Investigating the Corrosion Resistance of Different SiC Crystal Types: From Energy Sectors to Advanced Applications.

Silicon carbide, as a third-generation semiconductor material, plays a pivotal role in various advanced technological applications. Its exceptional stability under extreme conditions has garnered a significant amount of attention. These superior characteristics make silicon carbide an ideal candidate material for high-frequency, high-power electronic devices and applications in harsh environments. In particular, corrosion resistance in natural or artificially acidic and alkaline environments limits the practical application of many other materials. In fields such as chemical engineering, energy conversion, and environmental engineering, materials often face severe chemical erosion, necessitating materials with excellent chemical stability as foundational materials, carriers, or reaction media. Silicon carbide exhibits outstanding performance under these conditions, demonstrating significant resistance to corrosive substances such as hydrochloric acid, sulfuric acid, nitric acid, and alkaline substances such as potassium hydroxide and sodium hydroxide. Despite the well-known chemical stability of silicon carbide, the stability conditions of its different types (such as 3C-, 4H-, and 6H-SiC polycrystals) in acidic and alkaline environments, as well as the specific corrosion mechanisms and differences, warrant further investigation. This Review not only delves deeply into the detailed studies related to this topic but also highlights the current applications of different silicon carbide polycrystals in chemical reaction systems, energy conversion equipment, and recycling processes. Through a comprehensive analysis, this Review aims to bridge research gaps, offering a comparative analysis of the advantages and disadvantages between different polymorphs. It provides material scientists, engineers, and developers with a thorough understanding of silicon carbide's behavior in various chemical environments. This work will propel the research and development of silicon carbide materials under extreme conditions, especially in areas where chemical stability is crucial for device performance and durability. It lays a solid foundation for ultra-high-power, high-integration, high-reliability module architectures, supercomputing chips, and highly safe long-life batteries.

Expression, purification, and crystal structure of mpox virus A41 protein.

Mpox is a zoonotic disease that was once endemic in Africa countries caused by mpox virus. However, cases recently have been confirmed in many non-endemic countries outside of Africa. The rapidly increasing number of confirmed mpox cases poses a threat to the international community. In-depth studies of key viral factors are urgently needed, which will inform the design of multiple antiviral agents. Mpox virus A41L gene encodes a secreted protein, A41, that is nonessential for viral replication, but could affect the host response to infection via interacting with chemokines. Here, mpox virus A41 protein was expressed in Sf9 cells, and purified by affinity chromatography followed by gel filtration. Surface plasmon resonance spectroscopy showed that purified A41 binds a certain human chemokine CXCL8 with the equilibrium dissociation constant (KD) being 1.22 × 10-6 M. The crystal structure of mpox virus A41 protein was solved at 1.92 Å. Structural analysis and comparison revealed that mpox virus A41 protein adopts a characteristic ß-sheet topology, showing minor differences with that of vaccinia virus. These preliminary structural and functional studies of A41 protein from mpox virus will help us better understand its role in chemokine subversion, and contributing to the knowledge to viral chemokine binding proteins.

Rational targeting of autophagy in colorectal cancer therapy: From molecular interactions to pharmacological compounds.

The abnormal progression of tumors has been a problem for treatment of cancer and therapeutic should be directed towards targeting main mechanisms involved in tumorigenesis in tumors. The genomic mutations can result in changes in biological mechanisms in human cancers. Colorectal cancer is one of the most malignant tumors of gastrointestinal tract and its treatment has been faced some difficulties due to development of resistance in tumor cells and also, their malignant behavior. Hence, new therapeutic modalities for colorectal cancer are being investigated. Autophagy is a "self-digestion" mechanism that is responsible for homeostasis preserving in cells and its aberrant activation/inhibition can lead to tumorigenesis. The current review focuses on the role of autophagy mechanism in colorectal cancer. Autophagy may be associated with increase/decrease in progression of colorectal cancer due to mutual function of this molecular mechanism. Pro-survival autophagy inhibits apoptosis to increase proliferation and survival rate of colorectal tumor cells and it is also involved in cancer metastasis maybe due to EMT induction. In contrast, pro-death autophagy decreases growth and invasion of colorectal tumor cells. The status of autophagy (upregulation and down-regulation) is a determining factor for therapy response in colorectal tumor cells. Therefore, targeting autophagy can increase sensitivity of colorectal tumor cells to chemotherapy and radiotherapy. Interestingly, nanoparticles can be employed for targeting autophagy in cancer therapy and they can both induce/suppress autophagy in tumor cells. Furthermore, autophagy modulators can be embedded in nanostructures in improving tumor suppression and providing cancer immunotherapy.

Comparative Efficacy and Acceptability of 12 Phosphorus-Lowering Drugs in Adults with Hyperphosphatemia and Chronic Kidney Disease: A Systematic Review and Network Meta-Analysis.

BACKGROUND: Hyperphosphatemia is associated with cardiovascular morbidity and mortality in adults with chronic kidney disease (CKD). Drug therapy has an irreplaceable role in the management of hyperphosphatemia. OBJECTIVES: We aimed to compare and rank phosphorus-lowering drugs, including phosphate binder and nonphosphate binder, in hyperphosphatemia adults with CKD. METHODS: We did a systematic review and frequentist random-effect network meta-analysis. We searched in PubMed, Cochrane Library, Web of Science, and Embase from inception to February 1, 2023, for randomized controlled trials of 12 phosphorus-lowering drugs in adults with hyperphosphatemia and CKD. Primary outcomes were efficacy (changes in serum phosphorus) and acceptability (treatment withdrawals due to any cause). We ranked each drug according to the value of surface under the cumulative ranking curve. We applied the Confidence in Network Meta-Analysis frameworks to rate the certainty of evidence. This study was registered with PROSPERO, number CRD42022322270. RESULTS: We identified 2,174 citations, and of these, we included 94 trials comprising 14,459 participants and comparing 13 drugs or placebo. In terms of efficacy, except for niacinamide, all drugs lowered the level of serum phosphorus compared with placebo, with mean difference ranging between -1.61 (95% credible interval [CrI], -2.60 to -0.62) mg/dL for magnesium carbonate and -0.85 (-1.66 to -0.05) mg/dL for bixalomer. Only ferric citrate with odds ratios 0.56 (95% CrI: 0.36-0.89) was significantly associated with fewer dropouts for acceptability. Of the 94 trials, 43 (46%), 7 (7%), and 44 (47%) trials were rated as high, moderate, and low risk of bias, respectively, the certainty of the evidence was moderate to very low. CONCLUSIONS: Magnesium carbonate has the best phosphorus-lowering effect in hyperphosphatemia adults with CKD; considering efficacy and acceptability, ferric citrate shows evidence to be the most appropriate drug with or without dialysis.

Hounsfield units on abdominal computed tomography: a new tool for predicting osteoporosis.

BACKGROUND: Osteoporosis can cause bone fractures and disability, but early diagnosis faces challenges. Our proposed diagnostic indicators offer a new approach for early detection, which benefits early identification. PURPOSE: To determine the most appropriate threshold for predicting osteoporosis in patients with each section of vertebral body. MATERIAL AND METHODS: A retrospective analysis of 210 patients, including 646 vertebrae, who had both abdominal computed tomography (CT) and dual-energy X-ray absorptiometry (DXA) within six months. The correlation between DXA T-score and CT Hounsfield units (HU) values was tested by Pearson. The area under the curve (AUC) was calculated using the threshold obtained from the regression equation. RESULTS: The thresholds matching the T-score of -2.5 were 85, 95, 85, and 90 HU for the upper axial plane of the vertebral body (Lau), the middle axial plane of the vertebral body (Lam), the lower axial plane of the vertebral body (Lad), and the mid-sagittal plane of the vertebral body (Lsm), respectively. Defining osteoporosis using CT as Lau ≤ 85, Lam ≤ 95, Lad ≤ 85, or Lsm ≤ 90 HU had a specificity of 88.1% (116/134) and sensitivity of 90.8% (69/76) for distinguishing DXA osteoporosis of the lumbar spine in 210 patients. T-score ≤-2.5 defined as Lau ≤85 or Lam ≤95 or Lad ≤85 or Lsm ≤90 HU had a specificity of 85.9% (275/320) and sensitivity of 82.8% (270/326) for DXA T-score ≤-2.5 in 646 lumbar vertebrae. CONCLUSION: CT HU values obtained based on different sections of the vertebral body in abdominal CT can be used as a supplementary measure to assess osteoporosis.

Routine chest CT combined with the osteoporosis self-assessment tool for Asians (OSTA): a screening tool for patients with osteoporosis.

INTRODUCTION: The osteoporosis self-assessment tool for Asians (OSTA) is a common screening tool for osteoporosis. The seventh thoracic CT (CT-T7) Hounsfield unit (HU) measured by chest CT correlates with osteoporosis. This study aimed to investigate the diagnostic value of OSTA alone, CT-T7 alone, or the combination of OSTA and CT-T7 in osteoporosis. MATERIALS AND METHODS: In this study, 1268 participants were grouped into 586 men and 682 women. We established multiple linear regression models by combining CT-T7 and OSTA. Receiver operating characteristic (ROC) curves were used to evaluate the ability to diagnose osteoporosis. RESULTS: In the male group, the mean age was 59.02 years, and 108 patients (18.4%) had osteoporosis. In the female group, the mean age was 63.23 years, and 308 patients (45.2%) had osteoporosis. By ROC curve comparison, the CT-T7 (male, AUC = 0.789, 95% CI 0.745-0.832; female, AUC = 0.835, 95% CI 0.805-0.864) in the diagnosis of osteoporosis was greater than the OSTA (male, AUC = 0.673, 95% CI 0.620-0.726; female, AUC = 0.775, 95% CI 0.741-0.810) in both the male and female groups (p < 0.001). When OSTA was combined with CT, the equation of multiple linear regression (MLR) was obtained as follows: female = 3.020-0.028*OSTA-0.004*CT-T7. In the female group, it was found that the AUC of MLR (AUC = 0.853, 95% CI 0.825-0.880) in the diagnosis of osteoporosis was larger than that of CT-T7 (p < 0.01). When the MLR was 2.65, the sensitivity and specificity were 53.9% and 90%, respectively. CONCLUSION: For a patient who has completed chest CT, CT-T7 (HU) combined with OSTA is recommended to identify the high-risk population of osteoporosis, and it has a higher diagnostic value than OSTA alone or CT-T7 alone, especially among females. For a female with MLR greater than 2.65, further DXA examination is needed.

The role of programmed cell death in diabetic foot ulcers.

Diabetic foot ulcer, is a chronic complication afflicting individuals with diabetes, continue to increase worldwide, immensely burdening society. Programmed cell death, which includes apoptosis, autophagy, ferroptosis, necroptosis and pyroptosis, has been increasingly implicated in the pathogenesis of diabetic foot ulcer. This review is based on an exhaustive examination of the literature on 'programmed cell death' and 'diabetic foot ulcers' via PubMed. The findings revealed that natural bioactive compounds, noncoding RNAs and certain proteins play crucial roles in the healing of diabetic foot ulcers through various forms of programmed cell death, including apoptosis, autophagy, ferroptosis and pyroptosis.

Particulate toxicity of metal-organic framework UiO-66 to white rot fungus Phanerochaete chrysosporium.

Metal-organic frameworks (MOF) are emerging materials with fantastic properties and wide applications. The release of metal ions from MOF materials is usually regarded as the origin of soluble MOF toxicity. However, whether the stable MOF particulates would induce environmental hazards is not clear. Herein, we aimed to reveal the particulate toxicity of MOF materials using the insoluble UiO-66 as the representative MOF and Phanerochaete chrysosporium as the model microorganism. UiO-66 nanoparticles (NPs) were synthesized by solvothermal method and their diameter was 68.4 ± 8.5 nm. UiO-66 NPs were stable in the culture system and the dissolution rate of 500 mg/L group was 0.26% after 14 d incubation. UiO-66 NPs did not affect the fungus growth according to the fresh weight increases and unchanged dry weights. Fungus mycelia kept even at concentrations up to 500 mg/L. Ultrastructural observation showed that UiO-66 NPs did not enter the fungal cells, but slightly destroyed the cell wall. UiO-66 NPs inhibited the laccase activity and promoted the activity of manganese peroxidase. The overall impact on the decomposition activity of P. chrysosporium was low in dye coloration test and sawdust degradation assay. Meaningful oxidative stress was aroused by UiO-66 NPs, as indicated by the decreases of catalase, glutathione, and total superoxide dismutase, and the increases of H2O2. Our results collectively suggested that the MOF particulates could induce mild mechanical damage to fungi and the toxicity was low comparing to other instable MOF materials.

What Is the Optimal Timing for Reading the Leukocyte Esterase Strip for the Diagnosis of Periprosthetic Joint Infection?

BACKGROUND: The leucocyte esterase (LE) strip test often is used to diagnose periprosthetic joint infection (PJI). In accordance with the manufacturer's directions, the LE strip test result is read 3 minutes after exposing it to joint fluid, but this has not been supported by robust research. Moreover, we have noted that the results of the LE strip test might change over time, and our previous studies have found that centrifugation causes the results of the LE strip test to degrade. Still, there is no evidence-based recommendation as to when to read the LE strip test to maximize diagnostic accuracy, in general, and the best reading times for the LE strip test before and after centrifugation need to be determined separately, in particular. QUESTIONS/PURPOSES: (1) What is the optimal timing for reading LE strip test results before centrifugation to diagnose PJI? (2) What is the optimal timing for reading LE strip test results after centrifugation to diagnose PJI? METHODS: This study was a prospective diagnostic trial. In all, 120 patients who were scheduled for revision arthroplasty and had signs of infection underwent joint aspiration in the outpatient operating room between July 2018 and July 2019 and were enrolled in this single-center study. For inclusion, patients must have had a diagnosis of PJI or nonPJI, valid synovial fluid samples, and must not have received antibiotics within 2 weeks before arthrocentesis. As such, 36 patients were excluded; 84 patients were included for analysis, and all 84 patients agreed to participate. The 2018 International Consensus Meeting Criteria (ICM 2018) was used for the classification of 49 patients with PJI (score ≥ 6) and 35 without PJI (score ≤ 2). The classification was used as the standard against which the different timings for reading LE strips were compared. All patients without PJI were followed for more than 1 year, during which they did not report the occurrence of PJI. All patients were graded against the diagnostic criteria regardless of their LE strip test results. In 83 patients, one drop of synovial fluid (50 µL) was applied to LE strips before and after centrifugation, and in one patient (without PJI), the sample was not centrifuged because the sample volume was less than 1.5 mL. The results of the strip test were read on an automated colorimeter. Starting from 1 minute after centrifugation, these strips were automatically read once every minute, 15 times (over a period of 16 minutes), and the results were independently recorded by two observers. Results were rated as negative, ±, 1+, and 2+ upon the machine reading. Grade 2+ (dark purple) was used as the threshold for a positive result. An investigator who was blinded to the study performed the statistics. Optimal timing for reading the LE strip before and after centrifugation was determined by using receiver operative characteristic (ROC) analysis. The specificity, sensitivity, and positive predictive and negative predictive values were calculated for key timepoints. RESULTS: Before centrifugation, the area under the curve was the highest when the results were read at 5 minutes (0.90 [95% CI 0.83 to 0.98]; sensitivity 0.88 [95% CI 0.75 to 0.95]; specificity 0.89 [95% CI 0.72 to 0.96]). After centrifugation, the area under the curve was the highest when the results were read at 10 minutes (0.92 [95% CI 0.86 to 0.98]; sensitivity 0.65 [95% CI 0.50 to 0.78]; specificity 0.97 [95% CI 0.83 to 1.00]). CONCLUSION: The LE strip test results are affected by time and centrifugation. For samples without centrifugation, we found that 5 minutes after application was the best time to read LE strips. We cannot deny the use of centrifuges because this is an effective way to solve the sample-mingling problem at present. We recommend 10 minutes postapplication as the most appropriate time to read LE strips after centrifugation. Multicenter and large-sample size studies are warranted to further verify our conclusion. LEVEL OF EVIDENCE: Level II, diagnostic study.

Management of intraoperative acetabular fracture in primary total hip arthroplasty.

BACKGROUND: Intraoperative acetabular fracture(IAF) is a rare complication of primary total hip arthroplasty(THA). The previous reports have lacked a sufficiently large number of subjects to allow for an analysis of the causes and appropriate treatment of this problem. METHODS: Between 2015 to 2018, 4888 primary THA were enrolled. We retrospectively reviewed the records in our Total Joint Registry Database and found that 24 patients (24 hips) had sustained intraoperative acetabular fractures. Twenty-four patients(16 females and 8males)were all treated with a posterolateral approach using uncemented components. Twenty patients(83.3%)underwent supplemental screw fixation, of which 2 patients were treated with steel plate fixation. Two patients' femoral heads were used as a graft. In 4 patients(16.7%), the acetabular components were judged to be stable despite the fracture and no additional treatment was performed. All patients were evaluated clinically with Harris Hip Scores (HHS) and radiographically with serial X-rays which follow up for a mean period of 34.0 ± 12.6 months. We evaluated the anatomic locations, causes, treatments, and outcome of the fractures to study the treatment method and effect of intraoperative acetabular fracture during operation. RESULTS: The fracture rate associated with uncemented components was 0.49%. In 17(70.8%) of these patients, the fracture was noted during the impaction of the real acetabular component. Six patients(25%)with Ankylosing Spondylitis had fractures, 4 in the anterior wall, and 1 in the anterior column, because the patient with hip joint fusion needs a to pre-osteotomy before the dislocation. The HHS score increased from 30.8 ± 9.7 preoperatively to 90.2 ± 4.2 postoperatively. All the latest x-ray showed that the fracture did not move, and there is no translucent line formed in the acetabular cup bone interface. CONCLUSION: Intraoperative acetabular fractures are rare complications of THA, and most commonly occur during the implantation of the acetabular components. It is necessary to prevent the occurrence of fractures as much as possible even if the fractures are found during the operation. It should be noted that patients with ankylosing spondylitis involving hip joints during THA surgery must be careful to prevent IAFs during dislocation and pre-osteotomy.

Enhanced electrochemical phosphate recovery from livestock wastewater by adjusting pH with plant ash.

In the field of environmental wastewater treatment, it is a very meaningful topic to recover phosphate from swine wastewater in the form of struvite precipitation. The solution pH is one of the important influencing factors in the process of struvite precipitation. In this paper, an attempt was made to recover the phosphate from swine wastewater by adding plant ash. Experimental results have revealed that aeration can be replaced by optimal plant ash adding mode to increase the phosphate recovery efficiency. With the dosages of plant ash and magnesium metal were respectively 11.66 and 3.33 g/L the phosphate recovery efficiency reached 97.69% in 60 min. The efficiency was still above 95% after repeatedly using magnesium pellet for 3 times. The economic evaluation further revealed that the recovery cost of the proposed method was 0.62 $/kg PO4-P.

Evolution and expression patterns of the trehalose-6-phosphate synthase gene family in drumstick tree (Moringa oleifera Lam.).

MAIN CONCLUSION: Moringa oleifera TPSs were genome-wide identified for the first time, and a phylogenetic analysis was performed to investigate evolutionary divergence. The qRT-PCR data show that MoTPS genes response to different stress treatments. The trehalose-6-phosphate synthase (TPS) family is involved in a wide range of stress-resistance processes in plants. Its direct product, trehalose-6-phosphate, acts as a specific signal of sucrose status and a regulator to modulate carbon metabolism within the plant. In this study, eight TPS genes were identified and cloned based on the M. oleifera genome; only MoTPS1 exhibited TPS activity among Group I proteins. The characteristics of the MoTPS gene family were determined by analyzing phylogenetic relationships, gene structures, conserved motifs, selective forces, and expression patterns. The Group II MoTPS genes were under relaxed purifying selection or positive selection. The glycosyltransferase family 20 domains generally had lower Ka/Ks ratios and nonsynonymous (Ka) changes compared with those of trehalose-phosphatase domains, which is consistent with stronger purifying selection due to functional constraints in performing TPS enzyme activity. Phylogenetic analyses of TPS proteins from M. oleifera and 17 other plant species indicated that TPS were present before the monocot-dicot split, whereas Group II TPSs were duplicated after the separation of dicots and monocots. Quantitative real-time PCR analysis showed that the expression patterns of TPSs displayed group specificities in M. oleifera. Particularly, Group I MoTPS genes closely relate to reproductive development and Group II MoTPS genes closely relate to high temperature resistance in leaves, stem, stem tip and roots. This work provides a scientific classification of plant TPSs, dissects the internal relationships between their evolution and expressions, and promotes functional researches.

A simple method for RNA isolation from various tissues of the tree Neolamarckia cadamba.

Plant tissues contain abundant polysaccharides, phenolic compounds and other metabolites, which makes it difficult to isolate high-quality RNA from them. In addition, Neolamarckia cadamba contains large quantities of other components, particularly RNA-binding alkaloids, which makes the isolation even more challenging. Here, we describe a concise and efficient RNA isolation method that combines the cetyltrimethyl ammonium bromide (CTAB) and Plant RNA Kit (Omega) protocols. Gel electrophoresis showed that RNA extracted from all tissues, using this protocol, was of good integrity and without DNA contamination. Furthermore, the isolated RNA was of high purity, with an A260/A280 ratio of 2.1 and an A260/A230 ratio of >2.0. The isolated RNA was also suitable for downstream applications, such as reverse transcription-polymerase chain reaction (RT-PCR) and quantitative RT-PCR (RT-qPCR). The RNA isolation method was also efficient for recalcitrant plant tissues.

Cost-Sensitive Weighted Contrastive Learning Based on Graph Convolutional Networks for Imbalanced Alzheimer's Disease Staging.

Identifying the progression stages of Alzheimer's disease (AD) can be considered as an imbalanced multi-class classification problem in machine learning. It is challenging due to the class imbalance issue and the heterogeneity of the disease. Recently, graph convolutional networks (GCNs) have been successfully applied in AD classification. However, these works did not handle the class imbalance issue in classification. Besides, they ignore the heterogeneity of the disease. To this end, we propose a novel cost-sensitive weighted contrastive learning method based on graph convolutional networks (CSWCL-GCNs) for imbalanced AD staging using resting-state functional magnetic resonance imaging (rs-fMRI). The proposed method is developed on a multi-view graph constructed using the functional connectivity (FC) and high-order functional connectivity (HOFC) features of the subjects. A novel cost-sensitive weighted contrastive learning procedure is proposed to capture discriminative information from the minority classes, encouraging the samples in the minority class to provide adequate supervision. Considering the heterogeneity of the disease, the weights of the negative pairs are introduced into contrastive learning and they are computed based on the distance to class prototypes, which are automatically learned from the training data. Meanwhile, the cost-sensitive mechanism is further introduced into contrastive learning to handle the class imbalance issue. The proposed CSWCL-GCN is evaluated on 720 subjects (including 184 NCs, 40 SMC patients, 208 EMCI patients, 172 LMCI patients and 116 AD patients) from the ADNI (Alzheimer's Disease Neuroimaging Initiative). Experimental results show that the proposed CSWCL-GCN outperforms state-of-the-art methods on the ADNI database.

EWT: Efficient Wavelet-Transformer for single image denoising.

Transformer-based image denoising methods have shown remarkable potential but suffer from high computational cost and large memory footprint due to their linear operations for capturing long-range dependencies. In this work, we aim to develop a more resource-efficient Transformer-based image denoising method that maintains high performance. To this end, we propose an Efficient Wavelet Transformer (EWT), which incorporates a Frequency-domain Conversion Pipeline (FCP) to reduce image resolution without losing critical features, and a Multi-level Feature Aggregation Module (MFAM) with a Dual-stream Feature Extraction Block (DFEB) to harness hierarchical features effectively. EWT achieves a faster processing speed by over 80% and reduces GPU memory usage by more than 60% compared to the original Transformer, while still delivering denoising performance on par with state-of-the-art methods. Extensive experiments show that EWT significantly improves the efficiency of Transformer-based image denoising, providing a more balanced approach between performance and resource consumption.

Multimodal Co-attention Fusion Network with Online Data Augmentation for Cancer Subtype Classification.

It is an essential task to accurately diagnose cancer subtypes in computational pathology for personalized cancer treatment. Recent studies have indicated that the combination of multimodal data, such as whole slide images (WSIs) and multi-omics data, could achieve more accurate diagnosis. However, robust cancer diagnosis remains challenging due to the heterogeneity among multimodal data, as well as the performance degradation caused by insufficient multimodal patient data. In this work, we propose a novel multimodal co-attention fusion network (MCFN) with online data augmentation (ODA) for cancer subtype classification. Specifically, a multimodal mutual-guided co-attention (MMC) module is proposed to effectively perform dense multimodal interactions. It enables multimodal data to mutually guide and calibrate each other during the integration process to alleviate inter- and intra-modal heterogeneities. Subsequently, a self-normalizing network (SNN)-Mixer is developed to allow information communication among different omics data and alleviate the high-dimensional small-sample size problem in multi-omics data. Most importantly, to compensate for insufficient multimodal samples for model training, we propose an ODA module in MCFN. The ODA module leverages the multimodal knowledge to guide the data augmentations of WSIs and maximize the data diversity during model training. Extensive experiments are conducted on the public TCGA dataset. The experimental results demonstrate that the proposed MCFN outperforms all the compared algorithms, suggesting its effectiveness.

Involution Transformer based U-Net for Landmark Detection in Ultrasound Images for Diagnosis of Infantile DDH.

The B-mode ultrasound based computer-aided diagnosis (CAD) has demonstrated its effectiveness for diagnosis of Developmental Dysplasia of the Hip (DDH) in infants, which can conduct the Graf's method by detecting landmarks in hip ultrasound images. However, it is still necessary to explore more valuable information around these landmarks to enhance feature representation for improving detection performance in the detection model. To this end, a novel Involution Transformer based U-Net (IT-UNet) network is proposed for hip landmark detection. The IT-UNet integrates the efficient involution operation into Transformer to develop an Involution Transformer module (ITM), which consists of an involution attention block and a squeeze-and-excitation involution block. The ITM can capture both the spatial-related information and long-range dependencies from hip ultrasound images to effectively improve feature representation. Moreover, an Involution Downsampling block (IDB) is developed to alleviate the issue of feature loss in the encoder modules, which combines involution and convolution for the purpose of downsampling. The experimental results on two DDH ultrasound datasets indicate that the proposed IT-UNet achieves the best landmark detection performance, indicating its potential applications.

A fine-grained orthodontics segmentation model for 3D intraoral scan data.

With the widespread application of digital orthodontics in the diagnosis and treatment of oral diseases, more and more researchers focus on the accurate segmentation of teeth from intraoral scan data. The accuracy of the segmentation results will directly affect the follow-up diagnosis of dentists. Although the current research on tooth segmentation has achieved promising results, the 3D intraoral scan datasets they use are almost all indirect scans of plaster models, and only contain limited samples of abnormal teeth, so it is difficult to apply them to clinical scenarios under orthodontic treatment. The current issue is the lack of a unified and standardized dataset for analyzing and validating the effectiveness of tooth segmentation. In this work, we focus on deformed teeth segmentation and provide a fine-grained tooth segmentation dataset (3D-IOSSeg). The dataset consists of 3D intraoral scan data from more than 200 patients, with each sample labeled with a fine-grained mesh unit. Meanwhile, 3D-IOSSeg meticulously classified every tooth in the upper and lower jaws. In addition, we propose a fast graph convolutional network for 3D tooth segmentation named Fast-TGCN. In the model, the relationship between adjacent mesh cells is directly established by the naive adjacency matrix to better extract the local geometric features of the tooth. Extensive experiments show that Fast-TGCN can quickly and accurately segment teeth from the mouth with complex structures and outperforms other methods in various evaluation metrics. Moreover, we present the results of multiple classical tooth segmentation methods on this dataset, providing a comprehensive analysis of the field. All code and data will be available at https://github.com/MIVRC/Fast-TGCN.

Pseudo-Data Based Self-Supervised Federated Learning for Classification of Histopathological Images.

Computer-aided diagnosis (CAD) can help pathologists improve diagnostic accuracy together with consistency and repeatability for cancers. However, the CAD models trained with the histopathological images only from a single center (hospital) generally suffer from the generalization problem due to the straining inconsistencies among different centers. In this work, we propose a pseudo-data based self-supervised federated learning (FL) framework, named SSL-FT-BT, to improve both the diagnostic accuracy and generalization of CAD models. Specifically, the pseudo histopathological images are generated from each center, which contain both inherent and specific properties corresponding to the real images in this center, but do not include the privacy information. These pseudo images are then shared in the central server for self-supervised learning (SSL) to pre-train the backbone of global mode. A multi-task SSL is then designed to effectively learn both the center-specific information and common inherent representation according to the data characteristics. Moreover, a novel Barlow Twins based FL (FL-BT) algorithm is proposed to improve the local training for the CAD models in each center by conducting model contrastive learning, which benefits the optimization of the global model in the FL procedure. The experimental results on four public histopathological image datasets indicate the effectiveness of the proposed SSL-FL-BT on both diagnostic accuracy and generalization.

Weakly Supervised Lesion Detection and Diagnosis for Breast Cancers With Partially Annotated Ultrasound Images.

Deep learning (DL) has proven highly effective for ultrasound-based computer-aided diagnosis (CAD) of breast cancers. In an automatic CAD system, lesion detection is critical for the following diagnosis. However, existing DL-based methods generally require voluminous manually-annotated region of interest (ROI) labels and class labels to train both the lesion detection and diagnosis models. In clinical practice, the ROI labels, i.e. ground truths, may not always be optimal for the classification task due to individual experience of sonologists, resulting in the issue of coarse annotation to limit the diagnosis performance of a CAD model. To address this issue, a novel Two-Stage Detection and Diagnosis Network (TSDDNet) is proposed based on weakly supervised learning to improve diagnostic accuracy of the ultrasound-based CAD for breast cancers. In particular, all the initial ROI-level labels are considered as coarse annotations before model training. In the first training stage, a candidate selection mechanism is then designed to refine manual ROIs in the fully annotated images and generate accurate pseudo-ROIs for the partially annotated images under the guidance of class labels. The training set is updated with more accurate ROI labels for the second training stage. A fusion network is developed to integrate detection network and classification network into a unified end-to-end framework as the final CAD model in the second training stage. A self-distillation strategy is designed on this model for joint optimization to further improves its diagnosis performance. The proposed TSDDNet is evaluated on three B-mode ultrasound datasets, and the experimental results indicate that it achieves the best performance on both lesion detection and diagnosis tasks, suggesting promising application potential.