Search

BACKGROUND: To use adversarial training to increase the generalizability and diagnostic accuracy of deep learning models for prostate cancer diagnosis. METHODS: This multicenter study retrospectively included 396 prostate cancer patients who underwent magnetic resonance imaging (development set, 297 patients from Shanghai Jiao Tong University Affiliated Sixth People’s Hospital and Eighth People’s Hospital; test set, 99 patients from Renmin Hospital of Wuhan University). Two binary classification deep learning models for clinically significant prostate cancer classification [PM1, pretraining Visual Geometry Group network (VGGNet)-16-based model 1; PM2, pretraining residual network (ResNet)-50-based model 2] and two multiclass classification deep learning models for prostate cancer grading (PM3, pretraining VGGNet-16-based model 3; PM4: pretraining ResNet-50-based model 4) were built using apparent diffusion coefficient and T2-weighted images. These models were then retrained with adversarial examples starting from the initial random model parameters (AM1, adversarial training VGGNet-16 model 1; AM2, adversarial training ResNet-50 model 2; AM3, adversarial training VGGNet-16 model 3; AM4, adversarial training ResNet-50 model 4, respectively). To verify whether adversarial training can improve the diagnostic model’s effectiveness, we compared the diagnostic performance of the deep learning methods before and after adversarial training. Receiver operating characteristic curve analysis was performed to evaluate significant prostate cancer classification models. Differences in areas under the curve (AUCs) were compared using Delong’s tests. The quadratic weighted kappa score was used to verify the PCa grading models. RESULTS: AM1 and AM2 had significantly higher AUCs than PM1 and PM2 in the internal validation dataset (0.84 vs. 0.89 and 0.83 vs. 0.87) and test dataset (0.73 vs. 0.86 and 0.72 vs. 0.82). AM3 and AM4 showed higher κ values than PM3 and PM4 in the internal validation dataset {0.266 [95% confidence interval (CI): 0.152–0.379] vs. 0.292 (95% CI: 0.178–0.405) and 0.254 (95% CI: 0.159–0.390) vs. 0.279 (95% CI: 0.163−0.396)} and test set [0.196 (95% CI: 0.029–0.362) vs. 0.268 (95% CI: 0.109–0.427) and 0.183 (95% CI: 0.015–0.351) vs. 0.228 (95% CI: 0.068−0.389)]. CONCLUSIONS: Using adversarial examples to train prostate cancer classification deep learning models can improve their generalizability and classification abilities.

Gastrointestinal (GI) cancers are among the most common cancer types and leading causes of cancer-related deaths worldwide. There is a tremendous clinical need for effective early diagnosis for better healthcare of GI cancer patients. In this article, we provide a short overview of the recent advances in GI cancer diagnosis. In the first part, we discuss the applications of blood-based biomarkers, such as plasma circulating cell-free DNA, circulating tumor cells, extracellular vesicles, and circulating cell-free RNA, for cancer liquid biopsies. In the second part, we review the current trends of artificial intelligence (AI) for pathology image and tissue biopsy analysis for GI cancer, as well as deep learning-based approaches for purity assessment of tissue biopsies. We further provide our opinions on the future directions in blood-based and AI-enhanced approaches for GI cancer diagnosis, and we think that these fields will have more intensive integrations with clinical needs in the near future.

Background Accumulating evidence demonstrated that long noncoding RNAs (lncRNAs) played important regulatory roles in many cancer types. However, the role of lncRNAs in gastric cancer (GC) progression remains unclear. Methods RT-qPCR assay was performed to detect the expression of HNF1A-AS1 in gastric cancer tissues and the non-tumourous gastric mucosa. Overexpression and RNA interference approaches were used to investigate the effects of HNF1A-AS1 on GC cells. Insight into competitive endogenous RNA (ceRNA) mechanisms was gained via bioinformatics analysis, luciferase assays and an RNA-binding protein immunoprecipitation (RIP) assay, RNA-FISH co-localisation analysis combined with microRNA (miRNA)-pulldown assay. Results This study displayed that revealed expression of HNF1A-AS1 was associated with positive lymph node metastasis in GC. Moreover, HNF1A-AS1 significantly promoted gastric cancer invasion, metastasis, angiogenesis and lymphangiogenesis in vitro and in vivo. In addition, HNF1A-AS1 was demonstrated to function as a ceRNA for miR-30b-3p. HNF1A-AS1 abolished the function of the miRNA-30b-3p and resulted in the derepression of its target, PIK3CD, which is a core oncogene involved in the progression of GC. Conclusion This study demonstrated that HNF1A-AS1 worked as a ceRNA and promoted PI3K/AKT signalling pathway-mediated GC metastasis by sponging miR-30b-3p, offering novel insights of the metastasis mechanism in GC.

Background Accumulating evidence indicates that the crosstalk between tumor cells and the microenvironment influences human cancer progression. However, the expression pattern, function role in the crosstalk between tumor cells and tumor microenvironment, and underlying mechanism of lncRNAs-related tumorigenesis in breast cancer are unknown. Methods The expression lncRNA-THAP7-AS1 in breast cancer (BC) were identified by in BC tissues. The functional roles of THAP7-AS1 were confirmed by in vitro and in vivo experiments. RNA-pulldown followed by mass spectrometry, RNA Immunoprecipitation (RIP), chromatin immunoprecipitation (ChIP) assays and luciferase reporter assay revealed the mechanisms of THAP7-AS1 in BC. RT-qPCR, ELISA assays, Flow cytometry, ChIP assays and luciferase reporter assay elucidated the crosstalk between tumor cells and (tumor-associated macrophages) TAMs. Results Here, we demonstrate that long non-coding RNA (lncRNA) THAP7-AS1 induces polarization of macrophages to the M2 phenotype in an IL-4-dependent manner, and M2 tumor-associated macrophages (TAMs) secreted IL-10, which then facilitates the progression of breast cancer (BC). Mechanistically, THAP7-AS1 promoted the combination between SNF2H, SNF2L, and BAF155 and recruited the SWI/SNF complex to the promoter of EGFR to upregulate its expression, and then induced IL-4-mediated M2 polarization of macrophages via activation of the EGFR-ELK1 signaling. Reciprocally, IL-10 released from M2 TAMs upregulates CEBP-β-dependent P300 expression, and then P300, synergistically worked with c-MYC and upregulated THAP7-AS1 expression in BC cells, which constituting a feed-forward loop between tumor cells and TAMs. Moreover, THAP7-AS1 knockdown inhibits the invasion, metastasis and M2 macrophage polarization of breast cancer in vivo. Conclusions Our study highlights the role of THAP7-AS1 in the regulation crosstalk between TAM and tumor cells in BC progression and may provide a novel therapeutic target for BC treatment.

KIF26B is a member of the kinesin superfamily that is up-regulated in various tumors, including breast cancer (BC), which can promote tumor progression. This study aimed to investigate the potential function of KIF26B in BC, and the underlying mechanisms, focusing mainly on cell proliferation. KIF26B expression was examined in BC tissue samples obtained from 99 patients. Then, we performed MTS, EdU and flow cytometry assays to detect cell proliferation, and western blotting to measure the expression of cell cycle-related proteins in MDA-MB-231 and MDA-MB-468 cells following KIF26B knockdown. Promoter analysis was used to study the upstream regulatory mechanism of KIF26B. KIF26B was upregulated in BC tissues. High expression of KIF26B was associated with clinicopathological parameters, such as positive lymph node metastasis, higher tumor grade, and higher proliferative index in BC. Furthermore, knockdown of KIF26B expression inhibited MDA-MB-231 and MDA-MB-468 cell proliferation, arresting cells in the G1 phase of the cell cycle in vitro. Similarly, KIF26B silencing decreased the expression levels of Wnt, β-catenin, and cell cycle-related proteins such as c-Myc, cyclin D1, and cyclin-dependent kinase 4, while increasing the expression of p27. Moreover, ELK1 could bind to the core promoter region of KIF26B and activate its transcription. KIF26B acts as an oncogene in BC by regulating multiple proteins involved in the cell cycle. ELK1 activates KIF26B transcription.

Session Initiation Protocol (SIP) is the most widely used signalling protocol for controlling communication, establishing, maintaining, and terminating sessions on the Internet. However, since sensitive information is often transmitted through open channels, a security authentication scheme is essential. Recently, Islam et al. proposed an authentication scheme for SIP, and argued that the scheme is immune to known attacks. However, we discover that their scheme fails to achieve user anonymity, and it cannot even resist impersonation attack. Therefore, this study proposes an enhanced mutual authentication scheme to eliminate the drawbacks of the scheme proposed by Islam et al. In addition, our proposed scheme is based on extended chaotic map, which avoids computationally expensive elliptic curve point multiplication. Then, we use Burrows-Abadi-Needham logic to prove that the proposed scheme achieves secure mutual authentication, and we use the Real-Or-Random model to analyze the formal security verification of the session key. Finally, we compare the performance and the security features of the proposed scheme with some existing schemes. Therefore, we provide better safety and efficiency than related schemes and the proposed scheme is suitable for SIP.

A basic but expensive operation in the implementations of several famous public-key cryptosystems is the computation of the multi-scalar multiplication in a certain finite additive group defined by an elliptic curve. We propose an adaptive window method for the multi-scalar multiplication, which aims to balance the computation cost and the memory cost under register-constrained environments. That is, our method can maximize the computation efficiency of multi-scalar multiplication according to any small, fixed number of registers provided by electronic devices. We further demonstrate that our method is efficient when five registers are available. Our method is further studied in detail in the case where it is combined with the non-adjacent form (NAF) representation and the joint sparse form (JSF) representation. One efficiency result is that our method with the proposed improved NAF n-bit representation on average requires 209n/432 point additions. To the best of our knowledge, this efficiency result is optimal compared with those of similar methods using five registers. Unlike the previous window methods, which store all possible values in the window, our method stores those with comparatively high probabilities to reduce the number of required registers.

Long noncoding RNAs (lncRNAs) are dysregulated in different cancer types, and thus have emerged as important regulators of the initiation and progression of human cancers. However, the biological functions and the underlying mechanisms responsible for their functions in gastric cancer (GC) remain poorly understood. Here, by lncRNA microarray, we identified 1414 differentially expressed lncRNAs, among which THAP7-AS1 was significantly upregulated in GC tissues compared with non-tumorous gastric tissues. High expression of THAP7-AS1 was correlated with positive lymph node metastasis and poorer prognosis. SP1, a transcription factor, could bind directly to the THAP7-AS1 promoter region and activate its transcription. Moreover, the m(6)A modification of THAP7-AS1 by METTL3 enhanced its expression depending on the “reader” protein IGF2BP1-dependent pathway. THAP7-AS1 promoted GC cell progression. Mechanistically, THAP7-AS1 interacted with the 1-50 Amino Acid Region (nuclear localization signal) of CUL4B through its 1-442 nt Sequence, and it promoted interaction between nuclear localization signal (NLS) and importin α1, and improved the CUL4B protein entry into the nucleus, repressing miR-22-3p and miR-320a expression by CUL4B-catalyzed H2AK119ub1 and the EZH2-mediated H3K27me3, subsequently activating PI3K/AKT signaling pathway to promote GC progression. Moreover, LV-sh-THAP7-AS1 treatment could suppress GC growth, invasion and metastasis, indicating that THAP7-AS1 may act as a promising molecular target for GC therapies. Taken together, our results show that THAP7-AS1, transcriptionally activated by SP1 and then modified by METTL3-mediated m6A, exerts oncogenic functions, by promoting interaction between NLS and importin α1 and then improving the CUL4B protein entry into the nucleus to repress the transcription of miR-22-3p and miR-320a.

Although studies using animal models have demonstrated that nonhemodynamic factors, including inflammatory cells and cytokines, contribute to left ventricular hypertrophy (LVH), there is little clinical data to confirm this association. Therefore in the present study, levels of circulating specific types of leukocyte were measured to determine the association between white blood cells and left ventricular mass index (LVMI) in hypertensive patients undergoing anti-hypertensive drug therapy. A total of 144 consecutive hypertensive patients taking anti-hypertensive drug therapy were enrolled in the current study. Subjects were divided into two groups: Those with normal geometry and those with left LVH. Total white blood cells and differentiated subtypes (neutrophils, lymphocytes, monocytes) were counted, and left ventricular end-diastolic diameter, left ventricular posterior wall thickness in diastole and inter-ventricular septal wall thickness in diastole were all measured. Analysis revealed a significant correlation between LVMI and total white blood cell levels (P=0.013). The percentage of LVH in the highest tertile of WBC was increased compared with the middle tertile (P=0.008). Furthermore, a significant correlation between the highest tertile of neutrophil counts and LVH was observed (P=0.039). However, no significant associations between LVMI and monocyte or lymphocyte counts were detected. Therefore, the current study determined that increased total white blood cell and neutrophil subtype counts were associated with LVMI in hypertensive patients undergoing anti-hypertensive drug therapy. They may provide convenient and useful markers for further risk appraisal of LVH caused by nonhemodynamic factors of hypertension.

The protocadherin 7 is a member of the protocadherin family that expressed aberrantly in many types of human cancers. However, its expression, function, and underlying mechanisms are little known in gastric cancer. In this study, we detected protocadherin 7 expression in gastric cancer tissues and non-tumorous gastric mucosa tissues by real-time quantitative polymerase chain reaction and immunohistochemistry. The association of protocadherin 7 expression with the clinicopathological characteristics and the prognosis was subsequently analyzed. MTS ((3-(4,5-dimethylthiazol-2-yl)-5-(3-carboxymethoxyphenyl)-2-(4-sulfophenyl)-2H-tetrazolium)) and transwell assays were performed to assess the effect of protocadherin 7 on proliferation, migration, and invasion in gastric cancer cell lines. Moreover, real-time quantitative polymerase chain reaction and western blot were used to detect the expression of epithelial–mesenchymal transition markers. Protocadherin 7 expression was decreased gradiently from normal tissue to gastric cancer, especially in gastric cancer tissue with lymph node metastasis. Low expression of protocadherin 7 was significantly associated with Lauren’s classification ( p = 0.0005), lymph node metastases ( p = 0.0002), and tumor node metastasis stage ( p = 0.0221), as well as poor prognosis ( p 0.05). Additionally, our results demonstrated that E-cadherin expression was down-regulated in gastric cancer cells with protocadherin 7 depletion. Our data indicated that protocadherin 7 may play important roles in the invasion and metastasis of gastric cancer, and protocadherin 7 could suppress cell migration and invasion through E-cadherin inhibition. Protocadherin 7 can serve as a novel biomarker for diagnostic and prognosis in patients with gastric cancer.

Transmembrane protease serine 4 (TMPRSS4) is a novel type II transmembrane serine protease that is overexpressed in various types of human cancers and has an important function in cancer progression. However, there is a paucity of data available regarding the biological effects of TMPRSS4 on breast cancer (BC) cells and the underlying mechanisms. In this study, expression of TMPRSS4 in BC tissues was detected by immunohistochemistry. The relationship between TMPRSS4 expression and clinicopathological characteristics as well as prognosis was evaluated. The effects of TMPRSS4 on cell proliferation, migration and invasion were investigated in BC cell lines in vitro. Additionally, RT-qPCR and western blot analysis were used to determine the expressions of epithelial-mesenchymal transition (EMT) biomarkers and TMPRSS4 in BC cell lines. We found that TMPRSS4 was overexpressed in BC tissues and its expression level was closely correlated with tumor size, histological grade, lymph node metastasis, clinical stage as well as poor survival (all P

The role of advanced glycation end products (AGEs) and its C-terminal truncated receptor (soluble receptor for advanced glycation end products, sRAGE) in ST-segment elevation myocardial infarction (STEMI) patients with or without diabetes is unknown. We compared their levels in patients with and without STEMI, as well as with and without diabetes. A prospective observational study was performed between December 2014 and December 2015. Study group included STEMI patients with coronary artery disease; control group included patients without coronary artery disease. Levels of AGEs and sRAGE were tested on Days 0, 2, and 5 after STEMI. Levels of creatine kinase-MB (CK-MB), cardiac troponin I, and N-terminal pro-brain natriuretic peptide (NT-proBNP) were tested on Days 0, 1, 2, and 3. Patient's diabetic status was determined by medical history or oral glucose tolerance test. Compared to patients in the control group, STEMI patients showed elevated levels of AGEs and sRAGE. In the STEMI group, diabetic patients had higher levels of AGEs and sRAGE compared to nondiabetic patients. The level of AGEs correlated with peak level of CK-MB in the overall population of patients with STEMI and with peak level of NT-proBNP in diabetic patients with STEMI. Levels of AGEs and sRAGE were elevated after STEMI, especially among patients with diabetes. These markers could serve to indicate the severity of myocardial injury and cardiac insufficiency, and play a potential role in predicting the prognosis of patients with STEMI.

Background Several studies have indicated that chronic kidney disease is independently associated with the presence of left ventricular hypertrophy ( LVH ). However, little clinical data are currently available regarding the detailed correlation between LVH and renal function in elderly patients with non–end‐stage renal disease. Methods and Results A total of 300 in‐ and outpatients (more than 60 years of age, non‐end‐stage renal disease), 251 with LVH and 49 without LVH , seen at Beijing Friendship Hospital from January 2000 to December 2010 were included in this retrospective study. One observation period of 12 months was used to detect rapid kidney function decline. The evaluations of cardiac structure and function were performed via echocardiography. The multivariable logistic analysis showed patients with LVH had a much higher risk of rapid kidney function decline than those without LVH . Additionally, the baseline left ventricular mass index was 140 (125–160) g/m 2 in the non–chronic kidney disease group, 152 (130–175) g/m 2 in the mild chronic kidney disease group (estimated glomerular filtration rate (eGFR)≥60 ml/min/1.73 m 2 ), and 153 (133–183) g/m 2 in the severe chronic kidney disease group (eGFR2 ), with a significant difference ( P =0.009). Conclusions Our data demonstrate that a high rate of renal function decline contributes to pathological LVH in non–end‐stage renal disease elderly patients and that LVH is positively associated with renal function decline followed by an increased risk of rapid kidney function decline.

To study the use of traditional Chinese medicine (TCM) or both TCM and guideline-recommended Western medicine (WM) in Chinese patients with coronary heart disease (CHD).A cross-sectional nationwide survey of 2803 CHD outpatients was completed by collecting information, including general demographic data, disease history, and use of drugs (including TCM and WM).Of the 2712 CHD outpatients with complete drug treatment data, only 3.1% received TCM without any WM for CHD, 30.0% received both TCM and WM recommended by current CHD guidelines, and 66.9% received only WM. Patients with a longer history of CHD or with a history of stroke, were more likely to use TCM. However, 90.6% of CHD patients who used TCM also used certain WM. Furthermore, patients who used more types of TCM tended to use much less WM recommended by current guidelines.A substantial proportion of Chinese CHD outpatients use both TCM and WM for secondary prevention of CHD. It is important to assess the effect of combined TCM and WM on major clinical outcomes in Chinese CHD patients.