RDAG U-Net: An Advanced AI Model for Efficient and Accurate CT Scan Analysis of SARS-CoV-2 Pneumonia Lesions.

Background/Objective: This study aims to utilize advanced artificial intelligence (AI) image recog-nition technologies to establish a robust system for identifying features in lung computed tomog-raphy (CT) scans, thereby detecting respiratory infections such as SARS-CoV-2 pneumonia. Spe-cifically, the research focuses on developing a new model called Residual-Dense-Attention Gates U-Net (RDAG U-Net) to improve accuracy and efficiency in identification. Methods: This study employed Attention U-Net, Attention Res U-Net, and the newly developed RDAG U-Net model. RDAG U-Net extends the U-Net architecture by incorporating ResBlock and DenseBlock modules in the encoder to retain training parameters and reduce computation time. The training dataset in-cludes 3,520 CT scans from an open database, augmented to 10,560 samples through data en-hancement techniques. The research also focused on optimizing convolutional architectures, image preprocessing, interpolation methods, data management, and extensive fine-tuning of training parameters and neural network modules. Result: The RDAG U-Net model achieved an outstanding accuracy of 93.29% in identifying pulmonary lesions, with a 45% reduction in computation time compared to other models. The study demonstrated that RDAG U-Net performed stably during training and exhibited good generalization capability by evaluating loss values, model-predicted lesion annotations, and validation-epoch curves. Furthermore, using ITK-Snap to convert 2D pre-dictions into 3D lung and lesion segmentation models, the results delineated lesion contours, en-hancing interpretability. Conclusion: The RDAG U-Net model showed significant improvements in accuracy and efficiency in the analysis of CT images for SARS-CoV-2 pneumonia, achieving a 93.29% recognition accuracy and reducing computation time by 45% compared to other models. These results indicate the potential of the RDAG U-Net model in clinical applications, as it can accelerate the detection of pulmonary lesions and effectively enhance diagnostic accuracy. Additionally, the 2D and 3D visualization results allow physicians to understand lesions' morphology and distribution better, strengthening decision support capabilities and providing valuable medical diagnosis and treatment planning tools.

Investigation of Degradation and Biocompatibility of Indirect 3D-Printed Bile Duct Stents.

This study proposes a bile duct stent based on indirect 3D printing technology. Four ratio materials were synthesized from lactic acid (LA) and glycolide (GA) monomers by melt polymerization: PLA, PLGA (70:30), PLGA (50:50), and PLGA (30:70). The four kinds of material powders were preliminarily degraded, and the appearance was observed with an optical microscope (OM) and a camera. The weight and appearance of the four materials changed significantly after four weeks of degradation, which met the conditions for materials to be degraded within 4-6 weeks. Among them, PLGA (50:50) lost the most-the weight dropped to 13.4%. A stent with an outer diameter of 10 mm and an inner diameter of 8 mm was successfully manufactured by indirect 3D printing technology, demonstrating the potential of our research. Then, the degradation experiment was carried out on a cylindrical stent with a diameter of 6 mm and a height of 3 mm. The weight loss of the sample was less than that of the powder degradation, and the weight loss of PLGA (50:50) was the largest-the weight dropped to 79.6%. The nano-indenter system measured the mechanical properties of materials. Finally, human liver cancer cells Hep-3B were used to conduct in vitro cytotoxicity tests on the scaffolds to test the biocompatibility of the materials. A bile duct stent meeting commercial size requirements has been developed, instilling confidence in the potential of our research for future medical applications.

Design, Manufacture, and Characterization of a Critical-Sized Gradient Porosity Dual-Material Tibial Defect Scaffold.

This study proposed a composite tibia defect scaffold with radial gradient porosity, utilizing finite element analysis to assess stress in the tibial region with significant critical-sized defects. Simulations for scaffolds with different porosities were conducted, designing an optimal tibia defect scaffold with radial gradient porosity for repairing and replacing critical bone defects. Radial gradient porosity scaffolds resulted in a more uniform stress distribution, reducing titanium alloy stiffness and alleviating stress shielding effects. The scaffold was manufactured using selective laser melting (SLM) technology with stress relief annealing to simplify porous structure fabrication. The study used New Zealand white rabbits' tibia defect sites as simulation parameters, reconstructing the 3D model and implanting the composite scaffold. Finite element analysis in ANSYS-Workbench simulated forces under high-activity conditions, analyzing stress distribution and strain. In the simulation, the titanium alloy scaffold bore a maximum stress of 122.8626 MPa, while the centrally encapsulated HAp material delivered 27.92 MPa. The design demonstrated superior structural strength, thereby reducing stress concentration. The scaffold was manufactured using SLM, and the uniform design method was used to determine a collection of optimum annealing parameters. Nanoindentation and compression tests were used to determine the influence of annealing on the elastic modulus, hardness, and strain energy of the scaffold.

Improving Respiratory Infection Diagnosis with Deep Learning and Combinatorial Fusion: A Two-Stage Approach Using Chest X-ray Imaging.

The challenges of respiratory infections persist as a global health crisis, placing substantial stress on healthcare infrastructures and necessitating ongoing investigation into efficacious treatment modalities. The persistent challenge of respiratory infections, including COVID-19, underscores the critical need for enhanced diagnostic methodologies to support early treatment interventions. This study introduces an innovative two-stage data analytics framework that leverages deep learning algorithms through a strategic combinatorial fusion technique, aimed at refining the accuracy of early-stage diagnosis of such infections. Utilizing a comprehensive dataset compiled from publicly available lung X-ray images, the research employs advanced pre-trained deep learning models to navigate the complexities of disease classification, addressing inherent data imbalances through methodical validation processes. The core contribution of this work lies in its novel application of combinatorial fusion, integrating select models to significantly elevate diagnostic precision. This approach not only showcases the adaptability and strength of deep learning in navigating the intricacies of medical imaging but also marks a significant step forward in the utilization of artificial intelligence to improve outcomes in healthcare diagnostics. The study's findings illuminate the path toward leveraging technological advancements in enhancing diagnostic accuracies, ultimately contributing to the timely and effective treatment of respiratory diseases.

Development and Fabrication of Biocompatible Ti-Based Bulk Metallic Glass Matrix Composites for Additive Manufacturing.

Ti-based metallic glasses have a high potential for implant applications. The feasibility of a new biocompatible Ti-based bulk metallic glass composite for selective laser melting (SLM) had been examined. Therefore, it is necessary to design a high-glass-forming-ability Ti-based metallic glass (∆Tx = 81 K, γ = 0.427, γm = 0.763), to fabricate a partial glass-formable spherical powder (the volume fraction of the amorphous phase in the atomized Ti-based powders being 73% [size < 25 µm], 61% [25-37 µm], and 50% [37-44 µm]), and establish an SLM parameter (a scan rate of 600 mm/s, a power of 120 W, and an overlap of 10%). The Ti42Zr35Si5Co12.5Sn2.5Ta3 bulk metallic glass composite was successfully fabricated through SLM. This study demonstrates that the TiZrSiCoSnTa system constitutes a promising basis for the additive manufacturing process in terms of preparing biocompatible metallic glass composites into complicated graded foam shapes.

Aptamer/doxorubicin-conjugated nanoparticles target membranous CEMIP2 in colorectal cancer.

The objectives were to identify the functional domains of a potential oncoprotein, cell migration inducing hyaluronidase 2 (CEMIP2), evaluate its expression levels and roles in colorectal cancer (CRC), and develop an aptamer-based nanoparticle for targeted therapy. Data mining on TCGA identified that CEMIP2 might play oncogenic roles in CRC. In a local cohort, CEMIP2 mRNA levels significantly stepwise increase in CRC patients with higher stages, and high CEMIP2 confers worse disease-free survival. In addition, CEMIP2 mRNA levels significantly correlated to hyaluronan levels in sera from CRC patients. Deletion mapping identified that CEMIP2 containing G8 and PANDER-like domains preserved hyaluronidase activity and oncogenic roles, including cell proliferation, anchorage-independent cell growth, cell migration and invasion, and human umbilical vein endothelial cell (HUVEC) tube formation in CRC-derived cells. A customized monoclonal mouse anti-human CEMIP2 antibody probing the PANDER-like domain (anti-289307) counteracted CEMIP2-mediated carcinogenesis in vitro. Cell-SELEX pinpointed an aptamer, aptCEMIP2(101), specifically interacted with the full-length CEMIP2, potentially involving its 3D structure. Treatments with aptCEMIP2(101) significantly reduced CEMIP2-mediated tumorigenesis in vitro. Mesoporous silica nanoparticles (MSN) carrying atpCEMIP2(101) and Dox were fabricated. Dox@MSN, MSN-aptCEMIP2(101), and Dox@MSN-aptCEMIP2(101) significantly suppressed tumorigenesis in vitro compared to the Mock, while Dox@MSN-aptCEMIP2(101) showed substantially higher effects compared to Dox@MSN and MSN-aptCEMIP2(101) in CRC-derived cells. Our study identified a novel oncogene and developed an effective aptamer-based targeted therapeutic strategy.

The autocrine glycosylated-GREM1 interacts with TGFB1 to suppress TGFß/BMP/SMAD-mediated EMT partially by inhibiting MYL9 transactivation in urinary carcinoma.

PURPOSE: Urothelial carcinoma (UC) is a common disease in developed counties. This study aimed to identify autocrine roles and signaling pathways of gremlin 1, DAN family BMP antagonist (GREM1), which inhibits tumor growth and epithelial-mesenchymal transition (EMT) in UC. METHODS: Systematic in vitro and in vivo studies using genetic engineering, different urinary bladder urothelial carcinoma (UBUC)-derived cell lines, and mouse models were performed, respectively. Further, primary upper tract urothelial carcinoma (UTUC) and UBUC specimens were evaluated by immunohistochemistry. RESULTS: GREM1 protein levels conferred better disease-specific and metastasis-free survival rates and played an independent prognostic factor in UTUC and UBUC. Hypermethylation is the primary cause of low GREM1 levels. In different UBUC-derived cell lines, the autocrine/secreted and glycosylated GREM1 interacted with transforming growth factor beta 1 (TGFB1) and inhibited TGFß/BMP/SMAD signaling and myosin light chain 9 (MYL9) transactivation, subsequently cell proliferation and epithelial-mesenchymal transition (EMT). Secreted and glycosylated GREM1 also suppressed tumor growth, metastasis, and MYL9 levels in the mouse model. Instead, cytosolic GREM1 promoted cell proliferation and EMT by activating the tumor necrosis factor (TNF)/AKT/nuclear factor kappa B (NFκB) axis. CONCLUSIONS: Clinical associations, animal models, and in vitro indications provided solid evidence to show that the epithelial autocrine GREM1 is a novel tumor suppressor in UCs. The glycosylated-GREM1 hampered cell proliferation, migration, invasion, and in vitro angiogenesis through interaction with TGFB1 to inactivate TGFß/BMP/SMAD-mediated EMT in an autocrine manner.

PVDF/AgNP/MXene composites-based near-field electrospun fiber with enhanced piezoelectric performance for self-powered wearable sensors.

336MXenes, as highly electronegative and conductive two-dimensional nanomaterials, are extensively studied for their use in sensors and flexible electronics. In this study, near-field electrospinning was used to prepare a new poly(vinylidene difluoride) (PVDF)/Ag nanoparticle (AgNP)/MXene composite nanofiber film as a self-powered flexible human motion-sensing device. The composite film displayed highly piezoelectric properties with the presence of MXene. Scanning electron microscopy, X-ray diffraction, and Fourier transform infrared spectroscopy revealed that the intercalated MXene in the composite nanofibers was evenly spread out, which not only prevented the aggregation of MXene but also enabled the composite materials to form self-reduced AgNPs. The prepared PVDF/AgNP/MXene fibers displayed exceptional stability and excellent output performance, enabling their use for energy harvesting and powering light-emitting diodes. The doping of MXene/AgNPs increased the electrical conductivity of the PVDF material, improved its piezoelectric properties, and enhanced the piezoelectric constant of PVDF piezoelectric fibers, thereby allowing the production of flexible, sustainable, wearable, and self-powered electrical devices.

Development of Deep Learning with RDA U-Net Network for Bladder Cancer Segmentation.

In today's high-order health examination, imaging examination accounts for a large proportion. Computed tomography (CT), which can detect the whole body, uses X-rays to penetrate the human body to obtain images. Its presentation is a high-resolution black-and-white image composed of gray scales. It is expected to assist doctors in making judgments through deep learning based on the image recognition technology of artificial intelligence. It used CT images to identify the bladder and lesions and then segmented them in the images. The images can achieve high accuracy without using a developer. In this study, the U-Net neural network, commonly used in the medical field, was used to extend the encoder position in combination with the ResBlock in ResNet and the Dense Block in DenseNet, so that the training could maintain the training parameters while reducing the overall identification operation time. The decoder could be used in combination with Attention Gates to suppress the irrelevant areas of the image while paying attention to significant features. Combined with the above algorithm, we proposed a Residual-Dense Attention (RDA) U-Net model, which was used to identify organs and lesions from CT images of abdominal scans. The accuracy (ACC) of using this model for the bladder and its lesions was 96% and 93%, respectively. The values of Intersection over Union (IoU) were 0.9505 and 0.8024, respectively. Average Hausdorff distance (AVGDIST) was as low as 0.02 and 0.12, respectively, and the overall training time was reduced by up to 44% compared with other convolution neural networks.

Development of Piezoelectric Silk Sensors Doped with Graphene for Biosensing by Near-Field Electrospinning.

A novel piezoelectric fiber sensor based on polyvinylidene fluoride piezoelectric (PVDF) doped with graphene is presented. The near-field electrospinning technology was used for developing the sensor. The uniform experimental design method was introduced to determine the ranges of experimental parameters, including the applied voltage, the drum speed range, the graphene doping ratios from 0% to 11 wt% in PVDF solution, and the electrode gap. By experimental results, the conductivities of PVDF solutions with different doping ratios of graphene increased from 19.6 µS/cm to 115.8 µS/cm. Tapping tests were performed to measure the voltages and currents produced by the piezoelectric fibers. The maximum output voltage was 4.56 V at 5 wt% graphene doping ratio in PVDF fibers, which was 11.54 times that of the pure PVDF sensors. Moreover, mechanical properties of the proposed sensor were measured. Motion intention and swallowing test, such as saliva-swallowing and eating, were carried out. When the subject spoke normally, the output voltage of the sensor was between 0.2 and 0.4 V, approximately. Furthermore, when the subject drank water and ate food, the output voltage of the sensor was between 0.5 and 1 V, approximately. The proposed sensor could be used to detect signals of the human body and serve as a wearable device, allowing for more diagnosis and medical treatment.

Development of Novel Residual-Dense-Attention (RDA) U-Net Network Architecture for Hepatocellular Carcinoma Segmentation.

The research was based on the image recognition technology of artificial intelligence, which is expected to assist physicians in making correct decisions through deep learning. The liver dataset used in this study was derived from the open source website (LiTS) and the data provided by the Kaohsiung Chang Gung Memorial Hospital. CT images were used for organ recognition and lesion segmentation; the proposed Residual-Dense-Attention (RDA) U-Net can achieve high accuracy without the use of contrast. In this study, U-Net neural network was used to combine ResBlock in ResNet with Dense Block in DenseNet in the coder part, allowing the training to maintain the parameters while reducing the overall recognition computation time. The decoder was equipped with Attention Gates to suppress the irrelevant areas of the image while focusing on the significant features. The RDA model was used to identify and segment liver organs and lesions from CT images of the abdominal cavity, and excellent segmentation was achieved for the liver located on the left side, right side, near the heart, and near the lower abdomen with other organs. Better recognition was also achieved for large, small, and single and multiple lesions. The study was able to reduce the overall computation time by about 28% compared to other convolutions, and the accuracy of liver and lesion segmentation reached 96% and 94.8%, with IoU values of 89.5% and 87%, and AVGDIST of 0.28 and 0.80, respectively.

Development of Flexible Biceps Tremors Sensing Chip of PVDF Fibers with Nano-Silver Particles by Near-Field Electrospinning.

Polyvinylidene fluoride (PVDF) and AgNO3/PVDF composite piezoelectric fibers were prepared using near-field electrospinning technology. The prepared fibers are attached to the electrode sheet and encapsulated with polydimethylsiloxane to create an energy acquisition device and further fabricated into a dynamic sensing element. The addition of AgNO3 significantly increased the conductivity of the solution from 40.33 µS/cm to 883.59 µS/cm, which in turn made the fiber drawing condition smoother with the increase of high voltage electric field and reduced the fiber wire diameter size from 0.37 µm to 0.23 µm. The tapping test shows that the voltage signal can reach ~0.9 V at a frequency of 7 Hz, and the energy conversion efficiency is twice that of the PVDF output voltage. The addition of AgNO3 effectively enhances the molecular bonding ability, which effectively increases the piezoelectric constants of PVDF piezoelectric fibers. When the human body is exercised for a long period of time and the body is overloaded, the biceps muscle is found to produce 8 to 16 tremors/second through five arm flexion movements. The voltage output of the flexible dynamic soft sensor is between 0.7-0.9 V and shows an orderly alternating current waveform of voltage signals. The sensor can be used to detect muscle tremors after high-intensity training and to obtain advance information about changes in the symptoms of fasciculation, allowing for more accurate diagnosis and treatment.

Highly sensitive, flexible and biocompatible temperature sensor utilizing ultra-long Au@AgNW-based polymeric nanocomposites.

Owing to their excellent sensitivity, stretchability, flexibility and conductivity, polymeric nanocomposites with conductive fillers have shown promise for a wide range of applications in bioelectronics and wearable devices. Herein, we report on the development of a flexible and biocompatible polymeric nanocomposite comprising ultra-long Ag-Au core-sheath nanowires (Au@AgNWs) dispersed in elastomeric media to fabricate a high-resolution wearable temperature sensor. Ultra-long AgNWs with an aspect ratio of about 1500 were synthesized using a Ca2+ ion-mediated facile one-pot polyol process. To enhance the biocompatibility and anti-oxidative property of the AgNWs, a 10-20 nm gold (Au) layer was conformably deposited without affecting the original nanowire morphology. The core-sheath structure of Au@AgNWs was characterized using HRTEM and EDS elemental mapping while the biocompatibility and anti-oxidative properties were tested using hydrogen peroxide (H2O2) etching in solution phase. Finally, the fabricated nanowires were used to prepare the Au@AgNW-poly-ethylene glycol (PEG)-polyurethane (PU)-based nanocomposite ink which can be printed on interdigitated electrodes to fabricate a thermoresistive temperature sensor with negative temperature coefficient (NTC) of resistance and quick response time (<100 s). The Au@AgNW-PEG-PU nanocomposite was characterized in detail and a novel temperature sensing mechanism based on controlling the internanowire distance of the PEG coated Au@AgNWs percolation by means of capillarity force among the nanowires as a result of the glass transition temperature of thermosensitive PEG was demonstrated. The proposed printable temperature sensor is flexible and biocompatible and shows promise for a range of wearable applications.

Characterization of Piezoelectric Properties of Ag-NPs Doped PVDF Nanocomposite Fibres Membrane Prepared by Near Field Electrospinning.

BACKGROUND: In this study, Near-field electrospinning (NFES) technique is used with a cylindrical collector to fabricate a large area permanent piezoelectric micro and nanofibers by a prepared solution. NFES requires a small electric field to fabricate fibers Objective: The objective of this paper to investigate silver nanoparticle (Ag-NP)/ Polyvinylidene fluoride (PVDF) composite as the best piezoelectric material with improved properties to produced tremendously flexible and sensitive piezoelectric material with pertinent conductance Methods: In this paper, we used controllable electrospinning technique based on Near-field electrospinning (NFES). The process parameter for Ag-NP/PVDF composite electrospun fiber based on pure PVDF fiber. A PVDF solution concentration of 18 wt.% and 6 wt.% silver nitrate, which is relative to the weight of PVDF wt.% with 1058 µS conductivity fibers, have been directly written on a rotating cylindrical collector for aligned fiber PVDF/Ag-NP fibers are patterned on fabricated copper (Cu) interdigitated electrodes were implemented on a thin flexible polyethylene terephthalate (PET) substrate and Polydimethylsiloxane (PDMS) used as a package to enhance the durability of the PVDF/ Ag-NP device. RESULTS: A notable effect on the piezoelectric response has been observed after Ag-NP addition, confirmed by XRD characterization and tapping test of Ag-NP/PVDF composite fiber. The morphology of the PVDF/Ag-NP fibers and measure diameter by scanning electron microscopy (SEM) and Optical micrograph (OM), of fiber. Finally, a diameter of PVDF/Ag-NP fibers up to ~7 µm. The high diffraction peak at 2θ = 20.5˚ was investigated by X-ray diffraction (XRD) in the piezoelectric crystal ß-phase structure. Further addition of silver nanoparticles (Ag- NPs) in the PVDF solution resulted in enhancing the electromechanical conversion of the fibers from ~0.1 V to ~1 V. CONCLUSION: In conclusion, we can say that confirmed and validated the addition of Ag-NP in PVDF could enhance the piezoelectric property by using NFES technique with improved crystalline phase content can be useful for a wide range of power and sensing applications like biomedical devices and energy harvesting, among others.

A New Design of Porosity Gradient Ti-6Al-4V Encapsulated Hydroxyapatite Dual Materials Composite Scaffold for Bone Defects.

The tibia of New Zealand White rabbits was used as a model of critical bone defects to investigate a new design of composite scaffold for bone defects composed of dual materials. The all-in-one design of a titanium alloy (Ti-6Al-4V) scaffold comprised the structure of a bone plate and gradient porosity cage. Hydroxyapatite (HAp), a biodegradable material, was encapsulated in the center of the scaffold. The gradient pore structure was designed with 70%-65%-60%-55%-50% porosity, since the stresses could be distributed more uniformly when the all-in-one scaffold was placed on the bone contact surface. By covering the center of the scaffold with a low strength of HAp to contact the relatively low strength of bone marrow tissues, the excessive stiffness of the Ti-6Al-4V can be effectively reduced and further diminish the incidence of the stress shielding effect. The simulation results show that the optimized composite scaffold for the 3D model of tibia had a maximum stress value of 27.862 MPa and a maximum strain of 0.065%. The scaffold prepared by selective laser melting was annealed and found that the Young's coefficient increased from 126.44 GPa to 131.46 GPa, the hardness increased from 3.9 GPa to 4.12 GPa, and the strain decreased from 2.27% to 1.13%. The result demonstrates that the removal of residual stress can lead to a more stable structural strength, which can be used as a reference for the design of future clinical tibial defect repair scaffolds.

Sustained-Release and pH-Adjusted Alginate Microspheres-Encapsulated Doxorubicin Inhibit the Viabilities in Hepatocellular Carcinoma-Derived Cells.

The objective of this study aimed to develop biodegradable calcium alginate microspheres carrying doxorubicin (Dox) at the micrometer-scale for sustained release and the capacity of pH regulatory for transarterial chemoembolization. Ultrasonic atomization and CaCl2 cross-linking technologies were used to prepare the microspheres. A 4-by-5 experiment was first designed to identify imperative parameters. The concentration of CaCl2 and the flow rate of the pump were found to be critical to generate microspheres with a constant volume median diameter (~39 µm) across five groups with different alginate: NaHCO3 ratios using each corresponding flow rate. In each group, the encapsulation efficiency was positively correlated to the Dox-loading %. Fourier-transform infrared spectroscopy showed that NaHCO3 and Dox were step-by-step incorporated into the calcium alginate microspheres successfully. Microspheres containing alginate: NaHCO3 = 1 exhibited rough and porous surfaces, high Young's modulus, and hardness. In each group with the same alginate: NaHCO3 ratio, the swelling rates of microspheres were higher in PBS containing 10% FBS compared to those in PBS alone. Microspheres with relatively high NaHCO3 concentrations in PBS containing 10% FBS maintained better physiological pH and higher accumulated Dox release ratios. In two distinct hepatocellular carcinoma-derived cell lines, treatments with microspheres carrying Dox demonstrated that the cell viabilities decreased in groups with relatively high NaHCO3 ratios in time- and dose-dependent manners. Our results suggested that biodegradable alginate microspheres containing relatively high NaHCO3 concentrations improved the cytotoxicity effects in vitro.

Recognition Rate Advancement and Data Error Improvement of Pathology Cutting with H-DenseUNet for Hepatocellular Carcinoma Image.

Due to the fact that previous studies have rarely investigated the recognition rate discrepancy and pathology data error when applied to different databases, the purpose of this study is to investigate the improvement of recognition rate via deep learning-based liver lesion segmentation with the incorporation of hospital data. The recognition model used in this study is H-DenseUNet, which is applied to the segmentation of the liver and lesions, and a mixture of 2D/3D Hybrid-DenseUNet is used to reduce the recognition time and system memory requirements. Differences in recognition results were determined by comparing the training files of the standard LiTS competition data set with the training set after mixing in an additional 30 patients. The average error value of 9.6% was obtained by comparing the data discrepancy between the actual pathology data and the pathology data after the analysis of the identified images imported from Kaohsiung Chang Gung Memorial Hospital. The average error rate of the recognition output after mixing the LiTS database with hospital data for training was 1%. In the recognition part, the Dice coefficient was 0.52 after training 50 epochs using the standard LiTS database, while the Dice coefficient was increased to 0.61 after adding 30 hospital data to the training. After importing 3D Slice and ITK-Snap software, a 3D image of the lesion and liver segmentation can be developed. It is hoped that this method could be used to stimulate more research in addition to the general public standard database in the future, as well as to study the applicability of hospital data and improve the generality of the database.

EMP2 induces cytostasis and apoptosis via the TGFß/SMAD/SP1 axis and recruitment of P2RX7 in urinary bladder urothelial carcinoma.

PURPOSE: Urinary bladder urothelial carcinoma (UBUC) is a common malignant disease, and its high recurrence rates impose a heavy clinical burden. The objective of this study was to identify signaling pathways downstream of epithelial membrane protein 2 (EMP2), which induces cytostasis and apoptosis in UBUC. METHODS: A series of in vitro and in vivo assays using different UBUC-derived cell lines and mouse xenograft models were performed, respectively. In addition, primary UBUC specimens were evaluated by immunohistochemistry. RESULTS: Exogenous expression of EMP2 in J82 UBUC cells significantly decreased DNA replication and altered the expression levels of several TGFß signaling-related proteins. EMP2 knockdown in BFTC905 UBUC cells resulted in opposite effects. EMP2-dysregulated cell cycle progression was found to be mediated by the TGFß/TGFBR1/SP1 family member SMAD. EMP2 or purinergic receptor P2X7 (P2RX7) gene expression upregulation induced apoptosis via both intrinsic and extrinsic pathways. In 242 UBUC patient samples, P2RX7 protein levels were found to be significantly and positively correlated with EMP2 protein levels. Low P2RX7 levels conferred poor disease-specific and metastasis-free survival rates, and significantly decreased apoptotic cell rates. EMP2 was found to physically interact with P2RX7. In the presence of a P2RX7 agonist, BzATP, overexpression of both EMP2 and P2RX7 significantly increased apoptotic cell rates compared to overexpression of EMP2 or P2RX7 alone. CONCLUSIONS: EMP2 induces cytostasis via the TGFß/SMAD/SP1 axis and recruits P2RX7 to enhance apoptosis in UBUC. Our data provide new insights that may be employed for the design of UBUC targeting therapies.