paradigm, which aims at exploiting high-performance NLO perovskite materials across wide spectral regions and time scales.

MC-UNet: Multimodule Concatenation Based on U-Shape Network for Retinal Blood Vessels Segmentation.

Accurate retinal blood vessels segmentation is an important step in the clinical diagnosis of ophthalmic diseases. Many deep learning frameworks have come up for retinal blood vessels segmentation tasks. However, the complex vascular structure and uncertain pathological features make blood vessel segmentation still very challenging. This paper proposes a novel multimodule concatenation via a U-shaped network for retinal vessels segmentation, which is based on atrous convolution and multikernel pooling. The proposed network structure retains three layers of the essential structure of U-Net, in which the atrous convolution combining the multikernel pooling blocks are designed to obtain more contextual information. The spatial attention module is concatenated with the dense atrous convolution module and the multikernel pooling module to form a multimodule concatenation. And different dilation rates are selected by cascading to acquire a larger receptive field in atrous convolution. Adequate comparative experiments are conducted on these public retinal datasets: DRIVE, STARE, and CHASE_DB1. The results show that the proposed method is effective, especially for microvessels. The code will be released at https://github.com/rocklijun/MC-UNet.