UWAFA-GAN: Ultra-Wide-Angle Fluorescein Angiography Transformation via Multi-scale Generation and Registration Enhancement.

Fundus photography, in combination with the ultra-wide-angle fundus (UWF) techniques, becomes an indispensable diagnostic tool in clinical settings by offering a more comprehensive view of the retina. Nonetheless, UWF fluorescein angiography (UWF-FA) necessitates the administration of a fluorescent dye via injection into the patient's hand or elbow unlike UWF scanning laser ophthalmoscopy (UWF-SLO). To mitigate potential adverse effects associated with injections, researchers have proposed the development of cross-modality medical image generation algorithms capable of converting UWF-SLO images into their UWF-FA counterparts. Current image generation techniques applied to fundus photography encounter difficulties in producing high-resolution retinal images, particularly in capturing minute vascular lesions. To address these issues, we introduce a novel conditional generative adversarial network (UWAFA-GAN) to synthesize UWF-FA from UWF-SLO. This approach employs multi-scale generators and an attention transmit module to efficiently extract both global structures and local lesions. Additionally, to counteract the image blurriness issue that arises from training with misaligned data, a registration module is integrated within this framework. Our method performs non-trivially on inception scores and details generation. Clinical user studies further indicate that the UWF-FA images generated by UWAFA-GAN are clinically comparable to authentic images in terms of diagnostic reliability. Empirical evaluations on our proprietary UWF image datasets elucidate that UWAFA-GAN outperforms extant methodologies. The code is accessible at https://github.com/Tinysqua/UWAFA-GAN.

Identification of important gene signatures in schizophrenia through feature fusion and genetic algorithm.

Schizophrenia is a debilitating psychiatric disorder that can significantly affect a patient's quality of life and lead to permanent brain damage. Although medical research has identified certain genetic risk factors, the specific pathogenesis of the disorder remains unclear. Despite the prevalence of research employing magnetic resonance imaging, few studies have focused on the gene level and gene expression profile involving a large number of screened genes. However, the high dimensionality of genetic data presents a great challenge to accurately modeling the data. To tackle the current challenges, this study presents a novel feature selection strategy that utilizes heuristic feature fusion and a multi-objective optimization genetic algorithm. The goal is to improve classification performance and identify the key gene subset for schizophrenia diagnostics. Traditional gene screening techniques are inadequate for accurately determining the precise number of key genes associated with schizophrenia. Our innovative approach integrates a filter-based feature selection method to reduce data dimensionality and a multi-objective optimization genetic algorithm for improved classification tasks. By combining the filtering and wrapper methods, our strategy leverages their respective strengths in a deliberate manner, leading to superior classification accuracy and a more efficient selection of relevant genes. This approach has demonstrated significant improvements in classification results across 11 out of 14 relevant datasets. The performance on the remaining three datasets is comparable to the existing methods. Furthermore, visual and enrichment analyses have confirmed the practicality of our proposed method as a promising tool for the early detection of schizophrenia.

TDFFM: Transformer and Deep Forest Fusion Model for Predicting Coronavirus 3C-Like Protease Cleavage Sites.

COVID-19, caused by the highly contagious SARS-CoV-2 virus, is distinguished by its positive-sense, single-stranded RNA genome. A thorough understanding of SARS-CoV-2 pathogenesis is crucial for halting its proliferation. Notably, the 3C- like protease of the coronavirus (denoted as 3CLpro) is instrumental in the viral replication process. Precise delineation of 3CLpro cleavage sites is imperative for elucidating the transmission dynamics of SARS-CoV-2. While machine learning tools have been deployed to identify potential 3CLpro cleavage sites, these existing methods often fall short in terms of accuracy. To improve the performances of these predictions, we propose a novel analytical framework, the Transformer and Deep Forest Fusion Model (TDFFM). Within TDFFM, we utilize the AAindex and the BLOSUM62 matrix to encode protein sequences. These encoded features are subsequently input into two distinct components: a Deep Forest, which is an effective decision tree ensemble methodology, and a Transformer equipped with a Multi-Level Attention Model (TMLAM). The integration of the attention mechanism allows our model to more accurately identify positive samples, thus enhancing the overall predictive performance. Evaluation on a test set demonstrates that our TDFFM achieves an accuracy of 0.955, an AUC of 0.980, and an F1-score of 0.367, substantiating the model's superior prediction capabilities.

Accurate leukocyte detection based on deformable-DETR and multi-level feature fusion for aiding diagnosis of blood diseases.

In standard hospital blood tests, the traditional process requires doctors to manually isolate leukocytes from microscopic images of patients' blood using microscopes. These isolated leukocytes are then categorized via automatic leukocyte classifiers to determine the proportion and volume of different types of leukocytes present in the blood samples, aiding disease diagnosis. This methodology is not only time-consuming and labor-intensive, but it also has a high propensity for errors due to factors such as image quality and environmental conditions, which could potentially lead to incorrect subsequent classifications and misdiagnosis. Contemporary leukocyte detection methods exhibit limitations in dealing with images with fewer leukocyte features and the disparity in scale among different leukocytes, leading to unsatisfactory results in most instances. To address these issues, this paper proposes an innovative method of leukocyte detection: the Multi-level Feature Fusion and Deformable Self-attention DETR (MFDS-DETR). To tackle the issue of leukocyte scale disparity, we designed the High-level Screening-feature Fusion Pyramid (HS-FPN), enabling multi-level fusion. This model uses high-level features as weights to filter low-level feature information via a channel attention module and then merges the screened information with the high-level features, thus enhancing the model's feature expression capability. Further, we address the issue of leukocyte feature scarcity by incorporating a multi-scale deformable self-attention module in the encoder and using the self-attention and cross-deformable attention mechanisms in the decoder, which aids in the extraction of the global features of the leukocyte feature maps. The effectiveness, superiority, and generalizability of the proposed MFDS-DETR method are confirmed through comparisons with other cutting-edge leukocyte detection models using the private WBCDD, public LISC and BCCD datasets. Our source code and private WBCCD dataset are available at https://github.com/JustlfC03/MFDS-DETR.

MiR-26a-5p exerts its influence by targeting EP300, a molecule known for its role in activating the PI3K/AKT/mTOR signaling pathway in CD8+tumor-infiltrating lymphocytes of colorectal cancer.

Surgical resection remains the primary approach for treating colorectal cancer, which is among the prevalent types of cancers affecting the digestive system. Tumor-infiltrating lymphocyte (TIL) therapy has emerged as a prominent area of study in the field of tumor immunotherapy in recent times, with the potential to serve as a supplementary treatment for colorectal cancer. For this investigation, we employed single-cell sequencing data to assess the manifestation extent of miR-26a-5p exists in healthy colon tissue, tissue affected by colorectal cancer, and tissue adjacent to the tumor. According to our findings, tumor-infiltrating T lymphocytes express comparatively less miR-26a-5p in comparison to normal T lymphocytes, the role of it in modulating the function of tumor-infiltrating T lymphocytes is suggested. Studies on miR-26a-5p's involvement in tumor-infiltrating T lymphocytes is limited, despite previous evidence indicating its ability to facilitate the development and advancement of cancerous cells. As a result of our experiments, we concluded that miR-26a-5p hindered the PI3K/AKT/mTOR(PAM) signaling pathway, reducing the ability of CD8+ tumor-infiltrating cells eradicate tumors. Using bioinformatics tools, we utilized prediction methods to identify EP300 as the specific gene targeted by miR-26a-5p. Subsequent research understood that downregulation of EP300 counteracted the suppressive impact exerted by miR-26a-5p on the stimulation of PAM signaling pathway, while it also diminishes the viability and cytotoxicity of CD8+ tumor-infiltrating lymphocytes. Therefore, miR-26a-5p emerges as a compelling option for the effective control of TIL therapy.

Exploring the mechanism of resistance to vincristine in breast cancer cells using transcriptome sequencing technology.

Breast cancer has replaced lung cancer as the leading cancer globally, but various chemotherapy drugs for breast cancer are prone to resistance, especially in patients with distant metastases who are susceptible to multiple chemotherapy drug resistance often leading to treatment failure. Vincristine (VCR) is an alkaloid extracted from Catharanthus roseus, and is often used in combination with other chemotherapy drugs to treat various types of cancer, including breast cancer. Research on the development of resistance to VCR has been carried out using transcriptome sequencing technology. Firstly, gradient increase of VCR concentration was used to produce a VCR-resistant breast cancer cell line. Mechanistically, RNA was extracted from the VCR-resistant breast cancer cell line, and the transcriptome was sequenced. Further analysis showed changes in the expression levels of various genes in the aforementioned VCR-resistant breast cancer cell line. Meanwhile, the analysis of splicing events also indicated a change in variable splicing events. Further validation showed that the expression levels of multiple genes, including interleukin-1ß, were altered in the VCR-resistant breast cancer cell line, and these gene expression changes were related to VCR resistance. The results of the present study provide a theoretical basis for exploring the mechanism of VCR resistance clinically.

Characterization of anoikis-based molecular heterogeneity in pancreatic cancer and pancreatic neuroendocrine tumor and its association with tumor immune microenvironment and metabolic remodeling.

Background: Accumulating evidence suggests that anoikis plays a crucial role in the onset and progression of pancreatic cancer (PC) and pancreatic neuroendocrine tumors (PNETs); nevertheless, the prognostic value and molecular characteristics of anoikis in cancers are yet to be determined. Materials and methods: We gathered and collated the multi-omics data of several human malignancies using the TCGA pan-cancer cohorts. We thoroughly investigated the genomics and transcriptomics features of anoikis in pan-cancer. We then categorized a total of 930 patients with PC and 226 patients with PNETs into distinct clusters based on the anoikis scores computed through single-sample gene set enrichment analysis. We then delved deeper into the variations in drug sensitivity and immunological microenvironment between the various clusters. We constructed and validated a prognostic model founded on anoikis-related genes (ARGs). Finally, we conducted PCR experiments to explore and verify the expression levels of the model genes. Results: Initially, we identified 40 differentially expressed anoikis-related genes (DE-ARGs) between pancreatic cancer (PC) and adjacent normal tissues based on the TCGA, GSE28735, and GSE62452 datasets. We systematically explored the pan-cancer landscape of DE-ARGs. Most DE-ARGs also displayed differential expression trends in various tumors, which were strongly linked to favorable or unfavorable prognoses of patients with cancer, especially PC. Cluster analysis successfully identified three anoikis-associated subtypes for PC patients and two anoikis-associated subtypes for PNETs patients. The C1 subtype of PC patients showed a higher anoikis score, poorer prognosis, elevated expression of oncogenes, and lower level of immune cell infiltration, whereas the C2 subtype of PC patients had the exact opposite characteristics. We developed and validated a novel and accurate prognostic model for PC patients based on the expression traits of 13 DE-ARGs. In both training and test cohorts, the low-risk subpopulations had significantly longer overall survival than the high-risk subpopulations. Dysregulation of the tumor immune microenvironment could be responsible for the differences in clinical outcomes between low- and high-risk groups. Conclusions: These findings provide fresh insights into the significance of anoikis in PC and PNETs. The identification of subtypes and construction of models have accelerated the progress of precision oncology.

Determination and characterization of molecular heterogeneity and precision medicine strategies of patients with pancreatic cancer and pancreatic neuroendocrine tumor based on oxidative stress and mitochondrial dysfunction-related genes.

Background: Mitochondria are significant both for cellular energy production and reactive oxygen/nitrogen species formation. However, the significant functions of mitochondrial genes related to oxidative stress (MTGs-OS) in pancreatic cancer (PC) and pancreatic neuroendocrine tumor (PNET) are yet to be investigated integrally. Therefore, in pan-cancer, particularly PC and PNET, a thorough assessment of the MTGs-OS is required. Methods: Expression patterns, prognostic significance, mutation data, methylation rates, and pathway-regulation interactions were studied to comprehensively elucidate the involvement of MTGs-OS in pan-cancer. Next, we separated the 930 PC and 226 PNET patients into 3 clusters according to MTGs-OS expression and MTGs-OS scores. LASSO regression analysis was utilized to construct a novel prognostic model for PC. qRT-PCR(Quantitative real-time PCR) experiments were performed to verify the expression levels of model genes. Results: The subtype associated with the poorest prognosis and lowerest MTGs-OS scores was Cluster 3, which could demonstrate the vital function of MTGs-OS for the pathophysiological processes of PC. The three clusters displayed distinct variations in the expression of conventional cancer-associated genes and the infiltration of immune cells. Similar molecular heterogeneity was observed in patients with PNET. PNET patients with S1 and S2 subtypes also showed distinct MTGs-OS scores. Given the important function of MTGs-OS in PC, a novel and robust MTGs-related prognostic signature (MTGs-RPS) was established and identified for predicting clinical outcomes for PC accurately. Patients with PC were separated into the training, internal validation, and external validation datasets at random; the expression profile of MTGs-OS was used to classify patients into high-risk (poor prognosis) or low-risk (good prognosis) categories. The variations in the tumor immune microenvironment may account for the better prognoses observed in high-risk individuals relative to low-risk ones. Conclusions: Overall, our study for the first time identified and validated eleven MTGs-OS remarkably linked to the progression of PC and PNET, and elaborated the biological function and prognostic value of MTGs-OS. Most importantly, we established a novel protocol for the prognostic evaluation and individualized treatment for patients with PC.

Comprehensive Characterization of RNA-Binding Proteins in Colon Adenocarcinoma Identifies a Novel Prognostic Signature for Predicting Clinical Outcomes and Immunotherapy Responses Based on Machine Learning.

BACKGROUND: RNA-binding proteins (RBPs) are crucial factors that function in the posttranscriptional modification process and are significant in cancer. OBJECTIVE: This research aimed for a multigene signature to predict the prognosis and immunotherapy response of patients with colon adenocarcinoma (COAD) based on the expression profile of RNA-binding proteins (RBPs). METHODS: COAD samples retrieved from the TCGA and GEO datasets were utilized for a training dataset and a validation dataset. Totally, 14 shared RBP genes with prognostic significance were identified. Non-negative matrix factorization clusters defined by these RBPs could stratify COAD patients into two molecular subtypes. Cox regression analysis and identification of 8-gene signature categorized COAD patients into high- and low-risk populations with significantly different prognosis and immunotherapy responses. RESULTS: Our prediction signature was superior to another five well-established prediction models. A nomogram was generated to quantificationally predict the overall survival (OS) rate, validated by calibration curves. Our findings also indicated that high-risk populations possessed an enhanced immune evasion capacity and low-risk populations might benefit immunotherapy, especially for the joint combination of PD-1 and CTLA4 immunosuppressants. DHX15 and LARS2 were detected with significantly different expressions in both datasets, which were further confirmed by qRTPCR and immunohistochemical staining. CONCLUSION: Our observations supported an eight-RBP-related signature that could be applied for survival prediction and immunotherapy response of patients with COAD.

Real-time automatic prediction of treatment response to transcatheter arterial chemoembolization in patients with hepatocellular carcinoma using deep learning based on digital subtraction angiography videos.

BACKGROUND: Transcatheter arterial chemoembolization (TACE) is the mainstay of therapy for intermediate-stage hepatocellular carcinoma (HCC); yet its efficacy varies between patients with the same tumor stage. Accurate prediction of TACE response remains a major concern to avoid overtreatment. Thus, we aimed to develop and validate an artificial intelligence system for real-time automatic prediction of TACE response in HCC patients based on digital subtraction angiography (DSA) videos via a deep learning approach. METHODS: This retrospective cohort study included a total of 605 patients with intermediate-stage HCC who received TACE as their initial therapy. A fully automated framework (i.e., DSA-Net) contained a U-net model for automatic tumor segmentation (Model 1) and a ResNet model for the prediction of treatment response to the first TACE (Model 2). The two models were trained in 360 patients, internally validated in 124 patients, and externally validated in 121 patients. Dice coefficient and receiver operating characteristic curves were used to evaluate the performance of Models 1 and 2, respectively. RESULTS: Model 1 yielded a Dice coefficient of 0.75 (95% confidence interval [CI]: 0.73-0.78) and 0.73 (95% CI: 0.71-0.75) for the internal validation and external validation cohorts, respectively. Integrating the DSA videos, segmentation results, and clinical variables (mainly demographics and liver function parameters), Model 2 predicted treatment response to first TACE with an accuracy of 78.2% (95%CI: 74.2-82.3), sensitivity of 77.6% (95%CI: 70.7-84.0), and specificity of 78.7% (95%CI: 72.9-84.1) for the internal validation cohort, and accuracy of 75.1% (95% CI: 73.1-81.7), sensitivity of 50.5% (95%CI: 40.0-61.5), and specificity of 83.5% (95%CI: 79.2-87.7) for the external validation cohort. Kaplan-Meier curves showed a significant difference in progression-free survival between the responders and non-responders divided by Model 2 (p = 0.002). CONCLUSIONS: Our multi-task deep learning framework provided a real-time effective approach for decoding DSA videos and can offer clinical-decision support for TACE treatment in intermediate-stage HCC patients in real-world settings.

The Effect of Shaoyao Gancao Decoction on Sphincter of Oddi Dysfunction in Hypercholesterolemic Rabbits via Protecting the Enteric Nervous System-Interstitial Cells of Cajal-Smooth Muscle Cells Network.

OBJECTIVE: This study observes the morphological changes in the enteric nervous system (ENS) - interstitial cells of Cajal (ICC) - smooth muscle cells (SMC) network in sphincter of Oddi dysfunction (SOD) in hypercholesterolemic rabbits following treatment with Shaoyao Gancao decoction (SGD), as well as the apoptosis of the ICC. METHODS: In this study, 48 healthy adult New Zealand rabbits are randomly divided into three groups (n = 16 in each group): the control, the model, and the SGD treatment groups. The hypercholesterolemic rabbit model is established. Hematoxylin and eosin staining, transmission electron microscopy, immunofluorescence, terminal deoxynucleotidyl transferase dUTP nick end labeling staining, immunohistochemistry, Western blot analysis, and reverse transcription-polymerase chain reaction are used to detect the morphological changes in the ENS-ICC-SMC network, the expression of apoptosis-related proteins in the ICC, and to observe the curative effect of SGD after treatment. RESULTS: Compared with the control group, the morphology and the ultrastructure of the SO are destroyed in the model group. In addition, the protein gene product 9.5 (PGP9.5), nitric oxide (NO), the SMCs, and the ICC all significantly decreased while substance P (SP) significantly increased. Compared with the model group, the SO morphology and ultrastructure are repaired in the SGD group. In addition, the PGP9.5, NO, the SMCs, and the ICC significantly increased while SP decreased. In addition, SGD may activate the stem cell factor (SCF)/c-Kit signaling pathway to treat SO dysfunction by up-regulating the expression of c-Kit and SCF. Similarly, this pathway restores SO by up-regulating the expression of Bcl2 and inhibiting cleaved caspase-3, Bax, and the tumor necrosis factor. CONCLUSION: Shaoyao Gancao decoction can promote the recovery of sphincter of Oddi dysfunction in hypercholesterolemic rabbits by protecting the ENS-ICC-SMC network.

Recent advances in prevention and management of endoscopic retrograde cholangiopancreatography-related duodenal perforation.

Endoscopic retrograde cholangiopancreatography (ERCP) is the main diagnosis and treatment for biliary and pancreatic diseases; however, ERCP requires a high level of technical skill and experience, and there is always a risk of complications. ERCP-related duodenal perforation is one of the most serious complications of ERCP, and although the incidence rate is relatively low, the mortality rate is high. Recently, the introduction of new classification methods and the development of endoscopic technology and equipment have made endoscopic therapy a new trend. This may change the management strategy of perforation. Therefore, we reviewed the latest developments in endoscopic management, surgical management, and conservative internal medicine management. In addition to introducing many new endoscope treatment methods, we also discussed the timing of interventions, the progress of endoscope and surgical indications, and corresponding prevention strategies. We aim to retrospectively analyse these treatment modalities to propose appropriate solutions to improve dynamic clinical therapy.

Glioma Growth Prediction via Generative Adversarial Learning from Multi-Time Points Magnetic Resonance Images.

Gliomas are the most dominant and lethal type of brain tumors. Growth prediction is significant to quantify tumor aggressiveness, improve therapy planning, and estimate patients' survival time. This is commonly addressed in literature using mathematical models guided by multi-time point scans of multi/single-modal data for the same subject. However, these models are mechanism-based and heavily rely on complicated mathematical formulations of partial differential equations with few parameters that are insufficient to capture different patterns and other characteristics of gliomas. In this paper, we propose a 3D generative adversarial networks (GANs) for glioma growth prediction. Specifically, we stack 2 GANs with conditional initialization of segmented feature maps. Furthermore, we employ Dice loss in our objective function and devised 3D U-Net architecture for better image generation. The proposed method is trained and validated using 3D patch-based strategy on real magnetic resonance images of 9 subjects with 3 time points. Experimental results show that the proposed method can be successfully used for glioma growth prediction with satisfactory performance.

GP-GAN: Brain tumor growth prediction using stacked 3D generative adversarial networks from longitudinal MR Images.

Brain tumors are one of the major common causes of cancer-related death, worldwide. Growth prediction of these tumors, particularly gliomas which are the most dominant type, can be quite useful to improve treatment planning, quantify tumor aggressiveness, and estimate patients' survival time towards precision medicine. Studying tumor growth prediction basically requires multiple time points of single or multimodal medical images of the same patient. Recent models are based on complex mathematical formulations that basically rely on a system of partial differential equations, e.g. reaction diffusion model, to capture the diffusion and proliferation of tumor cells in the surrounding tissue. However, these models usually have small number of parameters that are insufficient to capture different patterns and other characteristics of the tumors. In addition, such models consider tumor growth independently for each subject, not being able to get benefit from possible common growth patterns existed in the whole population under study. In this paper, we propose a novel data-driven method via stacked 3D generative adversarial networks (GANs), named GP-GAN, for growth prediction of glioma. Specifically, we use stacked conditional GANs with a novel objective function that includes both l1 and Dice losses. Moreover, we use segmented feature maps to guide the generator for better generated images. Our generator is designed based on a modified 3D U-Net architecture with skip connections to combine hierarchical features and thus have a better generated image. The proposed method is trained and tested on 18 subjects with 3 time points (9 subjects from collaborative hospital and 9 subjects from BRATS 2014 dataset). Results show that our proposed GP-GAN outperforms state-of-the-art methods for glioma growth prediction and attain average Jaccard index and Dice coefficient of 78.97% and 88.26%, respectively.

Relationship between SDC1 and cadherin signalling activation in cancer.

E-cadherin and SDC1 are markers of epithelial-to-mesenchymal transition (EMT) that can be used to assess tumour prognosis. SDC1 has different effects in various types of cancers. On the one hand, reduced expression of SDC1 can leads to advantage stages of some cancers, such as gastric and colorectal cancer. On the other hand, SDC1 overexpression can also promote the growth and proliferation of cancer cells in pancreatic and breast cancer. However, the function of SDC1 is influenced and regulated by many factors. Exfoliated extracellular domain HS chain can mediate the function of SDC1 and play an important role in the occurrence and development of cancer. SDC1 binds to various ligands and influences the growth and reproduction of cancer cells via the activation of Wnt, the long isoform of FLICE-inhibitory protein (FLIP long), vascular endothelial growth factor receptor (VEGFR), mitogen-activated protein kinase (MAPK)/extracellular signal-regulated kinase (ERK) and MAPK/c-Jun N-terminal kinase (JNK) and other pathways. Cadherins occur in several types, but this review focuses on classical cadherins. N-cadherin and P-cadherin are activated during tumour development, whereas E-cadherin is a tumour suppressor. The cellular signalling pathways involved in classical cadherins, such as Wnt and VEGFR pathways, are also related to SDC1. The activation of E-cadherin caused by SDC1 knockdown has also been observed. Despite this evidence, no articles regarding the relationship of SDC1 and cadherin activation have been published. This review summarises the expressions of these two molecules in different cancers and analyses their possible relationship to provide insights into future cancer research and clinical treatment.

Effects of Paeoniflorin on the activity of muscle strips, intracellular calcium ion concentration and L­type voltage­sensitive calcium ion channels in the sphincter of Oddi of hypercholesterolemic rabbits.

Sphincter of Oddi dysfunction (SOD) is a benign obstructive disorder predominantly resulting from spasms of the SO. Pharmacological therapies aim to induce SO relaxation; the hypercholesterolemic (HC) rabbit is the only SOD model available for study. In the present study, SO muscle strips, intracellular calcium ion concentrations and the mRNA expression levels of the α1C subunit of the L­type calcium channel in the SO muscle cells of HC rabbits were employed to investigate the effects of paeoniflorin (PF). Alterations in L­type calcium channel α subunit 1C mRNA and protein expression in SO cells with HC following the application of different concentrations of PF were determined by reverse transcription­quantitative polymerase chain reaction and western blotting. The whole cell patch clamp technique was used to observe the effects of different concentrations of paeoniflorin on L­type calcium channel current. The results of the present study demonstrated that PF induced the relaxation of SO muscle strips and reduced the intracellular calcium concentration in the SO muscle cells of HC rabbits. In addition, PF decreased the mRNA expression levels of the α1C subunit of the L­type calcium channel and reduced the L­type calcium channel current in SO cells. These results suggested that the mechanism underlying the relaxation of the SO muscle by PF may be associated with the reduction of calcium ion influx via L­type calcium channels.

Adjuvant transarterial chemoembolization to improve the prognosis of hepatocellular carcinoma following curative resection.

The present study aimed to investigate the prognostic factors for recurrence of hepatocellular carcinoma (HCC) following curative resection, and evaluate the efficacy of postoperative adjuvant transarterial chemoembolization (TACE) in improving prognosis. A total of 166 patients who underwent curative resection followed by adjuvant TACE, and 190 patients who underwent curative resection alone were studied retrospectively. Univariate and multivariate analyses were performed to investigate the risk factors of recurrence. Separated based on risk factors, subgroup studies were conducted and the association between TACE and recurrence rates was examined. Postoperative overall survival rates were determined using the Kaplan-Meier method and differences between the two therapeutic strategies were identified through log-rank analysis. Computerized tomography (CT)/magnetic resonance imaging (MRI) images were used to evaluate the function of postoperative adjuvant TACE for enhancing the efficacy of CT/MRI in detecting recurrence. The results of the univariate and multivariate analyses revealed that tumor capsule invasion, vascular invasion, and multiple nodules were risk factors of early recurrence. For patients with these risk factors, recurrence rates were markedly decreased at 6 and 12 months, but not at 18 and 24 months, if TACE was added to curative resection. The hepatitis B virus (HBV) was a risk factor for late recurrence. Postoperative TACE was not effective in reducing the recurrence rate in patients with HBV. Survival increased following curative resection with TACE compared with curative resection alone. Furthermore, adjuvant TACE enhanced the efficacy of CT/MRI in detecting recurrence. Postoperative adjuvant TACE may improve the prognosis of HCC following curative resection.

MicroRNA-494 acts as a tumor suppressor in pancreatic cancer, inhibiting epithelial-mesenchymal transition, migration and invasion by binding to SDC1.

Pancreatic cancer (PC) is the fourth most common cause of cancer­related mortality in the industrialized world. Emerging evidence indicates that a variety of microRNAs (miRNAs or miRs) are involved in the development of PC. The aim of the present study was to elucidate the mechanisms through which miR­494 affects the epithelial­mesenchymal transition (EMT) and invasion of PC cells by binding to syndecan 1 (SDC1). PC tissues and pancreatitis tissues were collected, and the regulatory effects of miR­494 on SDC1 were validated using bioinformatics analysis and a dual­luciferase report gene assay. The cell line with the highest SDC1 expression was selected for use in the following experiments. The role of miR­494 in EMT was assessed by measuring the expression of SDC1, E­cadherin and vimentin. Cell proliferation was assessed using a cell counting kit (CCK)­8 assay, migration was measured using a scratch test, invasion was assessed with a Transwell assay and apoptosis was detected by flow cytometry. Finally, a xenograft tumor model was constructed in nude mice to observe tumor growth in vivo. We found that SDC1 protein expression was significantly higher in the PC tissues. SDC1 was verified as a target gene of miR­494. The SW1990 cell line was selected for use in further experiments as it had the lowest miR­494 expression and the highest SDC1 expression. Our results also demonstrated that miR­494 overexpression and SDC1 silencing significantly decreased the mRNA and protein expression of SDC1 and vimentin in SW1990 cells, while it increased E­cadherin expression and apoptosis, and inhibited cell growth, migration, invasion and tumor growth. On the whole, the findings of this study demonstrated that miR­494 is able to downregulate SDC1 expression, thereby inhibiting the progression of PC. These findings reveal a novel mechanism through which miR­494 affects the development of PC and may thus provide a basis for the application of miR­494 in pancreatic oncology.

Automated chest screening based on a hybrid model of transfer learning and convolutional sparse denoising autoencoder.

OBJECTIVE: In this paper, we aim to investigate the effect of computer-aided triage system, which is implemented for the health checkup of lung lesions involving tens of thousands of chest X-rays (CXRs) that are required for diagnosis. Therefore, high accuracy of diagnosis by an automated system can reduce the radiologist's workload on scrutinizing the medical images. METHOD: We present a deep learning model in order to efficiently detect abnormal levels or identify normal levels during mass chest screening so as to obtain the probability confidence of the CXRs. Moreover, a convolutional sparse denoising autoencoder is designed to compute the reconstruction error. We employ four publicly available radiology datasets pertaining to CXRs, analyze their reports, and utilize their images for mining the correct disease level of the CXRs that are to be submitted to a computer aided triaging system. Based on our approach, we vote for the final decision from multi-classifiers to determine which three levels of the images (i.e. normal, abnormal, and uncertain cases) that the CXRs fall into. RESULTS: We only deal with the grade diagnosis for physical examination and propose multiple new metric indices. Combining predictors for classification by using the area under a receiver operating characteristic curve, we observe that the final decision is related to the threshold from reconstruction error and the probability value. Our method achieves promising results in terms of precision of 98.7 and 94.3% based on the normal and abnormal cases, respectively. CONCLUSION: The results achieved by the proposed framework show superiority in classifying the disease level with high accuracy. This can potentially save the radiologists time and effort, so as to allow them to focus on higher-level risk CXRs.

Lung nodule classification using deep feature fusion in chest radiography.

Lung nodules are small, round, or oval-shaped masses of tissue in the lung region. Early diagnosis and treatment of lung nodules can significantly improve the quality of patients' lives. Because of their small size and the interlaced nature of chest anatomy, detection of lung nodules using different medical imaging techniques becomes challenging. Recently, several methods for computer aided diagnosis (CAD) were proposed to improve the detection of lung nodules with good performances. However, the current methods are unable to achieve high sensitivity and high specificity. In this paper, we propose using deep feature fusion from the non-medical training and hand-crafted features to reduce the false positive results. Based on our experimentation of the public dataset, our results show that, the deep fusion feature can achieve promising results in terms of sensitivity and specificity (69.3% and 96.2%) at 1.19 false positive per image, which is better than the single hand-crafted features (62% and 95.4%) at 1.45 false positive per image. As it stands, fusion features that were used to classify our candidate nodules have resulted in a more promising outcome as compared to the single features from deep learning features and the hand-crafted features. This will improve the current CAD method based on the use of deep feature fusion to more effectively diagnose the presence of lung nodules.