DE-JANet: A unified network based on dual encoder and joint attention for Alzheimer's disease classification using multi-modal data.

Structural magnetic resonance imaging (sMRI), which can reflect cerebral atrophy, plays an important role in the early detection of Alzheimer's disease (AD). However, the information provided by analyzing only the morphological changes in sMRI is relatively limited, and the assessment of the atrophy degree is subjective. Therefore, it is meaningful to combine sMRI with other clinical information to acquire complementary diagnosis information and achieve a more accurate classification of AD. Nevertheless, how to fuse these multi-modal data effectively is still challenging. In this paper, we propose DE-JANet, a unified AD classification network that integrates image data sMRI with non-image clinical data, such as age and Mini-Mental State Examination (MMSE) score, for more effective multi-modal analysis. DE-JANet consists of three key components: (1) a dual encoder module for extracting low-level features from the image and non-image data according to specific encoding regularity, (2) a joint attention module for fusing multi-modal features, and (3) a token classification module for performing AD-related classification according to the fused multi-modal features. Our DE-JANet is evaluated on the ADNI dataset, with a mean accuracy of 0.9722 and 0.9538 for AD classification and mild cognition impairment (MCI) classification, respectively, which is superior to existing methods and indicates advanced performance on AD-related diagnosis tasks.

Understanding the Mechanism and Selectivity of 1,1-Diborylalkanes from Alkenes Catalyzed by a Zirconium Complex.

The synthesis of 1,1-diborylalkanes from readily available alkenes is an appealing method. The density functional theory (DFT) method was employed to investigate the reaction mechanism of 1,1-diborylalkanes, which was synthesized from alkenes and a borane, and the reaction was catalyzed by a zirconium complex Cp2ZrCl2. The entire reaction is divided into two cycles: dehydrogenative boration to form vinyl boronate esters (VBEs) and hydroboration of VBEs. This article focuses on the hydroboration cycle and elaborates on the role of the reducing reagents in the equilibrium of self-contradictory reactivity (dehydrogenative boration and hydroboration). The H2 and HBpin pathways were investigated as the reducing reagents in the hydroboration process. The calculated results showed that it is more advantageous to use H2 as a reducing agent (path A). Furthermore, the σ-bond metathesis is the rate-determining step (RDS) with an energetic span of 21.4 kcal/mol. This is consistent with the self-contradictory reactivity balance proposed in the experiment. The reaction modes of the hydroboration process were also discussed. These analyses revealed the origin of selectivity in this boration reaction, in which the σ-bond metathesis of HBpin needs to overcome the strong interaction between HBpin and the Zr metal. Meanwhile, the origin of the selectivity of different positions of H2 is the interaction between the σ(H1-H2) → σ*(Zr1-C1) overlap and these findings have implications for catalyst design and application.

Density Functional Theory Study on the H2-Acceptorless Dehydrogenative Boration of Alkenes Catalyzed by a Zirconium Complex.

For the synthesis of vinyl boronate esters, the direct catalytic H2-acceptorless dehydrogenative boration of alkenes is one of the promising strategies. In this paper, the density functional theory method was employed to investigate the reaction mechanism of dehydrogenative boration and transfer boration of alkenes catalyzed by a zirconium complex (Cp2ZrH2). There are two possible pathways for this reaction: the alkene insertion followed by the dehydrogenative boration (path A) and the alkene insertion after the dehydrogenative boration (path B). The calculated results showed that path A is more favorable than path B, and that the rate-determining step is the C-B coupling step with an energy barrier of 18.7 kcal/mol. The reaction modes of the C-B coupling assisted dehydrogenative boration and the alkene insertion were also discussed. These analyses reveal a novel hydrogen release behavior in dehydrogenative boration and the alkene insertion modes and sequences were proposed to be of importance in the chemoselectivity of this reaction. In addition, the X ligand effect (X = H, Cl) on the catalytic activity of the zirconium complex was explored, indicating that the H ligand could enhance the catalytic activity of the complex for styrene dehydrogenative boration.

Multi-Label Classification Scheme Based on Local Regression for Retinal Vessel Segmentation.

Segmenting small retinal vessels with width less than 2 pixels in fundus images is a challenging task. In this paper, in order to effectively segment the vessels, especially the narrow parts, we propose a local regression scheme to enhance the narrow parts, along with a novel multi-label classification method based on this scheme. We consider five labels for blood vessels and background in particular: the center of big vessels, the edge of big vessels, the center as well as the edge of small vessels, the center of background, and the edge of background. We first determine the multi-label by the local de-regression model according to the vessel pattern from the ground truth images. Then, we train a convolutional neural network (CNN) for multi-label classification. Next, we perform a local regression method to transform the previous multi-label into binary label to better locate small vessels and generate an entire retinal vessel image. Our method is evaluated using two publicly available datasets and compared with several state-of-the-art studies. The experimental results have demonstrated the effectiveness of our method in segmenting retinal vessels.

A Survey on Intelligent Screening for Diabetic Retinopathy.

Diabetic retinopathy (DR) is one of the leading causes of vision loss and can be effectively avoided by screening, early diagnosis and treatment. In order to increase the universality and efficiency of DR screening, many efforts have been invested in developing intelligent screening, and there have been great advances. In this paper, we survey DR screening from four perspectives: 1) public color fundus image datasets of DR; 2) DR classification and related lesion-extraction approaches; 3) existing computer-aided systems for DR screening; and 4) existing issues, challenges, and research trends. Our goal is to provide insights for future research directions on DR intelligent screening.

[Effects of sublingual immunotherapy on serum IL-17 and IL-35 levels in children with allergic rhinitis or asthma].

OBJECTIVE: To study the clinical effect and mechanisms of specific sublingual immunotherapy (SLIT) for the treatment of allergic rhinitis or asthma in children. METHODS: Thirty children suffering from Dermatophagoides farinae-allergic rhinitis or asthma (case group) and 30 healthy children (control group) were enrolled in this study. The case group accepted SLIT between January and December 2011. The ratio of forced expiratory volume in one second (FEV1) and its expected value, the ratio of airway resistance and its expected value, peripheral blood eosinophil (Eos) count and serum levels of IL-17 and IL-35 were measured before treatment and one and two years after treatment. The rhinitis or asthma symptom scores were rated and the level of asthma control was monitored. RESULTS: Serum IL-17 level in the case group was significantly higher than in the control group before treatment and one year after treatment (P<0.01). Furthermore, serum IL-17 level in the case group gradually decreased from before treatment to 1 year to 2 years after treatment (P<0.01). By two years of treatment, there was no significant difference in serum IL-17 level between the case and control groups (P>0.05). The changes of serum IL-35 level after treatment were opposite to serum IL-17 in the case group. The ratio of FEV1 and its expected value gradually increased from before treatment to 1 year to 2 years after treatment (P<0.01) in the case group. In contrast, the change of the ratio of airway resistance and its expected value and Eos count gradually decreased from before treatment to 1 year to 2 years after treatment (P<0.01) in the case group. More patients achieved improved rhinitis or asthma symptom scores two years after treatment than one year after treatment in the case group (P<0.01). SLIT was effective in 85% of children with allergic rhinitis one after treatment vs 100% two years after treatment. Asthma control was observed in 76% of the asthmatic patients one after treatment vs 92% two years after treatment. CONCLUSIONS: SLIT is effective for allergic rhinitis and asthma in children, and the treatment period of two years seems to be superior to one year. The mechanism of action of SLIT for the treatment of allergic rhinitis and asthma may be associated with inhibition of IL-17 expression and promotion of IL-35 expression.

Franck-Condon simulation of vibrationally resolved optical spectra for zinc complexes of phthalocyanine and tetrabenzoporphyrin including the Duschinsky and Herzberg-Teller effects.

High resolved absorption and fluorescence spectra of zinc complexes of phthalocyanine (ZnPc) and tetrabenzoporphyrin (ZnTBP) in the region of Q states were reported. Few theoretical investigations were performed to simulate the well-resolved spectra and assigned the vibrational bands of the large molecules, especially for high symmetrical characteristic molecules, on account of the difficulties to optimize the excited states and analyze a large number of final vibrational-normal modes. In the present work, the S(0) ↔ S(1) absorption and fluorescence spectra (that is, the Q band) of ZnPc and ZnTBP were simulated using time-dependent density functional theory with the inclusions of Duschinsky and Herzberg-Teller contributions to the electronic transition dipole moments. The theoretical results provide a good description of the optical spectra and are proved to be in excellent agreement with experimental spectra in inert-gas matrices or in supersonic expansion. This study focused attentions on the optical spectral similarities and contrasts between ZnPc and ZnTBP, in particular the noticeable Duschinsky and Herzberg-Teller effects on the high-resolved absorption and fluorescence spectra were considered. Substitution of meso-tetraaza on the porphyrin macrocycle framework could affect the ground state geometry and alter the electron density distributions, the orbital energies that accessible in the Q band region of the spectrum. The results were used to help interpret both the nature of the electronic transitions in Q band region, and the spectral discrepancies between phthalocyanine and porphyrin systems.