HD-Former: A hierarchical dependency Transformer for medical image segmentation.

Medical image segmentation is a compelling fundamental problem and an important auxiliary tool for clinical applications. Recently, the Transformer model has emerged as a valuable tool for addressing the limitations of convolutional neural networks by effectively capturing global relationships and numerous hybrid architectures combining convolutional neural networks (CNNs) and Transformer have been devised to enhance segmentation performance. However, they suffer from multilevel semantic feature gaps and fail to account for multilevel dependencies between space and channel. In this paper, we propose a hierarchical dependency Transformer for medical image segmentation, named HD-Former. First, we utilize a Compressed Bottleneck (CB) module to enrich shallow features and localize the target region. We then introduce the Dual Cross Attention Transformer (DCAT) module to fuse multilevel features and bridge the feature gap. In addition, we design the broad exploration network (BEN) that cascades convolution and self-attention from different percepts to capture hierarchical dense contextual semantic features locally and globally. Finally, we exploit uncertain multitask edge loss to adaptively map predictions to a consistent feature space, which can optimize segmentation edges. The extensive experiments conducted on medical image segmentation from ISIC, LiTS, Kvasir-SEG, and CVC-ClinicDB datasets demonstrate that our HD-Former surpasses the state-of-the-art methods in terms of both subjective visual performance and objective evaluation. Code: https://github.com/barcelonacontrol/HD-Former.

SDMI-Net: Spatially Dependent Mutual Information Network for semi-supervised medical image segmentation.

Semi-supervised medical image segmentation strives to polish deep models with a small amount of labeled data and a large amount of unlabeled data. The efficiency of most semi-supervised medical image segmentation methods based on voxel-level consistency learning is affected by low-confidence voxels. In addition, voxel-level consistency learning fails to consider the spatial correlation between neighboring voxels. To encourage reliable voxel-level consistent learning, we propose a dual-teacher affine consistent uncertainty estimation method to filter out some voxels with high uncertainty. Moreover, we design the spatially dependent mutual information module, which enhances the spatial dependence between neighboring voxels by maximizing the mutual information between the local voxel blocks predicted from the dual-teacher models and the student model, enabling consistent learning at the block level. On two benchmark medical image segmentation datasets, including the Left Atrial Segmentation Challenge dataset and the BraTS-2019 dataset, our method achieves state-of-the-art performance in both quantitative and qualitative aspects.

GL-Segnet: Global-Local representation learning net for medical image segmentation.

Medical image segmentation has long been a compelling and fundamental problem in the realm of neuroscience. This is an extremely challenging task due to the intensely interfering irrelevant background information to segment the target. State-of-the-art methods fail to consider simultaneously addressing both long-range and short-range dependencies, and commonly emphasize the semantic information characterization capability while ignoring the geometric detail information implied in the shallow feature maps resulting in the dropping of crucial features. To tackle the above problem, we propose a Global-Local representation learning net for medical image segmentation, namely GL-Segnet. In the Feature encoder, we utilize the Multi-Scale Convolution (MSC) and Multi-Scale Pooling (MSP) modules to encode the global semantic representation information at the shallow level of the network, and multi-scale feature fusion operations are applied to enrich local geometric detail information in a cross-level manner. Beyond that, we adopt a global semantic feature extraction module to perform filtering of irrelevant background information. In Attention-enhancing Decoder, we use the Attention-based feature decoding module to refine the multi-scale fused feature information, which provides effective cues for attention decoding. We exploit the structural similarity between images and the edge gradient information to propose a hybrid loss to improve the segmentation accuracy of the model. Extensive experiments on medical image segmentation from Glas, ISIC, Brain Tumors and SIIM-ACR demonstrated that our GL-Segnet is superior to existing state-of-art methods in subjective visual performance and objective evaluation.

RMTF-Net: Residual Mix Transformer Fusion Net for 2D Brain Tumor Segmentation.

Due to the complexity of medical imaging techniques and the high heterogeneity of glioma surfaces, image segmentation of human gliomas is one of the most challenging tasks in medical image analysis. Current methods based on convolutional neural networks concentrate on feature extraction while ignoring the correlation between local and global. In this paper, we propose a residual mix transformer fusion net, namely RMTF-Net, for brain tumor segmentation. In the feature encoder, a residual mix transformer encoder including a mix transformer and a residual convolutional neural network (RCNN) is proposed. The mix transformer gives an overlapping patch embedding mechanism to cope with the loss of patch boundary information. Moreover, a parallel fusion strategy based on RCNN is utilized to obtain local-global balanced information. In the feature decoder, a global feature integration (GFI) module is applied, which can enrich the context with the global attention feature. Extensive experiments on brain tumor segmentation from LGG, BraTS2019 and BraTS2020 demonstrated that our proposed RMTF-Net is superior to existing state-of-art methods in subjective visual performance and objective evaluation.

Adverse Event Profiles of PARP Inhibitors: Analysis of Spontaneous Reports Submitted to FAERS.

Background: Several poly ADP ribose polymerase inhibitors (PARPis) are currently approved for the treatment of a variety of cancers. The safety profile of PARPis has not yet been systemically analyzed in the real world. We conducted this pharmacovigilance analysis using the US FDA's Adverse Event Reporting System (FAERS) database to explore the difference in adverse events (AEs) among PARPis. Methods: FAERS data (December 2014 to October 2021) were searched for reports of all FDA-approved PARPis across all indications. We used the standardized MedDRA query (SMQ) generalized search AEs on the preferred term (PT) level based on case reports. After filtering duplicate reports, disproportionality analysis was used to detect safety signals by calculating reporting odds ratios (ROR). Reports were considered statistically significant if the 95% confidence interval did not contain the null value. Results: Within the standardized MedDRA queries, significant safety signals were found, including those for olaparib [blood premalignant disorders (ROR = 17.06)], rucaparib [taste and smell disorders (ROR = 9.17)], niraparib [hematopoietic throbocytopenia (ROR = 28.2)], and talazoparib [hematopoietic erythropenia (ROR = 9.38)]. For AEs on the PT level, we found several significant signals, including platelet count decreased with niraparib (ROR = 52.78); red blood cell count decreased with niraparib (ROR = 70.47) and rucaparib (ROR = 15.09); myelodysplastic syndrome with olaparib (ROR = 35.47); acute myeloid leukaemia with olaparib (ROR = 25.14); blood pressure fluctuation with niraparib (ROR = 20.54); lymphangioleiomyomatosis with niraparib (ROR = 471.20); photosensitivity reaction with niraparib (ROR = 21.77) and rucaparib (ROR = 18.92); renal impairment with rucaparib (ROR = 33.32); and interstitial lung disease with Olaparib (ROR = 11.31). All the detected safety signals were confirmed using signals of disproportionality reporting methods. Conclusion: PARPis differed in their safety profile reports. The analysis of the FAERS database revealed significant safety signals that matched previously published case reports, including serious gastrointestinal, blood and lymphatic system, cardiovascular and respiratory complications, which require individualized drug administration according to patients' conditions.

Intuitionistic Fuzzy C-Means Algorithm Based on Membership Information Transfer-Ring and Similarity Measurement.

The fuzzy C-means clustering (FCM) algorithm is used widely in medical image segmentation and suitable for segmenting brain tumors. Therefore, an intuitionistic fuzzy C-means algorithm based on membership information transferring and similarity measurements (IFCM-MS) is proposed to segment brain tumor magnetic resonance images (MRI) in this paper. The original FCM lacks spatial information, which leads to a high noise sensitivity. To address this issue, the membership information transfer model is adopted to the IFCM-MS. Specifically, neighborhood information and the similarity of adjacent iterations are incorporated into the clustering process. Besides, FCM uses simple distance measurements to calculate the membership degree, which causes an unsatisfactory result. So, a similarity measurement method is designed in the IFCM-MS to improve the membership calculation, in which gray information and distance information are fused adaptively. In addition, the complex structure of the brain results in MRIs with uncertainty boundary tissues. To overcome this problem, an intuitive fuzzy attribute is embedded into the IFCM-MS. Experiments performed on real brain tumor images demonstrate that our IFCM-MS has low noise sensitivity and high segmentation accuracy.

Greatly Enhanced Faradic Capacities of 3D Porous Mn3O4/G Composites as Lithium-Ion Anodes and Supercapacitors by C-O-Mn Bonding.

Through C-O-Mn bonding, graphene nanosheets are homogeneously dispersed in porous Mn3O4 to take full advantages of porous Mn3O4 and graphene nanosheets, making the as-formed three-dimensional porous Mn3O4/reduced graphene oxide (rGO) composite exhibit good electrochemical performance. Besides, C-O-Mn bonding is demonstrated to greatly promote the Faradic reactions of the composite, resulting in the enhancement of its real capacity in supercapacitor (SC) electrodes as well as lithium-ion battery (LIB) anodes. By simply fine-tuning the content of graphene (<7 wt %), the composite with 2.8 wt % of rGO delivers a high capacitance of 315 F g-1 at 0.5 A g-1 with a high rate capability of 64.7% at 30 A g-1 and an excellent cycling stability of 105% (5 A g-1, 5000 cycles) as an SC electrode. Also, the one with 6.9 wt % rGO can present a reversible capacity of more than 1500 mAh g-1 at 0.05 A g-1 as the LIB anode, the highest value reported to date, which remains 561 mAh g-1 at 1 A g-1.

[Controlling effects of dual mulching on soil moisture in an apple orchard].

To investigate the controlling effects of dual mulching on soil moisture in an apple orchard on the Weibei rainfed highland, soil moisture in the 0-600 cm soil profile of the apple orchard was measured under four mulching treatments (plastic film plus straw, plastic film and straw mulches, as well as a non-mulching control) , and meanwhile the apple yield and branch growth increment were analyzed statistically. Results showed that the dual mulching treatment had the best effect on soil moisture conservation, and the soil water storage in such a soil profile was 6.7% higher than the control treatment. Long-term dual mulching could effectively alleviate soil desiccation occurring in deep soil layer in the region, and the monthly averaged soil water storage in stable layer (240-600 cm) was 64.22 mm higher than that of the control treatment. Both plastic film plus straw and plastic film mulches were able to reduce the temporal fluctuation of soil moisture in shallow soil (0-60 cm) and enhance the temporal stability of soil moisture in the layer. Compared with the single mulching treatments, the dual mulching treatment could effectively decrease the vertical variation of soil moisture in the profile and improve the stability of the vertical soil moisture distribution. The apple yield under the dual mulching treatment was evidently increased by 48.2%, as compared with the control treatment. All the analyses showed that dual mulching had more advantages in controlling soil moisture and improving apple yield than single mulching.

[Characteristics of soil moisture in artificial impermeable layers].

For the problem of low water and fertilizer use efficiency caused by nitrate nitrogen lea- ching into deep soil layer and soil desiccation in dryland apple orchard, characteristics of soil moisture were investigated by means of hand tamping in order to find a new approach in improving the water and fertilizer use efficiency in the apple orchard. Two artificial impermeable layers of red clay and dark loessial soil were built in soil, with a thickness of 3 or 5 cm. Results showed that artificial impermeable layers with the two different thicknesses were effective in reducing or blocking water infiltration into soil and had higher seepage controlling efficiency. Seepage controlling efficiency for the red clay impermeable layer was better than that for the dark loessial soil impermeable layer. Among all the treatments, the red clay impermeable layer of 5 cm thickness had the highest bulk density, the lowest initial infiltration rate (0.033 mm · min(-1)) and stable infiltration rate (0.018 mm · min(-1)) among all treatments. After dry-wet alternation in summer and freezing-thawing cycle in winter, its physiochemical properties changed little. Increase in years did not affect stable infiltration rate of soil water. The red clay impermeable layer of 5 cm thickness could effectively increase soil moisture content in upper soil layer which was conducive to raise the water and nutrient use efficiency. The approach could be applied to the apple production of dryland orchard.

Increased cadmium and lead uptake of a cadmium hyperaccumulator tomato by cadmium-resistant bacteria.

Two cadmium (Cd)-resistant strains Pseudomonas sp. RJ10 and Bacillus sp. RJ16 were investigated for their effects on the soil Cd and lead (Pb) solubilization and promotion of plant growth and Cd and Pb uptakes of a Cd-hyperaccumulator tomato. In the heavy metal-contaminated inoculated soil, the CaCl(2)-extractable Cd and Pb were increased by 58-104% and 67-93%, respectively, compared to the uninoculation control. The bacteria produced indole acetic acid, siderophore and 1-aminocyclopropane-1-carboxylate deaminase. Root elongation assay conducted on tomato under gnotobiotic conditions demonstrated increase in root elongation of inoculated tomato seedlings compared to the control plants. An increase in Cd and Pb contents of above-ground tissues varied from 92% to 113% and from 73% to 79% in inoculated plants growing in heavy metal-contaminated soil compared to the uninoculation control, respectively. These results show that the bacteria could be exploited for bacteria enhanced-phytoextraction of Cd- and Pb-polluted soils.

Carotid Intima Media Thickness and Pulse Pressure Index In Elderly Essential Hypertensive Patients / 中华高血压杂志

Objective To investigate the relationship between carotid intima media thickness (IMT) and pulse pressure index (PPI) in elderly hypertensive patients.PPI was defined as 24 h mean pulse pressure(PP)/24 h mean SBP.Methods One hundred and three elderly hypertensive patients were categorized by PPI level:group A (PPI

[Clinical assessment on treatment of hyperlipidemia with pushen capsule].

OBJECTIVE: To explore the therapeutic effect of Pushen capsule (PSC) in treating primary hyperlipidemia. METHODS: Two hundred and forty patients with primary hyperlipidemia were randomly divided into two groups, the 120 patients in the treated group treated with PSC (4 capsules, tid) and the 120 patients in the control group treated with Zhibituo tablet (3 tablets, tid), and they were administered at the same time with Zhibituo placebo. The therapeutic course for both groups was 4 weeks. The therapeutic effect and the effects on blood lipids and viscosity were observed. RESULTS: The effective rate in the treated group was 76.3%, which was significantly higher than that in the control group (48.7%, P < 0.01). PSC showed a significant lowering effect on TC, TG and LDL-C and raising effect on HDL-C, and the effect in lowering TG was significantly better than that of Zhibituo (P < 0.01). PSC also showed a certain effect in decreasing whole blood viscosity of both high-sheared and low-sheared viscosity. CONCLUSION: Pushen capsule has promising blood lipid regulating effect in patients with hyperlipidemia, and some effects in lowering the blood viscosity.

Clinical assessment on treatment of hyperlipidemia with pushen capsule / 中国中西医结合杂志

<p><b>OBJECTIVE</b>To explore the therapeutic effect of Pushen capsule (PSC) in treating primary hyperlipidemia.</p><p><b>METHODS</b>Two hundred and forty patients with primary hyperlipidemia were randomly divided into two groups, the 120 patients in the treated group treated with PSC (4 capsules, tid) and the 120 patients in the control group treated with Zhibituo tablet (3 tablets, tid), and they were administered at the same time with Zhibituo placebo. The therapeutic course for both groups was 4 weeks. The therapeutic effect and the effects on blood lipids and viscosity were observed.</p><p><b>RESULTS</b>The effective rate in the treated group was 76.3%, which was significantly higher than that in the control group (48.7%, P < 0.01). PSC showed a significant lowering effect on TC, TG and LDL-C and raising effect on HDL-C, and the effect in lowering TG was significantly better than that of Zhibituo (P < 0.01). PSC also showed a certain effect in decreasing whole blood viscosity of both high-sheared and low-sheared viscosity.</p><p><b>CONCLUSION</b>Pushen capsule has promising blood lipid regulating effect in patients with hyperlipidemia, and some effects in lowering the blood viscosity.</p>