SM-GRSNet: sparse mapping-based graph representation segmentation network for honeycomb lung lesion.

Objective. Honeycomb lung is a rare but severe disease characterized by honeycomb-like imaging features and distinct radiological characteristics. Therefore, this study aims to develop a deep-learning model capable of segmenting honeycomb lung lesions from Computed Tomography (CT) scans to address the efficacy issue of honeycomb lung segmentation.Methods. This study proposes a sparse mapping-based graph representation segmentation network (SM-GRSNet). SM-GRSNet integrates an attention affinity mechanism to effectively filter redundant features at a coarse-grained region level. The attention encoder generated by this mechanism specifically focuses on the lesion area. Additionally, we introduce a graph representation module based on sparse links in SM-GRSNet. Subsequently, graph representation operations are performed on the sparse graph, yielding detailed lesion segmentation results. Finally, we construct a pyramid-structured cascaded decoder in SM-GRSNet, which combines features from the sparse link-based graph representation modules and attention encoders to generate the final segmentation mask.Results. Experimental results demonstrate that the proposed SM-GRSNet achieves state-of-the-art performance on a dataset comprising 7170 honeycomb lung CT images. Our model attains the highest IOU (87.62%), Dice(93.41%). Furthermore, our model also achieves the lowest HD95 (6.95) and ASD (2.47).Significance.The SM-GRSNet method proposed in this paper can be used for automatic segmentation of honeycomb lung CT images, which enhances the segmentation performance of Honeycomb lung lesions under small sample datasets. It will help doctors with early screening, accurate diagnosis, and customized treatment. This method maintains a high correlation and consistency between the automatic segmentation results and the expert manual segmentation results. Accurate automatic segmentation of the honeycomb lung lesion area is clinically important.

W-N heteroatom-interface in melon carbon nitride/N-doped tungsten oxide Z-Scheme photocatalyst toward improved photocatalytic hydrogen generation activity.

The construction of heterointerface in photocatalyst is an efficient approach to boost the separation and utilization efficiency of charge carriers, which is challenging and crucial in photocatalysis. Here, the construction of melon-structured carbon nitride/N-doped WO3 (MCN/NWx) heterojunction photocatalyst was achieved by a method of prealcoholysis combined with thermal polymerization, where N-doping of WO3 was achieved in-situ in the formation of heterojunction. The promoted charge separation efficiency was realized through the charge transfer from the conduction band of N-doped WO3 to the valence band of the MCN. Density functional theory calculation results showed that the formation of the W-N heteroatom-interface led to the increase of density of states at the heterointerface and decrease of the band gap. The MCN/NWx nanocomposite featured a metallic band structure of the nanocomposite photocatalysts, resulting in the enhanced photocatalytic activity. The photocatalytic hydrogen evolution activity of the MCN/NW2 was enhanced about 2.5 times than that of MCN. This research provides a novel insight into the construction of a novel heteroatom-junction that boosts the separation efficiency of charge carriers, and thereby improves the photocatalytic activity.

Cross-linking and self-assembly synthesis of tannin-based carbon frameworks cathode for Zn-ion hybrid supercapacitors.

Carbon frameworks with well-developed porosity present broad application prospects in energy-related materials, and green preparation still face challenges. Herein, the tannins-derived framework-like carbon material is obtained by cross-linking and self-assembly strategy.The phenolic hydroxyl and quinones in tannin cross-linking react with the amine groups in the methenamine by simple stirring, which drives the self-assembly of tannins and methenamine,contributing to the reaction products being precipitated in solution as aggregates with framework-like structure. The porosity and micromorphology of framework-like structures are further enriched by the thermal stability difference between tannin and methenamine. The methenamine of framework-like structures is entirely removed by the sublimation and decomposition and the tannin is transformed into carbon materials inheriting framework-like structures after the carbonization, which offers the path for rapid electron transport. The framework-like structure, excellent specific surface area and nitrogen doping give the assembled Zn-ion hybrid supercapacitors a superior specific capacitance of 165.3 mAh·g-1 (350.4 F·g-1). This device could be charged to 1.87 V to power the bulb by using solar panels. This study proves that the tannin-derived framework-like carbon is a promising electrode of the Zn-ion hybrid supercapacitors, which is beneficial for value-added and industrial supercapacitors application of green feedstocks.