Neural network application in the discrimination of benign from malignant gastric cells

OBJECTIVE: To investigate the potential value of morphometry and neural networks for the discrimination of benign from malignant gastric lesions. STUDY DESIGN: One thousand cells from 19 cases of cancer, 19 cases of gastritis and 56 cases of ulcer were selected as a training set, and an additional 4,000 cells from the same cases of cancer, gastritis and ulcer were used as a test set. Images of routinely processed gastric smears stained by the Papanicolaou technique were analyzed by a custom-made image analysis system. RESULTS: Application of the neural network gave correct classification in 96% of benign cells and 89% of malignant cells. CONCLUSION: The results indicate that the use of neural networks and image morphometry may offer useful information concerning the potential of malignancy in gastric cells.     

Image analysis of low magnification images of fine needle aspirates of the breast produces useful discrimination between benign and malignant cases

Image analysis of low magnification images of fine needle aspirates of the breast produces useful discrimination between benign and malignant cases
Fine needle aspirates of the breast (FNAB) ( n =362; 204 malignant, 158 benign), prepared by cytocentrifuge methods and stained by the Papanicolaou technique, were analysed using a semi‐automated image analysis system at a low magnification which precluded resolution of nuclear detail. The measured parameters were integrated optical density, fractal textural dimension, number of cellular objects (single cells and contiguous groups of cells), distance between cellular objects (mean, s.d., skewness and kurtosis), area of cellular objects (mean, s.d., skewness, kurtosis) and the nearest neighbour statistic. The cases were divided into a 200‐case training set and a 162‐case test set. Analysis was performed by logistic regression and the multi‐layer Perceptron type of artificial neural network. Logistic regression and the neural network produced similar performances with a sensitivity of 82–83%, specificity 85% and a positive predictive value for a malignant result of 85%. A non‐parametric analysis of all the predictor variables showed that all except the mean area of cellular objects and the s.d. of this measurement were significant discriminants ( P <0.05), but most were highly interrelated and this was reflected in the selection of only three predictor variables by forward and backward conditional logistic regression. This study shows that much diagnostic information is present in low power views of FNAB, and that image analysis could form the basis of a semi‐automated decision‐support aid.     

What we have learned from the study of learning in the leech

The use of invertebrate preparations has contributed greatly to our understanding of the neural basis of learning. The leech is especially useful for studying behavioral changes and their underlying neuronal mechanisms. Learning in the leech is essentially identical to that found in other animals, both vertebrate and invertebrate. Using anatomical and physiological techniques on leeches as they learn, we have begun to characterize the properties of individual neurons and neuronal networks that play a role in learning. We have been able to show two neuronal mechanisms that have not been previously associated with associative conditioning. The first has to do with the importance of contingency: one stimulus [the conditional stimulus (CS)] becomes associated with a second stimulus [the unconditional stimulus, (US)] in proportion to the ability of the CS to predict the US. We have found that important properties for encoding predictability, such as circuit reconfiguration, may lie in the US pathway. The firing of the serotonergic Retzius cells is taken as the US; consistent CS prediction of a US prevents “dropout” of a critical component of one US pathway. Throughout training, predicted USs continue to elicit a barrage of action potentials in these cells. Recurring unpredicted USs degrade both the learning and the response of the Retzius cell to the US. A second insight is that at least two US pathways contribute to learning, the Retzius cell pathway and the nociceptive (N) cell pathway. This second pathway persists after the elimination of the Retzius cell pathway. The observation of multiple US pathways raises a host of issues concerning CS–US convergence and the functional significance of distinct US pathways, and our results are discussed in terms of implications to current models of learning. © 1995 John Wiley & Sons, Inc.     

The role of serum pepsinogen and gastrin test for the detection of gastric cancer in Korea

Background and Aim: This study was performed to determine whether serum pepsinogen (PG) and gastrin testing can be used to detect gastric cancer in Korea. Methods: Serum levels of PG I (sPGI) and sPGII, PG I/II ratios, and gastrin levels were measured in 1006 patients with gastroduodenal diseases including cancer. Follow‐up tests were performed 1 year after Helicobacter pylori eradication. Results: sPGI and sPGII levels increased and PG I/II ratios decreased in line with the severity of activity, chronic inflammation, and the presence of H. pylori (p < .01). In contrast, sPGI levels and PG I/II ratios decreased in proportion with the severity of atrophic gastritis (AG)/intestinal metaplasia (p < .01). Gastrin levels were found to be correlated with chronic inflammation negatively in the antrum but positively in the corpus. H. pylori eradication reduced sPGI, sPGII, and gastrin levels, and increased PG I/II ratios to the levels of H. pylori‐negative patients, and was found to be correlated with reductions in activity and chronic inflammation of gastritis. The sensitivity and specificity of a PG I/II ratio of ≤ 3.0 for the detection of dysplasia or cancer were 55.8–62.3% and 61%, respectively. In addition, sPGI and sPGII levels of intestinal‐type cancer were significantly lower than those of the diffuse type, respectively (p = .008 and p = .05, respectively). Gastric cancer risk was highest in the H. pylori‐positive, low PGI/II ratio (≤ 3.0) group with an odds ratio of 5.52 (confidence interval: 2.83–10.77). Conclusion: PG I/II ratio (≤ 3.0) was found to be a reliable marker for the detection of dysplasia or gastric cancer, especially of the intestinal type. This detection power of PG I/II ratio (≤ 3.0) significantly increased in the presence of H. pylori, and thus, provides a means of selecting those at high risk of developing gastric cancer in Korea.     

The effect of Helicobacter pylori infection on levels of DNA damage in gastric epithelial cells

Background. Helicobacter pylori infection leads to an increased risk of developing gastric cancer. The mechanism through which this occurs is not known. We aimed to determine the effect of H. pylori and gastritis on levels of DNA damage in gastric epithelial cells. Methods. Epithelial cells were isolated from antral biopsies from 111 patients. DNA damage was determined using single cell gel electrophoresis and the proportion of cells with damage calculated before and 6 weeks after eradication of H. pylori. Cell suspensions generated by sequential digestions of the same biopsies were assayed to determine the effect of cell position within the gastric pit on DNA damage. Results. DNA damage was significantly higher in normal gastric mucosa than in H. pylori gastritis [median (interquartile range) 65% (58.5–75.8), n = 18 and 21% (11.9–29.8), n = 65, respectively, p < .001]. Intermediate levels were found in reactive gastritis [55.5% (41.3–71.7), n = 13] and H. pylori negative chronic gastritis [50.5% (36.3–60.0), n = 15]. DNA damage rose 6 weeks after successful eradication of H. pylori[to 39.5% (26.3–51.0), p = .007] but was still lower than in normal mucosa. Chronic inflammation was the most important histological factor that determined DNA damage. DNA damage fell with increasing digestion times (r = –.92 and –.88 for normal mucosa and H. pylori gastritis, respectively). Conclusions. Lower levels of DNA damage in cells isolated from H. pylori infected gastric biopsies may be a reflection of increased cell turnover in H. pylori gastritis. The investigation of mature gastric epithelial cells for DNA damage is unlikely to elucidate the mechanisms underlying gastric carcinogenesis.     

低氘环境对胃癌细胞生长影响的体外实验

目的：研究低氘环境对人胃癌细胞（SGC-7901）增殖的影响并初步探讨其相关机制。方法：用含不同氘浓度的蒸馏水（实验组：25 ppm;对照组：150 ppm）配制的RPMI-1640培养基培养胃癌细胞SGC-7901。分别在不同的时间点对两组细胞的增殖率、细胞周期及凋亡情况进行检测,用Western blot法对两组细胞的增殖细胞核抗原蛋白（PCNA）的表达进行检测。结果：低氘环境下SGC-7901细胞的增殖率比对照组低10%左右。低氘环境对细胞的划痕愈合能力及集落形成能力也有显著抑制作用（P<0.05）。流式细胞术检测结果显示,与对照组相比,低氘组的细胞G1期细胞的比例增加（P<0.01）,而其所处S期细胞的比例下降（P<0.05）,两组细胞间早凋及晚凋比率差异无统计学意义。Western blot的结果显示低氘环境下培养的胃癌细胞的PCNA的表达明显下降。结论：低氘环境能够抑制胃癌细胞的生长,这可能与低氘环境下胃癌细胞阻滞于G1期及下调其PCNA的表达有关。     

Expression profile analysis of trichostatin A in human gastric cancer cells

Trichostatin A (TSA) is an inhibitor of histone deacetylase. cDNA microarray analysis was used to identify genes modulated by TSA. A total of 93 genes were up-regulated and 27 genes down-regulated. The expressions of some of these genes were confirmed by RT-PCR analysis.     

A comparative assessment of support vector regression,artificial neural networks,and random forests for predicting and mapping soil organic carbon stocks across an Afromontane landscape

Soil organic carbon (SOC) is a key indicator of ecosystem health, with a great potential to affect climate change. This study aimed to develop, evaluate, and compare the performance of support vector regression (SVR), artificial neural network (ANN), and random forest (RF) models in predicting and mapping SOC stocks in the Eastern Mau Forest Reserve, Kenya. Auxiliary data, including soil sampling, climatic, topographic, and remotely-sensed data were used for model calibration. The calibrated models were applied to create prediction maps of SOC stocks that were validated using independent testing data. The results showed that the models overestimated SOC stocks. Random forest model with a mean error (ME) of −6.5 Mg C ha⁻¹ had the highest tendency for overestimation, while SVR model with an ME of −4.4 Mg C ha⁻¹ had the lowest tendency. Support vector regression model also had the lowest root mean squared error (RMSE) and the highest R² values (14.9 Mg C ha⁻¹ and 0.6, respectively); hence, it was the best method to predict SOC stocks. Artificial neural network predictions followed closely with RMSE, ME, and R² values of 15.5, −4.7, and 0.6, respectively. The three prediction maps broadly depicted similar spatial patterns of SOC stocks, with an increasing gradient of SOC stocks from east to west. The highest stocks were on the forest-dominated western and north-western parts, while the lowest stocks were on the cropland-dominated eastern part. The most important variable for explaining the observed spatial patterns of SOC stocks was total nitrogen concentration. Based on the close performance of SVR and ANN models, we proposed that both models should be calibrated, and then the best result applied for spatial prediction of target soil properties in other contexts.     

Melatonin inhibits the migration of human gastric carcinoma cells at least in part by remodeling tight junction

The recurrence and metastasis is one of the major reasons for malignant tumor treatment failure. Melatonin, a naturally occuring hormone, could reduce the recurrence and metastasis of various tumors. However, the underlying molecular mechanisms of melatonin on tumor metastasis inhibition have not been fully elucidated. In the present study, we explored the impact of melatonin on the migratory capability of human gastric carcinoma cells using wound healing assay, and further investigated if the inhibition on migration ability of melatonin was embodied by relocating tight junction proteins zo-1 and occludin onto the cells surface to remodel tight junction structure. Immunofluorescence assay and Western blot analysis were performed to detect the expression and cell location of the tight junction proteins. The migration distance was decreased as the cells were treated with melatonin. And melatonin increased the membrane location of tight junction proteins, zo-1 and occludin, showed by immunofluorescence staining and Western blot analysis. The results we got show that melatonin makes tight junction proteins anchored more on the cells membrane to remodel cells tight junction, which increase cells adhesion and decrease motility, resulting in the inhibition of gastric cancer cells migration and metastasis ability.     

硫氧还蛋白还原酶1(TrxR1)在胃癌中的表达及对胃癌细胞生长的影响

目的:探讨胃癌组织硫氧还蛋白还原酶1(TrxR1)表达与生存时间的关系及其对胃癌细胞生长的影响。方法:用Real-time PCR法检测76例胃癌组织及癌旁TrxR1 mRNA表达,并分析其与胃癌患者临床病理特征及预后的关系;随机选取3例胃癌组织及癌旁组织,采用免疫组化法、Western blot法检测TrxR1蛋白表达。采用Western blot法和Real-time PCR法检测胃癌细胞系及人胃粘膜上皮细胞中TrxR1的表达。采用小RNA干扰序列(siRNA)处理AGS细胞,根据处理方法不同将AGS细胞分为3组:阴性对照组:转染NC-siRNA、TRXR1 siRNA干扰1组:转染TRXR1-siRNA1、TRXR1 siRNA干扰2组:转染TRXR1-siRNA2。使用Real-time PCR法检测各组AGS细胞中TrxR1 mRNA的表达,克隆形成试验和MTT法检测AGS细胞生长情况。结果:胃癌组织中TrxR1 mRNA和蛋白表达量均显著性上调,TrxR1主要定位于细胞质中。TrxR1高表达与患者TNM分期及淋巴结转移有关,且TrxR1高表达组患者的中位生存时间短于低表达组...     

PKCa translocation from mitochondria to nucleus is closely related to induction of apoptosis in gastric cancer cells

PKCs have been implicated in the regulation of cellular differentiation, proliferation, apoptosis and signal transduction. It was demonstrated in this study that PKCα was located both at mitochondria and in cytosol in gastric cancer cell line BGC-823. Treatment of cells with 12-O-tetradecanoylphorbol-13-acetate (TPA) resulted in the translocation of PKCα from both mitochondria and cytosol to nucleus as clearly shown by laser-scanning-confocal microscopy, while the protein level of PKCα was not changed by TPA treatment as detected by Western blot. The results also revealed that TPA-induced translocation of PKCα was in close association with apoptosis induction, and such association was further affirmed by other experiments where various apoptotic stimuli and specific inhibitors of PKC were used. Taken together, these findings indicate that translocation of PKCα from both mitochondria and cytosol to nucleus in gastric cancer cell is accompanied by induction of apoptosis, and may imply a new mechanism of the potential linking between cell apoptosis and PKCα translocation.     

Sounding out the hidden data: A concise review of deep learning in photoacoustic imaging

The rapidly evolving field of photoacoustic tomography utilizes endogenous chromophores to extract both functional and structural information from deep within tissues. It is this power to perform precise quantitative measurements in vivo—with endogenous or exogenous contrast—that makes photoacoustic tomography highly promising for clinical translation in functional brain imaging, early cancer detection, real-time surgical guidance, and the visualization of dynamic drug responses. Considering photoacoustic tomography has benefited from numerous engineering innovations, it is of no surprise that many of photoacoustic tomography’s current cutting-edge developments incorporate advances from the equally novel field of artificial intelligence. More specifically, alongside the growth and prevalence of graphical processing unit capabilities within recent years has emerged an offshoot of artificial intelligence known as deep learning. Rooted in the solid foundation of signal processing, deep learning typically utilizes a method of optimization known as gradient descent to minimize a loss function and update model parameters. There are already a number of innovative efforts in photoacoustic tomography utilizing deep learning techniques for a variety of purposes, including resolution enhancement, reconstruction artifact removal, undersampling correction, and improved quantification. Most of these efforts have proven to be highly promising in addressing long-standing technical obstacles where traditional solutions either completely fail or make only incremental progress. This concise review focuses on the history of applied artificial intelligence in photoacoustic tomography, presents recent advances at this multifaceted intersection of fields, and outlines the most exciting advances that will likely propagate into promising future innovations.     

The correlation of microRNA-499 rs3746444 T>C locus with the susceptibility of gastric cancer: from a case–control study to a meta-analysis

The relationship between rs3746444 T>C single-nucleotide polymorphism (SNP) in microRNA (mir)-499 and risk of gastric cancer (GC) has been widely investigated. However, the association was still unconfirmed. Here, we first recruited 490 GC patients and 1476 controls, and conducted a case-control study. And we did not find any association between rs3746444 T>C SNP polymorphism and risk of GC. Subsequently, we conducted a meta-analysis to explore the association of mir-499 rs3746444 polymorphism with GC development. Two authors searched the PubMed and EMBASE databases up to October 15, 2019 independently. Finally, nine literatures involving 12 independent studies were included. In total, 3954 GC cases and 9745 controls were recruited for meta-analysis. The results suggested that allele model, homozygote model and recessive model could increase the risk of overall GC (P = 0.002, 0.009 and 0.013, respectively). When we excluded the studies violated HWE, this association was also found in allele model (P = 0.020) and dominant model (P= 0.044). In subgroup analyses, we identified that rs3746444 SNP in mir-499 increased the risk of GC in Asians and gastric cardiac adenocarcinoma (GCA) subgroups. No significant bias of selection was found (all P>0.1). Test of sensitivity analysis indicated that our findings were stable. Additionally, we found that the power value was 0.891 in the allele model, suggesting the reliability of our findings. In summary, our analysis confirmed the association between rs3746444 and the risk of GC, especially in Asians and in patients with GCA.     

中国北方人群谷胱甘肽转硫酶P1基因多态性及其与胃癌遗传易感性的关系

为了分析中国北方人群谷胱甘肽转硫酶P1基因(glutathione-S-transferase P1, GSTP1)多态性分布, 同时探讨GSTP1基因多态性及其与幽门螺杆菌(H. pylori)既往感染联合作用对胃癌发病风险的影响, 采用多聚酶链反应-限制性片段长度多态性(PCR-RFLP)技术检测1,612例外周血DNA GSTP1的多态性; 采用ELISA方法检测血清H. pylori IgG。结果显示, (1) 中国北方人群GSTP1基因Val等位基因分布频率为22%, 胃癌高、低发区GSTP1 Val等位基因分布频率有显著性差异(0.23/0.20); (2) 以Ile/Ile基因型为参照组与其他两种基因型比较进行胃癌的风险分析, 结果显示携带Val/Val基因型的个体患胃癌的危险性最大, 其OR为5.588 (3.256 ~ 9.591); 携带Val等位基因的个体患胃癌危险性是非携带Val等位基因个体的1.587倍; (3) 以H. pylori IgG(-)并携带GSTP1基因纯合野生型(Ile/ Ile)的个体为参照, H. pylori IgG(+)并携带纯合多态基因型(Val/Val)的个体患胃癌的风险最高, OR为17.571(6.207 ~ 49.742)。说明GSTP1 Val等位基因的分布存在人群及地区差异。携带GSTP1 Val等位基因的个体胃癌发病风险增高。GSTP1 Val等位基因纯合型与H. pylori感染对于胃癌的发生具有交互作用。