ScribFormer: Transformer Makes CNN Work Better for Scribble-based Medical Image Segmentation.

Most recent scribble-supervised segmentation methods commonly adopt a CNN framework with an encoder-decoder architecture. Despite its multiple benefits, this framework generally can only capture small-range feature dependency for the convolutional layer with the local receptive field, which makes it difficult to learn global shape information from the limited information provided by scribble annotations. To address this issue, this paper proposes a new CNN-Transformer hybrid solution for scribble-supervised medical image segmentation called ScribFormer. The proposed ScribFormer model has a triple-branch structure, i.e., the hybrid of a CNN branch, a Transformer branch, and an attention-guided class activation map (ACAM) branch. Specifically, the CNN branch collaborates with the Transformer branch to fuse the local features learned from CNN with the global representations obtained from Transformer, which can effectively overcome limitations of existing scribble-supervised segmentation methods. Furthermore, the ACAM branch assists in unifying the shallow convolution features and the deep convolution features to improve model's performance further. Extensive experiments on two public datasets and one private dataset show that our ScribFormer has superior performance over the state-of-the-art scribble-supervised segmentation methods, and achieves even better results than the fully-supervised segmentation methods. The code is released at https://github.com/HUANGLIZI/ScribFormer.

LViT: Language Meets Vision Transformer in Medical Image Segmentation.

Deep learning has been widely used in medical image segmentation and other aspects. However, the performance of existing medical image segmentation models has been limited by the challenge of obtaining sufficient high-quality labeled data due to the prohibitive data annotation cost. To alleviate this limitation, we propose a new text-augmented medical image segmentation model LViT (Language meets Vision Transformer). In our LViT model, medical text annotation is incorporated to compensate for the quality deficiency in image data. In addition, the text information can guide to generate pseudo labels of improved quality in the semi-supervised learning. We also propose an Exponential Pseudo label Iteration mechanism (EPI) to help the Pixel-Level Attention Module (PLAM) preserve local image features in semi-supervised LViT setting. In our model, LV (Language-Vision) loss is designed to supervise the training of unlabeled images using text information directly. For evaluation, we construct three multimodal medical segmentation datasets (image + text) containing X-rays and CT images. Experimental results show that our proposed LViT has superior segmentation performance in both fully-supervised and semi-supervised setting. The code and datasets are available at https://github.com/HUANGLIZI/LViT.

A Distance Transformation Deep Forest Framework With Hybrid-Feature Fusion for CXR Image Classification.

Detecting pneumonia, especially coronavirus disease 2019 (COVID-19), from chest X-ray (CXR) images is one of the most effective ways for disease diagnosis and patient triage. The application of deep neural networks (DNNs) for CXR image classification is limited due to the small sample size of the well-curated data. To tackle this problem, this article proposes a distance transformation-based deep forest framework with hybrid-feature fusion (DTDF-HFF) for accurate CXR image classification. In our proposed method, hybrid features of CXR images are extracted in two ways: hand-crafted feature extraction and multigrained scanning. Different types of features are fed into different classifiers in the same layer of the deep forest (DF), and the prediction vector obtained at each layer is transformed to form distance vector based on a self-adaptive scheme. The distance vectors obtained by different classifiers are fused and concatenated with the original features, then input into the corresponding classifier at the next layer. The cascade grows until DTDF-HFF can no longer gain benefits from the new layer. We compare the proposed method with other methods on the public CXR datasets, and the experimental results show that the proposed method can achieve state-of-the art (SOTA) performance. The code will be made publicly available at https://github.com/hongqq/DTDF-HFF.

MRDFF: A deep forest based framework for CT whole heart segmentation.

Automatic whole heart segmentation plays an important role in the treatment and research of cardiovascular diseases. In this paper, we propose an improved Deep Forest framework, named Multi-Resolution Deep Forest Framework (MRDFF), which accomplishes whole heart segmentation in two stages. We extract the heart region by binary classification in the first stage, thus avoiding the class imbalance problem caused by too much background. The results of the first stage are then subdivided in the second stage to obtain accurate cardiac substructures. In addition, we also propose hybrid feature fusion, multi-resolution fusion and multi-scale fusion to further improve the segmentation accuracy. Experiments on the public dataset MM-WHS show that our model can achieve comparable accuracy in about half the training time of neural network models.

Effects of wood fiber impulse-cyclone drying process on the UV-accelerated aging properties of wood-plastic composites.

The impulse-cyclone drying and the silane coupling agent (A187) modification are applied to treat wood fibers under the following conditions: 180°C, 180°C+A187, 200°C+A187, 220°C+A187 and 240°C+ A187. Then, HDPE/wood fiber composites are fabricated with a two-stage plastic extruder, and the effects of impulse-cyclone drying technique on the UV-accelerated aging properties of composites are investigated. Fourier-transform infrared spectroscopy (FTIR) reveals that the silane coupling agent chemically reacts with the hydroxyl groups on the wood fiber surfaces, the anti-UV aging properties of composites is enhanced. Mechanical test shows that during the 0-3000 h of UV aging process, the mechanical properties of samples tend to increase initially and then decrease within a period of time. After 3000 h of UV aging, the specimen 4 exhibits the least loss of mechanical properties, with flexural modulus, flexural modulus and impact strength of 65.40 Mpa, 2082.08 Mpa and 12.85 Mpa, respectively. The effects of impulse-cyclone drying technique on the UV-accelerated aging properties of composites are investigated through Spectrophotometry and Surface microstructure observation. indicates that the ΔL* and ΔE* values increase greatly at the stage of 0-1000 h aging, which though tend to stabilize after 1000 h. The degree of discoloration changes little for specimen 4,and the number of surface cracks is relatively small, which exhibits the optimal aging resistance. In conclusion, the addition of wood fibers treated by impulse-cyclone drying (220°C) and A187 modification is effective in enhancing the anti-UV aging properties of HDPE/wood fiber composites. Nevertheless, such enhancing effect turns to decline when the temperature of impulse-cyclone drying treatment is excessively high.

Genetic Association of ERCC6 rs2228526 Polymorphism with the Risk of Cancer: Evidence from a Meta-Analysis.

At present, several studies have assessed the association between ERCC6 rs2228526 polymorphism and the risk of cancer. However, the association remained controversial. To provide a more accurate estimate on the association, we performed a meta-analysis search of case-control studies on the associations of ERCC6 rs2228526 with susceptibility to cancer. PubMed, Embase, Google Scholar, Wanfang database, and Chinese National Knowledge Infrastructure databases (CNKI) China Biological Medicine Database (CBM) (up to August 2021) were searched to identify eligible studies. The effect summary odds ratio (OR) with 95% confidence intervals (CI) was applied to assay the association between the ERCC6 rs2228526 polymorphism and the risk of cancer. 14 studies included 15 case-control studies which contained 5,856 cases, and 6,387 controls were finally determined as qualified studies for this meta-analysis. Overall, based on current studies, we found significant association between ERCC6 rs2228526 polymorphism and the risk of cancer in four genetic models [the allele model G vs. A: 1.10, (1.03-1.17); the homozygous model GG vs. AA: 1.27, (1.07-1.51); heterozygote model GA vs. AA: 1.08, (1.00-1.17); the dominant model GG + GA vs. AA: 1.10, (1.02-1.19); the recessive model GG vs. GA + AA: 1.22, (1.03-1.45)]. In the stratified analysis based on ethnicity, we found significant association in two genetic models in Asians. Further, significant genetic cancer susceptibility was found under PB control on subgroup analysis by source of control. In addition, no significant association was found in lung cancer and bladder cancer patients in subgroup analyses based on cancer style. This study suggests that the ERCC6 rs2228526 polymorphism may be associated with increased cancer risk.

Fucoxanthin regulates Nrf2 signaling to decrease oxidative stress and improves renal fibrosis depending on Sirt1 in HG-induced GMCs and STZ-induced diabetic rats.

Diabetic nephropathy (DN) is one of the major microvascular complications of diabetes. Nuclear factor erythroid 2-related factor 2 (Nrf2) is a crucial cellular defense factor to cope with oxidative stress. Silent information regulator T1 (Sirt1) is a deacetylase with antioxidative stress activity. Fucoxanthin is a marine-derived carotenoid. This study was conducted to investigate whether fucoxanthin could alleviate oxidative stress by activating Sirt1/Nrf2 signaling to alleviate DN. In streptozotocin-induced diabetic rats, fucoxanthin treatment effectively improved renal function, alleviated glomerulosclerosis. Fucoxanthin reversed the decreased protein levels of Sirt1 and Nrf2 in the kidney of diabetic rats and glomerular mesangial cells cultured in high glucose. Conversely, EX527, a Sirt1 inhibitor, counteracted the effect of fucoxanthin on the expression of Nrf2. Furthermore, in vivo and vitro results showed that fucoxanthin treatment reversed the low expression and activity of superoxide dismutase and heme oxygenase 1, depending on Sirt1 activation. Our results suggest that fucoxanthin improves diabetic kidney function and renal fibrosis by activating Sirt1/Nrf2 signaling to reduce oxidative stress.

A direct slicing technique for the 3D printing of implicitly represented medical models.

In conventional medical image printing methods, volumetric medical data needs to be conversed into STereo Lithography (STL) format, the most commonly used format for representing geometric models for 3D printing. However, this STL conversion process is not only time consuming, but more importantly, it often leads to the loss of accuracy. It has become a critical factor hindering the printing efficiency and precision of organ models. By examining the key characteristics of discrete medical volume data, this paper proposes a direct slicing technique for printing implicitly represented 3D medical models. The proposed method mainly consists of three algorithms: (1) A layer-based contour extraction algorithm for discrete volume data; (2) An inner shell construction algorithm based on discrete point differential indentation; (3) An infill generation algorithm based on the constructed virtual contour and scan lines. The proposed method has been applied to the slicing of several organ models for experiments, and the ratios of time cost and memory cost between the conventional method and the proposed method are about 4-100 and 1.1 to 1.4 respectively, which demonstrate that the proposed method has a great improvement in both time and space performance when compared with the conventional STL-based method. Our technique extends the direct input format of geometric models for additive manufacturing. That is, discrete volume data can be used as a direct input for additive manufacturing without conversion to STL format.

High-quality vascular modeling and modification with implicit extrusion surfaces for blood flow computations.

BACKGROUND AND OBJECTIVE: High-quality vascular modeling is crucial for blood flow simulations, i.e., computational fluid dynamics (CFD). As without an accurate geometric representation of the smooth vascular surface, it is impossible to make meaningful blood flow simulations. The purpose of this work is to develop high-quality vascular modeling and modification method for blood flow computations. METHODS: We develop a new technique for the accurate geometric modeling and modification of vasculatures using implicit extrusion surfaces (IES). In the proposed method, the skeleton of the vascular structure is subdivided into short curve segments, each of which is then represented implicitly locally as the intersection of two mutually orthogonal implicit surfaces defined by distance functions. A set of contour points is extracted and fitted with an implicit curve for accurately specifying the vessel cross-section profile, which is then extruded locally along the skeleton to fill the gaps between two vascular tube cross sections. We also present a new implicit geometric editing technique to modify the constructed vascular model with pathology for virtual stenting. RESULTS: Experimental results and validations show that accurate vascular models with highly smooth surfaces can be generated by the proposed method. In addition, we conduct some blood flow simulations to indicate the effectiveness of proposed method for hemodynamic simulations. CONCLUSIONS: The proposed technique can achieve precise geometric models of vasculatures with any required degree of smoothness for reliable blood flow simulations.

Effects of impulse-cyclone drying and silane modification on the properties of wood fiber/HDPE composite material.

Poplar fibers were pretreated under impulse-cyclone drying (ICD) and further modified by different types of silane with special chemical structures. The effects of ICD-assisted silane modification on the properties of wood plastic composites (WPCs) were investigated. The main findings indicated that the number of hydroxyl groups and the polarity of the fibers decreased after the ICD/silane co-modification, whereas the hydrophobicity and crystallinity of fibers, the compatibility and adhesion strength between fibers and plastics, and the mechanical properties, thermostability, and dynamic mechanical properties of WPCs were significantly improved. In this study, when the wood fibers were only modified by silane and the silane content was 5%, the WPCs had better properties, and the WPCs modified with vinyl tri-methoxysilane (A-171) had the best properties. Furthermore, the addition of a small amount of silane to the wood fibers modified by ICD provided even better physical and mechanical properties compared to those of the WPCs that were only modified by silane; when 3% silane was added, there were increases of 10.67%, 10.22% and 9.4%, in the tensile, flexural and impact strengths, respectively, and an increase of 6.84% in the contact angle of the composites. The water absorption rate of the composite significantly decreased as well.

Towards additive manufacturing oriented geometric modeling using implicit functions.

Surface-based geometric modeling has many advantages in terms of visualization and traditional subtractive manufacturing using computer-numerical-control cutting-machine tools. However, it is not an ideal solution for additive manufacturing because to digitally print a surface-represented geometric object using a certain additive manufacturing technology, the object has to be converted into a solid representation. However, converting a known surface-based geometric representation into a printable representation is essentially a redesign process, and this is especially the case, when its interior material structure needs to be considered. To specify a 3D geometric object that is ready to be digitally manufactured, its representation has to be in a certain volumetric form. In this research, we show how some of the difficulties experienced in additive manufacturing can be easily solved by using implicitly represented geometric objects. Like surface-based geometric representation is subtractive manufacturing-friendly, implicitly described geometric objects are additive manufacturing-friendly: implicit shapes are 3D printing ready. The implicit geometric representation allows to combine a geometric shape, material colors, an interior material structure, and other required attributes in one single description as a set of implicit functions, and no conversion is needed. In addition, as implicit objects are typically specified procedurally, very little data is used in their specifications, which makes them particularly useful for design and visualization with modern cloud-based mobile devices, which usually do not have very big storage spaces. Finally, implicit modeling is a design procedure that is parallel computing-friendly, as the design of a complex geometric object can be divided into a set of simple shape-designing tasks, owing to the availability of shape-preserving implicit blending operations.

Effect of Modified Red Pottery Clay on the Moisture Absorption Behavior and Weatherability of Polyethylene-Based Wood-Plastic Composites.

Red pottery clay (RPC) was modified using a silane coupling agent, and the modified RPC (mRPC) was then used to enhance the performance of high-density polyethylene-based wood-plastic composites. The effect of the mRPC content on the performances of the composites was investigated through Fourier transform infrared spectrometry, differential mechanical analysis (DMA) and ultraviolet (UV)-accelerated aging tests. After adding the mRPC, a moisture adsorption hysteresis was observed. The DMA results indicated that the mRPC effectively enhanced the rigidity and elasticity of the composites. The mRPC affected the thermal gravimetric, leading to a reduction of the thermal degradation rate and a right-shift of the thermal degradation peak; the initial thermal degradation temperature was increased. After 3000 h of UV-accelerated aging, the flexural strength and impact strength both declined. For aging time between 0 and 1000 h, the increase in amplitude of ΔL* (luminescence) and ΔE* (color) reached a maximum; the surface fading did not became obvious. ΔL* and ΔE* increased more significantly between 1000 and 2000 h. These characterization results indicate that the chromophores of the mRPC became briefly active. However, when the aging times were higher than 2000 h, the photo-degradation reaction was effectively prevented by adding the mRPC. The best overall enhancement was observed for an mRPC mass percentage of 5%, with a storage modulus of 3264 MPa and an increase in loss modulus by 16.8%, the best anti-aging performance and the lowest degree of color fading.

High-Temperature Hot Air/Silane Coupling Modification of Wood Fiber and Its Effect on Properties of Wood Fiber/HDPE Composites.

The surfaces of poplar wood fibers were modified using high-temperature hot air (HTHA) treatment and silane coupling agent. The single factor test was then used to investigate the performances (e.g., the change of functional groups, polarity, cellulose crystallinity, and thermal stability) of modified poplar wood fibers (mPWF) through Fourier transform infrared spectrometry, X-ray diffraction and thermo-gravimetric analysis for the subsequent preparation of wood-plastic composites (WPCs). The effect of HTHA treatment conditions-such as temperature, inlet air velocity, and feed rate-on the performances of WPCs was also investigated by scanning electron microscopy and dynamic mechanical analysis. The main findings indicated that HTHA treatment could promote the hydration of mPWF and improve the mechanical properties of WPCs. Treatment temperature strongly affected the mechanical properties and moisture adsorption characteristics of the prepared composites. With the increase of treated temperature and feed rate, the number of hydroxyl groups, holocellulose content, and the pH of mPWF decreased. The degree of crystallinity and thermal stability and the storage modulus of the prepared composites of mPWF increased. However, dimensional stability and water absorption of WPCs significantly reduced. The best mechanical properties enhancement was observed with treatment temperature at 220 °C. This study demonstrated the feasibility for the application of an HTHA treatment in the WPC production industry.

Effect of Surface-Modified TiO2 Nanoparticles on the Anti-Ultraviolet Aging Performance of Foamed Wheat Straw Fiber/Polypropylene Composites.

Surface modification and characterization of titanium dioxide (TiO2) nanoparticles and their roles in thermal, mechanical, and accelerated aging behavior of foamed wheat straw fiber/polypropylene (PP) composites are investigated. To improve the dispersion of nanoparticles and increase the possible interactions between wheat straw fiber and the PP matrix, the surface of the TiO2 nanoparticles was modified with ethenyltrimethoxy silane (A171), a silane coupling agent. The grafting of A171 on the TiO2 nanoparticles' surface was characterized by Fourier transform infrared spectroscopy (FTIR). The wheat straw fibers treated with A171 and modified TiO2 nanoparticles were characterized by FTIR and thermogravimetric analysis (TGA). FTIR spectra confirmed that the organic functional groups of A171 were successfully grafted onto the TiO2 nanoparticles and wheat straw fibers, and the modified TiO2 nanoparticles were adsorbed onto the wheat straw fibers. Thermogravimetric analysis showed that a higher thermal stability of the wheat straw fiber was obtained with the modified TiO2 nanoparticles. The flexural, tensile, and impact properties were improved. A higher ultraviolet (UV) stability of the samples treated with modified TiO2 nanoparticles was exhibited by the study of the color change and loss in mechanical properties.

Coaxial Electrospinning and Characterization of Core-Shell Structured Cellulose Nanocrystal Reinforced PMMA/PAN Composite Fibers.

A modified coaxial electrospinning process was used to prepare composite nanofibrous mats from a poly(methyl methacrylate) (PMMA) solution with the addition of different cellulose nanocrystals (CNCs) as the sheath fluid and polyacrylonitrile (PAN) solution as the core fluid. This study investigated the conductivity of the as-spun solutions that increased significantly with increasing CNCs addition, which favors forming uniform fibers. This study discussed the effect of different CNCs addition on the morphology, thermal behavior, and the multilevel structure of the coaxial electrospun PMMA + CNCs/PAN composite nanofibers. A morphology analysis of the nanofibrous mats clearly demonstrated that the CNCs facilitated the production of the composite nanofibers with a core-shell structure. The diameter of the composite nanofibers decreased and the uniformity increased with increasing CNCs concentrations in the shell fluid. The composite nanofibrous mats had the maximum thermal decomposition temperature that was substantially higher than electrospun pure PMMA, PAN, as well as the core-shell PMMA/PAN nanocomposite. The BET (Brunauer, Emmett and Teller) formula results showed that the specific surface area of the CNCs reinforced core-shell composite significantly increased with increasing CNCs content. The specific surface area of the composite with 20% CNCs loading rose to 9.62 m²/g from 3.76 m²/g for the control. A dense porous structure was formed on the surface of the electrospun core-shell fibers.

Quercetin Improves Glucose and Lipid Metabolism of Diabetic Rats: Involvement of Akt Signaling and SIRT1.

Glucose and lipid metabolism disorder in diabetes mellitus often causes damage to multiple tissues and organs. Diabetes mellitus is beneficially affected by quercetin. However, its concrete mechanisms are yet to be fully elucidated. In our study, diabetes was induced in Sprague-Dawley rats by STZ injection. The rats were randomly divided into normal control, diabetic model, low-dose quercetin treatment, high-dose quercetin treatment, and pioglitazone treatment groups. Fasting blood glucose was collected to evaluate diabetes. Immunohistochemistry and fluorometric assay were performed to explore SIRT1. Akt levels were measured through immunoprecipitation and Western blot. After 12 weeks of quercetin treatment, the biochemical parameters of glucose and lipid metabolism improved to varying degrees. Hepatic histomorphological injury was alleviated, and hepatic glycogen content was increased. The expression and activity of hepatic SIRT1 were enhanced, and Akt was activated by phosphorylation and deacetylation. These results suggested that the beneficial effects of quercetin on glucose and lipid metabolism disorder are probably associated with the upregulated activity and protein level of SIRT1 and its influence on Akt signaling pathway. Hence, quercetin shows potential for the treatment of glucose and lipid metabolism disorder in diabetes mellitus.

Optimization of High Temperature and Pressurized Steam Modified Wood Fibers for High-Density Polyethylene Matrix Composites Using the Orthogonal Design Method.

The orthogonal design method was used to determine the optimum conditions for modifying poplar fibers through a high temperature and pressurized steam treatment for the subsequent preparation of wood fiber/high-density polyethylene (HDPE) composites. The extreme difference, variance, and significance analyses were performed to reveal the effect of the modification parameters on the mechanical properties of the prepared composites, and they yielded consistent results. The main findings indicated that the modification temperature most strongly affected the mechanical properties of the prepared composites, followed by the steam pressure. A temperature of 170 °C, a steam pressure of 0.8 MPa, and a processing time of 20 min were determined as the optimum parameters for fiber modification. Compared to the composites prepared from untreated fibers, the tensile, flexural, and impact strength of the composites prepared from modified fibers increased by 20.17%, 18.5%, and 19.3%, respectively. The effect on the properties of the composites was also investigated by scanning electron microscopy and dynamic mechanical analysis. When the temperature, steam pressure, and processing time reached the highest values, the composites exhibited the best mechanical properties, which were also well in agreement with the results of the extreme difference, variance, and significance analyses. Moreover, the crystallinity and thermal stability of the fibers and the storage modulus of the prepared composites improved; however, the hollocellulose content and the pH of the wood fibers decreased.

3D vasculature segmentation using localized hybrid level-set method.

BACKGROUND: Intensity inhomogeneity occurs in many medical images, especially in vessel images. Overcoming the difficulty due to image inhomogeneity is crucial for the segmentation of vessel image. METHODS: This paper proposes a localized hybrid level-set method for the segmentation of 3D vessel image. The proposed method integrates both local region information and boundary information for vessel segmentation, which is essential for the accurate extraction of tiny vessel structures. The local intensity information is firstly embedded into a region-based contour model, and then incorporated into the level-set formulation of the geodesic active contour model. Compared with the preset global threshold based method, the use of automatically calculated local thresholds enables the extraction of the local image information, which is essential for the segmentation of vessel images. RESULTS: Experiments carried out on the segmentation of 3D vessel images demonstrate the strengths of using locally specified dynamic thresholds in our level-set method. Furthermore, both qualitative comparison and quantitative validations have been performed to evaluate the effectiveness of our proposed model. CONCLUSIONS: Experimental results and validations demonstrate that our proposed model can achieve more promising segmentation results than the original hybrid method does.

GPU accelerating technique for rendering implicitly represented vasculatures.

With the flooding datasets of medical Computed Tomography (CT) and Magnetic Resonance Imaging (MRI), implicit modeling techniques are increasingly applied to reconstruct the human organs, especially the vasculature. However, displaying implicitly represented geometric objects arises heavy computational burden. In this study, a Graphics Processing Unit (GPU) accelerating technique was developed for high performance rendering of implicitly represented objects, especially the vasculatures. The experimental results suggested that the rendering performance was greatly enhanced via exploiting the advantages of modern GPUs.

Implicit reconstruction of vasculatures using bivariate piecewise algebraic splines.

Vasculature geometry reconstruction from volumetric medical data is a crucial task in the development of computer guided minimally invasive vascular surgery systems. In this paper, a technique for reconstructing the geometry of vasculatures using bivariate implicit splines is developed. With the proposed technique, an implicit geometry representation of the vascular tree can be accurately constructed based on the voxels extracted directly from the surface of a certain vascular structure in a given volumetric medical dataset. Experimental results show that the geometric representation built using our method can faithfully represent the morphology and topology of vascular structures. In addition, both the qualitative and the quantitative validations have been performed to show that the reconstructed vessel geometry is of high accuracy and smoothness. An virtual angioscopy system has been implemented to indicate one of the strengths of our proposed method.