Integrating trans-omics, cellular experiments and clinical validation to identify ILF2 as a diagnostic serum biomarker and therapeutic target in gastric cancer.

BACKGROUND: Gastric cancer (GC) lacks serum biomarkers with clinical diagnostic value. Multi-omics analysis is an important approach to discovering cancer biomarkers. This study aimed to identify and validate serum biomarkers for GC diagnosis by cross-analysis of proteomics and transcriptomics datasets. METHODS: A cross-omics analysis was performed to identify overlapping differentially expressed genes (DEGs) between our previous aptamer-based GC serum proteomics dataset and the GC tissue RNA-Seq dataset in The Cancer Genome Atlas (TCGA) database, followed by lasso regression and random forest analysis to select key overlapping DEGs as candidate biomarkers for GC. The mRNA levels and diagnostic performance of these candidate biomarkers were analyzed in the original and independent GC datasets to select valuable candidate biomarkers. The valuable candidate biomarkers were subjected to bioinformatics analysis to select those closely associated with the biological behaviors of GC as potential biomarkers. The clinical diagnostic value of the potential biomarkers was validated using serum samples, and their expression levels and functions in GC cells were validated using in vitro cell experiments. RESULTS: Four candidate biomarkers (ILF2, PGM2L1, CHD7, and JCHAIN) were selected. Their mRNA levels differed significantly between tumor and normal tissues and showed different diagnostic performances for GC, with areas under the receiver operating characteristic curve (AUROCs) of 0.629-0.950 in the TCGA dataset and 0.736-0.840 in the Gene Expression Omnibus (GEO) dataset. In the bioinformatics analysis, only ILF2 (interleukin enhancer-binding factor 2) gene levels were associated with immune cell infiltration, some checkpoint gene expression, chemotherapy sensitivity, and immunotherapy response. Serum levels of ILF2 were higher in GC patients than in controls, with an AUROC of 0.944 for the diagnosis of GC, and it was also detected in the supernatants of GC cells. Knockdown of ILF2 by siRNA significantly reduced the proliferation and colony formation of GC cells. Overexpression of ILF2 significantly promotes the proliferation and colony formation of gastric cancer cells. CONCLUSIONS: Trans-omics analysis of proteomics and transcriptomics is an efficient approach for discovering serum biomarkers, and ILF2 is a potential diagnostic biomarker and therapeutic target of gastric cancer.

The Index sAGP is Valuable for Distinguishing Atypical Hepatocellular Carcinoma from Atypical Benign Focal Hepatic Lesions.

Purpose: The differential diagnosis of atypical hepatocellular carcinoma (aHCC) and atypical benign focal hepatic lesions (aBFHL) usually depends on pathology. This study aimed to develop non-invasive approaches based on conventional blood indicators for the differential diagnosis of aHCC and aBFHL. Patients and Methods: Hospitalized patients with pathologically confirmed focal hepatic lesions and their clinical data were retrospectively collected, in which patients with HCC with serum alpha-fetoprotein (AFP) levels of ≤200 ng/mL and atypical imaging features were designated as the aHCC group (n = 224), and patients with benign focal hepatic lesions without typical imaging features were designated as the aBFHL group (n = 178). The performance of indexes (both previously reported and newly constructed) derived from conventional blood indicators by four mathematical operations in distinguishing aHCC and aBFHL was evaluated using the receiver operating characteristic (ROC) curve and diagnostic validity metrics. Results: Among ten previously reported derived indexes related to HCC, the index GPR, the ratio of γ-glutamyltransferase (GGT) to platelet (PLT), showed the best performance in distinguishing aHCC from aBFHL with the area under ROC curve (AUROC) of 0.853 (95% CI 0.814-0.892), but the other indexes were of little value (AUROCs from 0.531 to 0.700). A new derived index, sAGP [(standardized AFP + standardized GGT)/standardized PLT], was developed and exhibited AUROCs of 0.905, 0.894, 0.891, 0.925, and 0.862 in differentiating overall, BCLC stage 0/A, TNM stage I, small, and AFP-negative aHCC from aBFHL, respectively. Conclusion: The sAGP index is an efficient, simple, and practical metric for the non-invasive differentiation of aHCC from aBFHL.

Rapid Visual LAMP Method for Detection of Genetically Modified Organisms.

We developed a novel loop-mediated isothermal amplification (LAMP) method using DNA captured on polyacrylamide microparticles (PAMMPs) as templates (PAMMPs@DNA-LAMP) for rapid qualitative detection of genetically modified organisms (GMOs). Here, DNA was extracted by a fast and cost-effective method using PAMMPs. Four LAMP primers were designed for the PAMMPs@DNA-LAMP method to detect the cauliflower mosaic virus 35S (CaMV35S) promotor in GMOs. We thus developed this method for rapid extraction of DNA (5-10 min) and fast amplification of DNA within ∼30 min at a constant temperature of 63 °C. Moreover, the DNA captured by PAMMPs (PAMMPs@DNA) could be effectively detected by both conventional and quantitative PCR (qPCR) and LAMP. The PAMMPs@DNA-LAMP method was validated with high specificity, sensitivity, and performance for practical sample analysis. This assay detected 0.01% target sequences, which had a high specificity like qPCR and better than the conventional PCR (cPCR). Furthermore, PAMMPs@DNA-LAMP was successfully used to extract and detect DNA from food samples of the major crops (soybean, maize, rice, etc.). In summary, a novel PAMMPs@DNA-LAMP assay has been developed, which has higher sensitivity and spends less time than the cPCR detection using the conventional DNA extracted process. This method offers a novel approach for rapid detection of GMOs in the field.

A lightweight dual-path cascaded network for vessel segmentation in fundus image.

Automatic and fast segmentation of retinal vessels in fundus images is a prerequisite in clinical ophthalmic diseases; however, the high model complexity and low segmentation accuracy still limit its application. This paper proposes a lightweight dual-path cascaded network (LDPC-Net) for automatic and fast vessel segmentation. We designed a dual-path cascaded network via two U-shaped structures. Firstly, we employed a structured discarding (SD) convolution module to alleviate the over-fitting problem in both codec parts. Secondly, we introduced the depthwise separable convolution (DSC) technique to reduce the parameter amount of the model. Thirdly, a residual atrous spatial pyramid pooling (ResASPP) model is constructed in the connection layer to aggregate multi-scale information effectively. Finally, we performed comparative experiments on three public datasets. Experimental results show that the proposed method achieved superior performance on the accuracy, connectivity, and parameter quantity, thus proving that it can be a promising lightweight assisted tool for ophthalmic diseases.

MIC-Net: multi-scale integrated context network for automatic retinal vessel segmentation in fundus image.

PURPOSE: Accurate retinal vessel segmentation is of great value in the auxiliary screening of various diseases. However, due to the low contrast between the ends of the branches of the fundus blood vessels and the background, and the variable morphology of the optic disc and cup in the retinal image, the task of high-precision retinal blood vessel segmentation still faces difficulties. METHOD: This paper proposes a multi-scale integrated context network, MIC-Net, which fully fuses the encoder-decoder features, and extracts multi-scale information. First, a hybrid stride sampling (HSS) block was designed in the encoder to minimize the loss of helpful information caused by the downsampling operation. Second, a dense hybrid dilated convolution (DHDC) was employed in the connection layer. On the premise of preserving feature resolution, it can perceive richer contextual information. Third, a squeeze-and-excitation with residual connections (SERC) was introduced in the decoder to adjust the channel attention adaptively. Finally, we utilized a multi-layer feature fusion mechanism in the skip connection part, which enables the network to consider both low-level details and high-level semantic information. RESULTS: We evaluated the proposed method on three public datasets DRIVE, STARE and CHASE. In the experimental results, the Area under the receiver operating characteristic (ROC) and the accuracy rate (Acc) achieved high performances of 98.62%/97.02%, 98.60%/97.76% and 98.73%/97.38%, respectively. CONCLUSIONS: Experimental results show that the proposed method can obtain comparable segmentation performance compared with the state-of-the-art (SOTA) methods. Specifically, the proposed method can effectively reduce the small blood vessel segmentation error, thus proving it a promising tool for auxiliary diagnosis of ophthalmic diseases.

Multi-scale attention and deep supervision-based 3D UNet for automatic liver segmentation from CT.

BACKGROUND: Automatic liver segmentation is a prerequisite for hepatoma treatment; however, the low accuracy and stability hinder its clinical application. To alleviate this limitation, we deeply mine the context information of different scales and combine it with deep supervision to improve the accuracy of liver segmentation in this paper. METHODS: We proposed a new network called MAD-UNet for automatic liver segmentation from CT. It is grounded in the 3D UNet and leverages multi-scale attention and deep supervision mechanisms. In the encoder, the downsampling pooling in 3D UNet is replaced by convolution to alleviate the loss of feature information. Meanwhile, the residual module is introduced to avoid gradient vanishment. Besides, we use the long-short skip connections (LSSC) to replace the ordinary skip connections to preserve more edge detail. In the decoder, the features of different scales are aggregated, and the attention module is employed to capture the spatial context information. Moreover, we utilized the deep supervision mechanism to improve the learning ability on deep and shallow information. RESULTS: We evaluated the proposed method on three public datasets, including, LiTS17, SLiver07, and 3DIRCADb, and obtained Dice scores of 0.9727, 0.9752, and 0.9691 for liver segmentation, respectively, which outperform the other state-of-the-art (SOTA) methods. CONCLUSIONS: Both qualitative and quantitative experimental results demonstrate that the proposed method can make full use of the feature information of different stages while enhancing spatial data's learning ability, thereby achieving high liver segmentation accuracy. Thus, it proved to be a promising tool for automatic liver segmentation in clinical assistance.

Ferroptosis assassinates tumor.

In 2020, nearly 20 million peoples got cancer and nearly 10 million peoples died of cancer, indicating the cancer remains a great threat to human health and life. New therapies are still in urgent demand. We here develop a novel cancer therapy named Ferroptosis ASsassinates Tumor (FAST) by combining iron oxide nanoparticles with cancer-selective knockdown of seven key ferroptosis-resistant genes (FPN, LCN2, FTH1, FSP1, GPX4, SLC7A11, NRF2). We found that FAST had notable anti-tumor activity in a variety of cancer cells but little effect on normal cells. Especially, FAST eradicated three different types of tumors (leukemia, colon cancer, and lung metastatic melanoma) from over 50% of cancer mice, making the mice survive up to 250 days without tumor relapse. FAST also significantly inhibited and prevented the growth of spontaneous breast cancer and improved survival in mice. FAST showed high pan anti-tumor efficacy, high cancer specificity, and in vivo safety. FAST defines a new form of advanced nanomaterials, advanced combinatorial nanomaterials, by combining two kinds of nanomaterials, a chemical nanomaterial (iron oxide nanoparticles) and a biochemical nanomaterial (adeno-associated virus), which successfully turns a general iron nanomaterial into an unprecedented assassin to cancer.

Alterations in Plasma Lipidomic Profiles in Adult Patients with Schizophrenia and Major Depressive Disorder.

Background and Objectives: Lipidomics is a pivotal tool for investigating the pathogenesis of mental disorders. However, studies qualitatively and quantitatively analyzing peripheral lipids in adult patients with schizophrenia (SCZ) and major depressive disorder (MDD) are limited. Moreover, there are no studies comparing the lipid profiles in these patient populations. Materials and Method: Lipidomic data for plasma samples from sex- and age-matched patients with SCZ or MDD and healthy controls (HC) were obtained and analyzed by liquid chromatography-mass spectrometry (LC-MS). Results: We observed changes in lipid composition in patients with MDD and SCZ, with more significant alterations in those with SCZ. In addition, a potential diagnostic panel comprising 103 lipid species and another diagnostic panel comprising 111 lipid species could distinguish SCZ from HC (AUC = 0.953) or SCZ from MDD (AUC = 0.920) were identified, respectively. Conclusions: This study provides an increased understanding of dysfunctional lipid composition in the plasma of adult patients with SCZ or MDD, which may lay the foundation for identifying novel clinical diagnostic methods for these disorders.

Deep supervision and atrous inception-based U-Net combining CRF for automatic liver segmentation from CT.

Due to low contrast and the blurred boundary between liver tissue and neighboring organs sharing similar intensity values, the problem of liver segmentation from CT images has not yet achieved satisfactory performance and remains a challenge. To alleviate these problems, we introduce deep supervision (DS) and atrous inception (AI) technologies with conditional random field (CRF) and propose three major improvements that are experimentally shown to have substantive and practical value. First, we replace the encoder's standard convolution with the residual block. Residual blocks can increase the depth of the network. Second, we provide an AI module to connect the encoder and decoder. AI allows us to obtain multi-scale features. Third, we incorporate the DS mechanism into the decoder. This helps to make full use of information of the shallow layers. In addition, we employ the Tversky loss function to balance the segmented and non-segmented regions and perform further refinement with a dense CRF. Finally, we extensively validate the proposed method on three public databases: LiTS17, 3DIRCADb, and SLiver07. Compared to the state-of-the-art methods, the proposed method achieved increased segmentation accuracy for the livers with low contrast and the fuzzy boundary between liver tissue and neighboring organs and is, therefore, more suited for automatic segmentation of these livers.

Circulating tumor DNA integrating tissue clonality detects minimal residual disease in resectable non-small-cell lung cancer.

BACKGROUND: Circulating tumor DNA (ctDNA) has been proven as a marker for detecting minimal residual diseases following systemic therapies in mid-to-late-stage non-small-cell lung cancers (NSCLCs) by multiple studies. However, fewer studies cast light on ctDNA-based MRD monitoring in early-to-mid-stage NSCLCs that received surgical resection as the standard of care. METHODS: We prospectively recruited 128 patients with stage I-III NSCLCs who received curative surgical resections in our Lung Cancer Tempo-spatial Heterogeneity prospective cohort. Plasma samples were collected before the surgery, 7 days after the surgery, and every 3 months thereafter. Targeted sequencing was performed on a total of 628 plasma samples and 645 matched tumor samples using a panel covering 425 cancer-associated genes. Tissue clonal phylogeny of each patient was reconstructed and used to guide ctDNA detection. RESULTS: The results demonstrated that ctDNA was more frequently detected in patients with higher stage diseases pre- and postsurgery. Positive ctDNA detection at as early as 7 days postsurgery identified high-risk patients with recurrence (HR = 3.90, P < 0.001). Our results also show that longitudinal ctDNA monitoring of at least two postsurgical time points indicated a significantly higher risk (HR = 7.59, P < 0.001), preceding radiographic relapse in 73.5% of patients by a median of 145 days. Further, clonal ctDNA mutations indicated a high-level specificity, and subclonal mutations informed the origin of tumor recurrence. CONCLUSIONS: Longitudinal ctDNA surveillance integrating clonality information may stratify high-risk patients with disease recurrence and infer the evolutionary origin of ctDNA mutations.

Cancer-associated fibroblast-specific lncRNA LINC01614 enhances glutamine uptake in lung adenocarcinoma.

BACKGROUND: Besides featured glucose consumption, recent studies reveal that cancer cells might prefer "addicting" specific energy substrates from the tumor microenvironment (TME); however, the underlying mechanisms remain unclear. METHODS: Fibroblast-specific long noncoding RNAs were screened using RNA-seq data of our NJLCC cohort, TCGA, and CCLE datasets. The expression and package of LINC01614 into exosomes were identified using flow cytometric sorting, fluorescence in situ hybridization (FISH), and quantitative reverse transcription polymerase chain reaction (RT-PCR). The transfer and functional role of LINC01614 in lung adenocarcinoma (LUAD) and CAFs were investigated using 4-thiouracil-labeled RNA transfer and gain- and loss-of-function approaches. RNA pull-down, RNA immunoprecipitation, dual-luciferase assay, gene expression microarray, and bioinformatics analysis were performed to investigate the underlying mechanisms involved. RESULTS: We demonstrate that cancer-associated fibroblasts (CAFs) in LUAD primarily enhance the glutamine metabolism of cancer cells. A CAF-specific long noncoding RNA, LINC01614, packaged by CAF-derived exosomes, mediates the enhancement of glutamine uptake in LUAD cells. Mechanistically, LINC01614 directly interacts with ANXA2 and p65 to facilitate the activation of NF-κB, which leads to the upregulation of the glutamine transporters SLC38A2 and SLC7A5 and eventually enhances the glutamine influx of cancer cells. Reciprocally, tumor-derived proinflammatory cytokines upregulate LINC01614 in CAFs, constituting a feedforward loop between CAFs and cancer cells. Blocking exosome-transmitted LINC01614 inhibits glutamine addiction and LUAD growth in vivo. Clinically, LINC01614 expression in CAFs is associated with the glutamine influx and poor prognosis of patients with LUAD. CONCLUSION: Our study highlights the therapeutic potential of targeting a CAF-specific lncRNA to inhibit glutamine utilization and cancer progression in LUAD.

Current and Future Perspectives of Cell-Free DNA in Liquid Biopsy.

A liquid biopsy is a minimally invasive or non-invasive method to analyze a range of tumor material in blood or other body fluids, including circulating tumor cells (CTCs), cell-free DNA (cfDNA), messenger RNA (mRNA), microRNA (miRNA), and exosomes, which is a very promising technology. Among these cancer biomarkers, plasma cfDNA is the most widely used in clinical practice. Compared with a tissue biopsy of traditional cancer diagnosis, in assessing tumor heterogeneity, a liquid biopsy is more reliable because all tumor sites release cfDNA into the blood. Therefore, a cfDNA liquid biopsy is less invasive and comprehensive. Moreover, the development of next-generation sequencing technology makes cfDNA sequencing more sensitive than a tissue biopsy, with higher clinical applicability and wider application. In this publication, we aim to review the latest perspectives of cfDNA liquid biopsy clinical significance and application in cancer diagnosis, treatment, and prognosis. We introduce the sequencing techniques and challenges of cfDNA detection, analysis, and clinical applications, and discuss future research directions.

Automatic Liver Segmentation Using EfficientNet and Attention-Based Residual U-Net in CT.

This paper proposes a new network framework, which leverages EfficientNetB4, attention gate, and residual learning techniques to achieve automatic and accurate liver segmentation. First, we use EfficientNetB4 as the encoder to extract more feature information during the encoding stage. Then, an attention gate is introduced in the skip connection to eliminate irrelevant regions and highlight features of a specific segmentation task. Finally, to alleviate the problem of gradient vanishment, we replace the traditional convolution of the decoder with a residual block to improve the segmentation accuracy. We verified the proposed method on the LiTS17 and SLiver07 datasets and compared it with classical networks such as FCN, U-Net, attention U-Net, and attention Res-U-Net. In the Sliver07 evaluation, the proposed method achieved the best segmentation performance on all five standard metrics. Meanwhile, in the LiTS17 assessment, the best performance is obtained except for a slight inferior on RVD. The proposed method's qualitative and quantitative results demonstrated its applicability in liver segmentation and proved its good prospect in computer-assisted liver segmentation.

An AAV-Based NF-κB-Targeting Gene Therapy (rAAV-DMP-miR533) to Inflammatory Diseases.

Background: The inflammatory diseases pose a great threat to human health. Variant anti-inflammatory agents have been therefore developed. However, the current anti-inflammatory drugs are still challenged by low response and side effects. There remain great unmet treatments to inflammatory diseases. Methods: In this work, we fabricate a recombinant adeno-associated virus (rAAV), rAAV-DMP-miR533, by packaging a DNA molecule DMP-miR533 into AAV, in which DMP is a NF-κB-activatable promoter composed of a NF-κB decoy and a minimal promoter and miR533 codes an artificial microRNA targeting NF-κB RELA. We evaluate the in vitro and in vivo anti-inflammatory effect of the virus with inflammatory cells and the mice of three typical inflammatory diseases including the dextran sulphate sodium-induced acute colitis, imiquimod-induced psoriasis, and collagen-induced arthritis. Results: We found that rAAV-DMP-miR533 had marked anti-inflammatory effect in both cells and mice. In addition, rAAV-DMP-miR533 showed biosafety in mice. Conclusion: This study thus provides a promising gene therapy to variant inflammatory diseases by directly targeting NF-κB, an established hub regulator of inflammation.

An improved residual U-Net with morphological-based loss function for automatic liver segmentation in computed tomography.

This paper proposes an improved ResU-Net framework for automatic liver CT segmentation. By employing a new loss function and data augmentation strategy, the accuracy of liver segmentation is improved, and the performance is verified on two public datasets LiTS17 and SLiver07. Firstly, to speed up the convergence of the model, the residual module is used to replace the original convolution module of U-Net. Secondly, to suppress the problem of pixel imbalance, the opposite number of Dice is proposed to replace the cross-entropy loss function, and the morphological method is introduced to weigh the pixels. Finally, to improve the generalization ability of the model, random affine transformation and random elastic deformation are employed for data augmentation. From 20 training datasets of Sliver07, 16 sets were selected as the training set, two sets were used for verification, and two sets were used for the test; meanwhile, from 131 training datasets of LiTS2017, eight sets were selected as the test set. In the experiment, four evaluation metrics, including DICE global, DICE per case, VOE, and RVD, were calculated, with the accuracies of 94.28, 94.24 ± 2.07, 10.83 ± 3.70, and -0.25 ± 2.74, respectively. Compared with U-Net and ResU-Net, the performance of the proposed method is significantly improved. The experimental results show that, although the method's complexity is high, it has a faster convergence speed and stronger generalization ability. The segmentation effect on the 2D image is significantly improved, and the scalability on 3D data is also robust. In addition, the proposed method performs well in the case of low-contrast neighboring organs, which proves the robustness of the proposed method.

Erratum: A New Tool for CRISPR-Cas13a-BasedCancer Gene Therapy.

[This corrects the article DOI: 10.1016/j.omto.2020.09.004.].

Gene interfered-ferroptosis therapy for cancers.

Although some effective therapies have been available for cancer, it still poses a great threat to human health and life due to its drug resistance and low response in patients. Here, we develop a ferroptosis-based therapy by combining iron nanoparticles and cancer-specific gene interference. The expression of two iron metabolic genes (FPN and LCN2) was selectively knocked down in cancer cells by Cas13a or microRNA controlled by a NF-κB-specific promoter. Cells were simultaneously treated by iron nanoparticles. As a result, a significant ferroptosis was induced in a wide variety of cancer cells. However, the same treatment had little effect on normal cells. By transferring genes with adeno-associated virus and iron nanoparticles, the significant tumor growth inhibition and durable cure were obtained in mice with the therapy. In this work, we thus show a cancer therapy based on gene interference-enhanced ferroptosis.

SERR-U-Net: Squeeze-and-Excitation Residual and Recurrent Block-Based U-Net for Automatic Vessel Segmentation in Retinal Image.

METHODS: A new SERR-U-Net framework for retinal vessel segmentation is proposed, which leverages technologies including Squeeze-and-Excitation (SE), residual module, and recurrent block. First, the convolution layers of encoder and decoder are modified on the basis of U-Net, and the recurrent block is used to increase the network depth. Second, the residual module is utilized to alleviate the vanishing gradient problem. Finally, to derive more specific vascular features, we employed the SE structure to introduce attention mechanism into the U-shaped network. In addition, enhanced super-resolution generative adversarial networks (ESRGANs) are also deployed to remove the noise of retinal image. RESULTS: The effectiveness of this method was tested on two public datasets, DRIVE and STARE. In the experiment of DRIVE dataset, the accuracy and AUC (area under the curve) of our method were 0.9552 and 0.9784, respectively, and for SATRE dataset, 0.9796 and 0.9859 were achieved, respectively, which proved a high accuracy and promising prospect on clinical assistance. CONCLUSION: An improved U-Net network combining SE, ResNet, and recurrent technologies is developed for automatic vessel segmentation from retinal image. This new model enables an improvement on the accuracy compared to learning-based methods, and its robustness in circumvent challenging cases such as small blood vessels and intersection of vessels is also well demonstrated and validated.

SAR-U-Net: Squeeze-and-excitation block and atrous spatial pyramid pooling based residual U-Net for automatic liver segmentation in Computed Tomography.

BACKGROUND AND OBJECTIVE: Liver segmentation is an essential prerequisite for liver cancer diagnosis and surgical planning. Traditionally, liver contour is delineated manually by radiologist in a slice-by-slice fashion. However, this process is time-consuming and prone to errors depending on radiologist's experience. In this paper, a modified U-Net based framework is presented, which leverages techniques from Squeeze-and-Excitation (SE) block, Atrous Spatial Pyramid Pooling (ASPP) and residual learning for accurate and robust liver Computed Tomography (CT) segmentation, and the effectiveness of the proposed method was tested on two public datasets LiTS17 and SLiver07. METHODS: A new network architecture, called SAR-U-Net was designed, which is grounded in the classical U-Net. Firstly, the SE block is introduced to adaptively extract image features after each convolution in the U-Net encoder, while suppressing irrelevant regions, and highlighting features of specific segmentation task; Secondly, the ASPP is employed to replace the transition layer and the output layer, and acquire multi-scale image information via different receptive fields. Thirdly, to alleviate the gradient vanishment problem, the traditional convolution block is replaced with the residual structures, and thus prompt the network to gain accuracy from considerably increased depth. RESULTS: In the LiTS17 database experiment, five popular metrics were used for evaluation, including Dice coefficient, VOE, RVD, ASD and MSD. Compared with other closely related models, the proposed method achieved the highest accuracy. In addition, in the experiment of the SLiver07 dataset, compared with other closely related models, the proposed method achieved the highest segmentation accuracy except for the RVD. CONCLUSION: An improved U-Net network combining SE, ASPP, and residual structures is developed for automatic liver segmentation from CT images. This new model shows a great improvement on the accuracy compared to other closely related models, and its robustness to challenging problems, including small liver regions, discontinuous liver regions, and fuzzy liver boundaries, is also well demonstrated and validated.

Microbiologically influenced corrosion inhibition mechanisms in corrosion protection: A review.

Microbial activities can change the properties of biofilm/metal interfaces to accelerate or decelerate the corrosion of metals in a given environment. Microbiologically influenced corrosion inhibition (MICI) is the inhibition of corrosion that is directly or indirectly induced by microbial action. Compared with conventional methods for protection from corrosion, MICI is environmentally friendly and an emerging approach for the prevention and treatment of (bio)corrosion. However, due to the diversity of microorganisms and the fact that their metabolic processes are greatly complicated by environmental factors, MICI is still facing challenges for practical application. This review provides a comprehensive overview of the mechanisms of MICI under different conditions and their advantages and disadvantages for potential applications in corrosion protection.