Pelvic bone tumor segmentation fusion algorithm based on fully convolutional neural network and conditional random field.

Background and objective: Pelvic bone tumors represent a harmful orthopedic condition, encompassing both benign and malignant forms. Addressing the issue of limited accuracy in current machine learning algorithms for bone tumor image segmentation, we have developed an enhanced bone tumor image segmentation algorithm. This algorithm is built upon an improved full convolutional neural network, incorporating both the fully convolutional neural network (FCNN-4s) and a conditional random field (CRF) to achieve more precise segmentation. Methodology: The enhanced fully convolutional neural network (FCNN-4s) was employed to conduct initial segmentation on preprocessed images. Following each convolutional layer, batch normalization layers were introduced to expedite network training convergence and enhance the accuracy of the trained model. Subsequently, a fully connected conditional random field (CRF) was integrated to fine-tune the segmentation results, refining the boundaries of pelvic bone tumors and achieving high-quality segmentation. Results: The experimental outcomes demonstrate a significant enhancement in segmentation accuracy and stability when compared to the conventional convolutional neural network bone tumor image segmentation algorithm. The algorithm achieves an average Dice coefficient of 93.31 %, indicating superior performance in real-time operations. Conclusion: In contrast to the conventional convolutional neural network segmentation algorithm, the algorithm presented in this paper boasts a more intricate structure, proficiently addressing issues of over-segmentation and under-segmentation in pelvic bone tumor segmentation. This segmentation model exhibits superior real-time performance, robust stability, and is capable of achieving heightened segmentation accuracy.

Role of protein degradation systems in colorectal cancer.

Protein degradation is essential for maintaining protein homeostasis. The ubiquitin‒proteasome system (UPS) and autophagy-lysosome system are the two primary pathways responsible for protein degradation and directly related to cell survival. In malignant tumors, the UPS plays a critical role in managing the excessive protein load caused by cancer cells hyperproliferation. In this review, we provide a comprehensive overview of the dual roles played by the UPS and autolysosome system in colorectal cancer (CRC), elucidating their impact on the initiation and progression of this disease while also highlighting their compensatory relationship. Simultaneously targeting both protein degradation pathways offers new promise for enhancing treatment efficacy against CRC. Additionally, apoptosis is closely linked to ubiquitination and autophagy, and caspases degrade proteins. A thorough comprehension of the interplay between various protein degradation pathways is highly important for clarifying the mechanism underlying the onset and progression of CRC.

Deep learning-based image segmentation model using an MRI-based convolutional neural network for physiological evaluation of the heart.

Background and Objective: Cardiovascular disease is a high-fatality health issue. Accurate measurement of cardiovascular function depends on precise segmentation of physiological structure and accurate evaluation of functional parameters. Structural segmentation of heart images and calculation of the volume of different ventricular activity cycles form the basis for quantitative analysis of physiological function and can provide the necessary support for clinical physiological diagnosis, as well as the analysis of various cardiac diseases. Therefore, it is important to develop an efficient heart segmentation algorithm. Methods: A total of 275 nuclear magnetic resonance imaging (MRI) heart scans were collected, analyzed, and preprocessed from Huaqiao University Affiliated Strait Hospital, and the data were used in our improved deep learning model, which was designed based on the U-net network. The training set included 80% of the images, and the remaining 20% was the test set. Based on five time phases from end-diastole (ED) to end-systole (ES), the segmentation findings showed that it is possible to achieve improved segmentation accuracy and computational complexity by segmenting the left ventricle (LV), right ventricle (RV), and myocardium (myo). Results: We improved the Dice index of the LV to 0.965 and 0.921, and the Hausdorff index decreased to 5.4 and 6.9 in the ED and ES phases, respectively; RV Dice increased to 0.938 and 0.860, and the Hausdorff index decreased to 11.7 and 12.6 in the ED and ES, respectively; myo Dice increased to 0.889 and 0.901, and the Hausdorff index decreased to 8.3 and 9.2 in the ED and ES, respectively. Conclusion: The model obtained in the final experiment provided more accurate segmentation of the left and right ventricles, as well as the myocardium, from cardiac MRI. The data from this model facilitate the prediction of cardiovascular disease in real-time, thereby providing potential clinical utility.

Electrocardiogram Signal Classification in the Diagnosis of Heart Disease Based on RBF Neural Network.

Heart disease is a common disease affecting human health. Electrocardiogram (ECG) classification is the most effective and direct method to detect heart disease, which is helpful to the diagnosis of most heart disease symptoms. At present, most ECG diagnosis depends on the personal judgment of medical staff, which leads to heavy burden and low efficiency of medical staff. Automatic ECG analysis technology will help the work of relevant medical staff. In this paper, we use the MIT-BIH ECG database to extract the QRS features of ECG signals by using the Pan-Tompkins algorithm. After extraction of the samples, K-means clustering is used to screen the samples, and then, RBF neural network is used to analyze the ECG information. The classifier trains the electrical signal features, and the classification accuracy of the final classification model can reach 98.9%. Our experiments show that this method can effectively detect the abnormality of ECG signal and implement it for the diagnosis of heart disease.

Fully connected network with multi-scale dilation convolution module in evaluating atrial septal defect based on MRI segmentation.

BACKGROUND AND OBJECTIVE: Atrial septal defect (ASD) is a common congenital heart disease. During embryonic development, abnormal atrial septal development leads to pores between the left and right atria. ASD accounts for the largest proportion of congenital heart disease. Therefore, the design and implementation of an ASD intelligent auxiliary segmentation system based on deep learning segmentation of the atria has very important practical significance, which we aim to achieve in this paper. METHODS: This study proposes a multi-scale dilated convolution module, which is composed of three parallel dilated convolutions with different expansion coefficients. The original FCN network usually adopts bilinear interpolation or deconvolution methods when upsampling, both of which lead to information loss to a certain extent. In order to make up for the loss of information, it is expected that the final segmentation result can be directly connected to the deep features in the cardiac MRI. This study uses a dense upsampling convolution module, and in order to obtain the shallow position information, the original FCN jump connection module is still retained. In this research, a deep convolutional neural network for multi-scale feature extraction is designed through the multi-scale expansion convolution module. At the same time, this paper also implements two traditional machine learning segmentation methods (K-means and Watershed algorithms) and a deep learning algorithm (U-net) for comparison. RESULTS: The intelligent auxiliary segmentation algorithm for atrial images proposed in this framework based on multi-scale expansion convolution and adversarial learning can achieve superior results. Among them, the segmentation algorithm based on multi-scale expansion convolution can extract the associated features of pixels in multiple ranges, and can obtain deeper feature information when using a limited downsampling layer. According to the experimental results of the multi-scale expanded convolutional network on the data set, the Proportion of Greater Contour (PGC) index of the multi-scale expanded convolutional network is 98.78, the value of Average Perpendicular Distance (ADP) is 1.72mm, and the value of Overlapping Dice Metric (ODM) is 0.935, which are higher than other models. CONCLUSION: The experimental results show that compared with other segmentation models, the model based on multi-scale expansion convolution has significantly improved the accuracy of segmentation. Our technique will be able to assist in the segmentation of ASD, evaluation of the extent of the defect and enhance surgical planning via atrial septal occlusion.

Super-resolution reconstruction of pneumocystis carinii pneumonia images based on generative confrontation network.

OBJECTIVE: Pneumocystis carinii pneumonia, also known as pneumocystis carinii pneumonia (PCP), is an interstitial plasma cell pneumonia caused by pneumocystis spp. It is a conditional lung infectious disease. Because the early and correct diagnosis of PCP has a great influence on the prognosis of patients, the image processing of PCP's high-resolution CT (HRCT) is extremely important. Traditional image super-resolution reconstruction algorithms have difficulties in network training and artifacts in generated images. The super-resolution reconstruction algorithm of generative counter-networks can optimize these two problems well. METHODS: In this paper, the texture enhanced super-resolution generative adversarial network (TESRGAN) is based on a generative confrontation network, which mainly includes a generative network and a discriminant network. In order to improve the quality of image reconstruction, TESRGAN improved the structure of the Super-Resolution Generative Adversarial Network (SRGAN) generation network, removed all BN layers in SRGAN, and replaced the ReLU function with the LeakyReLU function as the nonlinear activation function of the network to avoid the disappearance of the gradient. EXPERIMENTAL RESULTS: The TESRGAN algorithm in this paper is compared with the image reconstruction results of Bicubic, SRGAN, Enhanced Deep Super-Resolution network (EDSR), and ESRGAN. Compared with algorithms such as SRGAN and EDSR, our algorithm has clearer texture details and more accurate brightness information without extending the running time. Our reconstruction algorithm can improve the accuracy of image low-frequency information. CONCLUSION: The texture details of the reconstruction result are clearer and the brightness information is more accurate, which is more in line with the requirements of visual sensory evaluation.

Current Progress and Future Perspectives of Immune Checkpoint in Cancer and Infectious Diseases.

The inhibitory regulators, known as immune checkpoints, prevent overreaction of the immune system, avoid normal tissue damage, and maintain immune homeostasis during the antimicrobial or antiviral immune response. Unfortunately, cancer cells can mimic the ligands of immune checkpoints to evade immune surveillance. Application of immune checkpoint blockade can help dampen the ligands expressed on cancer cells, reverse the exhaustion status of effector T cells, and reinvigorate the antitumor function. Here, we briefly introduce the structure, expression, signaling pathway, and targeted drugs of several inhibitory immune checkpoints (PD-1/PD-L1, CTLA-4, TIM-3, LAG-3, VISTA, and IDO1). And we summarize the application of immune checkpoint inhibitors in tumors, such as single agent and combination therapy and adverse reactions. At the same time, we further discussed the correlation between immune checkpoints and microorganisms and the role of immune checkpoints in microbial-infection diseases. This review focused on the current knowledge about the role of the immune checkpoints will help in applying immune checkpoints for clinical therapy of cancer and other diseases.

Automatic segmentation of cardiac magnetic resonance images based on multi-input fusion network.

PURPOSE: Using computer-assisted means to process a large amount of heart image data in order to speed up the diagnosis efficiency and accuracy of medical doctors has become a research worthy of investigation. METHOD: Based on the U-Net model, this paper proposes a multi-input fusion network (MIFNet) model based on multi-scale input and feature fusion, which automatically extracts and fuses features of different input scales to realize the detection of Cardiac Magnetic Resonance Images (CMRI). The MIFNet model is trained and verified on the public data set, and then compared with the segmentation models, namely the Fully Convolutional Network (FCN) and DeepLab v1. RESULTS: MIFNet model segmentation of CMRI significantly improved the segmentation accuracy, and the Dice value reached 97.238%. Compared with FCN and DeepLab v1, the average Hausdorff distance (HD) was reduced by 16.425%. The capacity parameter of FCN is 124.86% of MIFNet, DeepLab v1 is 103.22% of MIFNet. CONCLUSION: Our proposed MIFNet model reduces the amount of parameters and improves the training speed while ensuring the simultaneous segmentation of overlapping targets. It can help clinicians to more quickly check the patient's CMRI focus area, and thereby improving the efficiency of diagnosis.

Comparative analysis of pulmonary nodules segmentation using multiscale residual U-Net and fuzzy C-means clustering.

BACKGROUND AND OBJECTIVE: Pulmonary nodules have different shapes and uneven density, and some nodules adhere to blood vessels, pleura and other anatomical structures, which increase the difficulty of nodule segmentation. The purpose of this paper is to use multiscale residual U-Net to accurately segment lung nodules with complex geometric shapes, while comparing it with fuzzy C-means clustering and manual segmentation. METHOD: We selected 58 computed tomography (CT) scan images of patients with different lung nodules for image segmentation. This paper proposes an automatic segmentation algorithm for lung nodules based on multiscale residual U-Net. In order to verify the accuracy of the method, we also conducted comparative experiments, while comparing it with fuzzy C-means clustering. RESULTS: Compared with the other two methods, the segmentation of lung nodules based on multiscale residual U-Net has a higher accuracy, with an accuracy rate of 94.57%. This method not only maintains a high accuracy rate, but also shortens the recognition time significantly with a segmentation time of 3.15 s. CONCLUSIONS: The diagnosis method of lung nodules combined with deep learning has a good market prospect and can improve the efficiency of doctors in diagnosing benign and malignant lung nodules.

Management of medical and health big data based on integrated learning-based health care system: A review and comparative analysis.

PURPOSE: We present a Health Care System (HCS) based on integrated learning to achieve high-efficiency and high-precision integration of medical and health big data, and compared it with an internet-based integrated system. METHOD: The method proposed in this paper adopts the Bagging integrated learning method and the Extreme Learning Machine (ELM) prediction model to obtain a high-precision strong learning model. In order to verify the integration efficiency of the system, we compare it with the Internet-based health big data integration system in terms of integration volume, integration efficiency, and storage space capacity. RESULTS: The HCS based on integrated learning relies on the Internet in terms of integration volume, integration efficiency, and storage space capacity. The amount of integration is proportional to the time and the integration time is between 170-450 ms, which is only half of the comparison system; whereby the storage space capacity reaches 8.3×28TB. CONCLUSION: The experimental results show that the integrated learning-based HCS integrates medical and health big data with high integration volume and integration efficiency, and has high space storage capacity and concurrent data processing performance.

Inhibition LC3B can increase chemosensitivity of ovarian cancer cells.

BACKGROUND: Ovarian cancer is often accompanied by the production of ascites, and patients with repeated ascites are associated with chemotherapy resistance. The previous study confirmed that the ovarian cancer patients who developed ascites after chemotherapy had elevated autophagy levels in the ascites and precipitated cells, which was positively correlated with MDR1 expression in the blood of patients. METHODS: In order to explore the correlation between autophagy and chemoresistant, we searched TCGA and GEO database to analyze the correlation between LC3B and MDR1, and identified the targeting miRNA of LC3B. It was verified by dual luciferase that miR-204 can target LC3B. The ovarian cancer cell line and the BALB/c nude mice tumor-bearing model were selected for in vitro and in vivo verification. In vitro studies confirmed that ovarian cancer cells were more sensitive to cisplatin by inhibiting LC3B. RESULTS: Overexpression of miR-204 reduced the expression of LC3B, Atg7, and MDR1, and promoted apoptosis. In vivo studies have also confirmed that reducing the level of autophagy in ovarian cancer cells increases the sensitivity to cisplatin. CONCLUSIONS: It suggests that miR-204 can be used as a tumor suppressor gene and LC3B expression level can be used as a potential molecular marker to guide the diagnosis and treatment of patients with ovarian cancer.

CLIC1 a novel biomarker of intraperitoneal metastasis in serous epithelial ovarian cancer.

Early diagnosis of intraperitoneal metastasis is a pivot for survival of patients with serous epithelial ovarian cancers (SEOC). However, to date, there is lack of efficient molecular biomarker for early metastasis of SEOC. Here, we found that the expression of chloride intracellular channel 1 (CLIC1) is highly correlative with intraperitoneal metastasis. There is very low expression of CLIC1 in normal ovaries (NO), benign ovarian tumor (BOT), and primary ovarian cancer without metastasis (POCNM); but its expression is remarkably high in primary ovarian cancer with metastasis (POCM) omentum and peritoneal metastasis. Furthermore, for clinic prediction of intraperitoneal metastasis of SEOC, the sensitivity and specificity of CLIC1 overexpression were 97.4 and 88.1 %, respectively. Collectively, CLIC1 may be a potential sensitive and specific molecular biomarker for early diagnose for SEOC metastasis.

[Raman spectroscopic investigation of hydrogen storage in nitrogen gas hydrates].

Recently, hydrogen storage using clathrate hydrate as a medium has become a hotspot of hydrogen storage research In the present paper, the laser Raman spectroscopy was used to study the hydrogen storage in nitrogen hydrate. The synthetic nitrogen hydrate was reacted with hydrogen gas under relatively mild conditions (e.g., 15 MPa, -18 degrees C). The Raman spectra of the reaction products show that the hydrogen molecules have enclathrated the cavities of the nitrogen hydrate, with multiple hydrogen cage occupancies in the clathrate cavities. The reaction time is an important factor affecting the hydrogen storage in nitrogen hydrate. The experimental results suggest that nitrogen hydrates are expected to be an effective media for hydrogen storage.

[In situ Raman spectroscopic observation of micro-processes of methane hydrate formation and dissociation].

Micro laser Raman spectroscopic technique was used for in situ observation of the micro-processes of methane hydrate formed and decomposed in a high pressure transparent capillary. The changes in clathrate structure of methane hydrate were investigated during these processes. The results show that, during hydrate formation, the Raman peak (2 917 cm(-1)) of methane gas gradually splits into two peaks (2 905 and 2 915 cm(-1)) representing large and small cages, respectively, suggesting that the dissolved methane molecules go into two different chemical environments. In the meantime, the hydrogen bonds interaction is strengthened because water is changing from liquid to solid state gradually. As a result, the O-H stretching vibrations of water shift to lower wavenumber. During the decomposition process of methane hydrates, the Raman peaks of the methane molecules both in the large and small cages gradually clear up, and finally turn into a single peak of methane gas. The experimental results show that laser Raman spectroscopy can accurately demonstrate some relevant information of hydrate crystal structure changes during the formation and dissociation processes of methane hydrate.

[Determination of hydration number of methane hydrates using micro-laser Raman spectroscopy].

Methane hydrates are clathrate compounds that are formed by methane molecules and water molecules under low temperature and high pressure conditions. It was found that methane hydrates exist widely in sea-shelf floor and permafrost, and are considered as a potential energy resource. In the crystal lattice of clathrate hydrate, the water molecules form both large cages (5(12)6(2)) and small cages (5(12)) under the interaction of the hydrogen-hydrogen bond. In this paper, the authors designed a set of experimental apparatus for methane hydrates formation. Based on this equipment, the authors synthesized a series of methane hydrates in various systems in laboratory, including SDS solution (3% Wt) and methane, powdered ice and methane, and powdered ice and methane and natural sand with various sizes (i. e. 250-350, 180-250, 125-180 and 63-90 microm), under different temperature and pressure. The authors also designed a small device which was proved to be convenient for Raman determination of the methane hydrates. Raman spectroscopy was used to analyze the methane hydrates and to measure the structural parameters such as hydration numbers and cage occupancies. The results show that the methane hydrate samples are all in structure I type, and hydration numbers and cage occupancies are almost independent of the sediment sizes. In the three systems, the large cages of methane hydrate samples are nearly full occupied, with the occupancy ratios larger than 97%, whereas the small cages between 80% and 86%. The hydration numbers of these methane hydrate samples are between 6.05 and 6.15.

Marinobacter segnicrescens sp. nov., a moderate halophile isolated from benthic sediment of the South China Sea.

A Gram-negative, motile, non-spore-forming and moderately halophilic ellipsoid-shaped marine coccobacillus, designated strain SS011B1-4(T), was isolated from benthic sediment of the South China Sea. Optimum growth occurred at 30-37 degrees C, pH 7.5-8.0 and 4-8 % (w/v) NaCl. Strain SS011B1-4(T) utilized a variety of organic substrates as sole carbon sources, but did not utilize toluene, n-tetradecane or crude oil. Strain SS011B1-4(T) had ubiquinone-9 as the major respiratory quinone and C(18 : 1)omega9c, C(16 : 0) and C(12 : 0) 3-OH as the predominant fatty acids. The genomic DNA G+C content was 62.2 mol%. Phylogenetic analysis based on 16S rRNA gene sequences showed that strain SS011B1-4(T) belonged to the genus Marinobacter of the Gammaproteobacteria. The results of the phenotypic, phylogenetic and genomic analyses revealed that strain SS011B1-4(T) represents a novel species of the genus Marinobacter. The name Marinobacter segnicrescens sp. nov. is therefore proposed, with strain SS011B1-4(T) (=LMG 23928(T)=CGMCC 1.6489(T)) as the type strain.

Oceanicola nanhaiensis sp. nov., isolated from sediments of the South China Sea.

A Gram-negative, non-motile, rod-shaped bacterium, strain SS011B1-20(T), was isolated from sediments of the South China Sea. Growth occurred at NaCl concentrations between 0 and 10 % and at temperatures between 10 and 37 degrees C. Strain SS011B1-20(T) contained Q-10 as the major respiratory quinone and C(18 : 1)omega7c (81.2 %), C(16 : 0) (7.0 %) and C(18 : 1) methyl (4.3 %) as the predominant fatty acids. The G+C content of the genomic DNA was 64.7 mol%. A phylogenetic analysis based on the 16S rRNA gene sequence indicated that strain SS011B1-20(T) belonged to a clade within the genus Oceanicola in the Alphaproteobacteria, the highest sequence similarities being found with respect to Oceanicola batsensis (96.3 %) and with Oceanicola granulosus (94.9 %). Strain SS011B1-20(T) could be clearly distinguished from other Oceanicola species on the basis of the genotypic, phenotypic and phylogenetic data. Thus, it is proposed that strain SS011B1-20(T) represents a novel species of the genus Oceanicola, with the name Oceanicola nanhaiensis sp. nov. The type strain is SS011B1-20(T) (=LMG 23508(T)=CGMCC 1.6293(T)).