An Efficient Approach for Automated Mass Segmentation and Classification in Mammograms

Breast cancer is becoming a leading death of women all over the world; clinical experiments demonstrate that early detection and accurate diagnosis can increase the potential of treatment. In order to improve the breast cancer diagnosis precision, this paper presents a novel automated segmentation and classification method for mammograms. We conduct the experiment on both DDSM database and MIAS database, firstly extract the region of interests (ROIs) with chain codes and using the rough set (RS) method to enhance the ROIs, secondly segment the mass region from the location ROIs with an improved vector field convolution (VFC) snake and following extract features from the mass region and its surroundings, and then establish features database with 32 dimensions; finally, these features are used as input to several classification techniques. In our work, the random forest is used and compared with support vector machine (SVM), genetic algorithm support vector machine (GA-SVM), particle swarm optimization support vector machine (PSO-SVM), and decision tree. The effectiveness of our method is evaluated by a comprehensive and objective evaluation system; also, Matthew’s correlation coefficient (MCC) indicator is used. Among the state-of-the-art classifiers, our method achieves the best performance with best accuracy of 97.73 %, and the MCC value reaches 0.8668 and 0.8652 in unique DDSM database and both two databases, respectively. Experimental results prove that the proposed method outperforms the other methods; it could consider applying in CAD systems to assist the physicians for breast cancer diagnosis.     

Versión en español del software gratuito OxMaR para minimización y aleatorización de estudios clínicos

Randomized clinical trials provide the highest level of scientific evidence. The method used for randomization should make the group to which each case will be assigned unpredictable and facilitate the concealment of the randomization sequence. Centralized methods, generally implemented with computer support, are considered the safest to avoid biases. The OxMaR system, acronym for Oxford Minimization and Randomization, was published as free and open source software in 2014. It works online in a web environment and allows simple randomization and adaptive assignment through minimization. We present a Spanish version developed in collaboration with the author of the original English version. The system has been modified to work on low cost shared web servers and also to allow the concealment of the randomization sequence.     

基于随机森林的精神分裂症血清代谢组学研究

目的探讨随机森林对精神分裂症患者和健康对照的血清代谢组学数据的分类能力,并筛选出差异代谢物。方法病例组为50例精神分裂症患者,对照组为62例健康个体,收集他们的血清进行代谢组学检测,然后用随机森林对数据进行分类,用OOB误差率估计、五折交叉验证评价分类效果,借助随机森林中变量重要性评分(VIM)获得重要的差异代谢物。结果随机森林对病例组和对照组的血清代谢组学数据分类效果较好。病例组错分率为4.0%,对照组错分率为1.6%。OOB误差率估计为2.68%,五折交叉验证ROC曲线下面积为0.99,并根据VIM筛选出15个重要的差异代谢物。结论将液相色谱-质谱代谢组学技术与随机森林相结合,能够筛选出有潜在临床应用价值的代谢物,可用于代谢组学研究。     

Profiling of the pattern of the human TRB/IGH–CDR3 repertoire in primary biliary cholangitis patients

IntroductionPrimary biliary cholangitis (PBC) is characterized by lymphocyte cell-induced immune destruction of cholangiole. However, the immunological characteristics of peripheral blood cells in PBC patients remain unknown. This study was designed to reveal the differences in the immunological characteristics between PBC patients and healthy adults.MethodsWe performed high-throughput sequencing to determine the TRB–CDR3 and IGH–CDR3 repertoires of T and B cells in 19 healthy controls and 29 PBC patients. Different immunological characteristics, such as distinctive complementarity determining region 3 (TRB–CDR3) lengths, usage bias of V and J segments, and random nucleotide addition were identified in PBC and healthy control (HC) groups.ResultsThe diversity of TRB–CDR3 was significantly lower in the PBC group compared with the HC group. CDR3 and the N addition length distribution were significantly changed compared with the HC group. It appeared that the PBC group had more short N additions and the HC group had more long N additions in the TRB–CDR3 repertoire. The results also revealed a set of PBC-associated clonotypes compared with the HC group.ConclusionThis study suggested that PBC is a complex autoimmune disease process with evidence of different TRB–CDR3 rearrangements compared with healthy adults that share IGH–CDR3 peptides with some autoimmune diseases. This new insight may contribute to a better understanding of the immune functions of PBC patients and benefit efficient applications of PBC diagnosis and treatments.     

基于随机森林与logistic回归的高血压影响因素研究

目的 针对铜陵市天桥社区居民体检数据中多因素、有效样本有限的情况，挖掘与分析高血压影响因素与因素间的交互效应，为高血压干预提供参考。方法 选取2017年该社区801例体检数据为研究对象，采用随机森林方法，筛选出重要性评分较大的特征，代入logistic完全二次回归模型，逐步回归分析影响因素及因素间的交互效应。结果 随机森林模型准确率83.67%，特征重要性前10项为年龄、糖尿病、锻炼频率、体质指数、总胆固醇、吸烟情况、饮酒情况、中心性肥胖、甘油三酯、血尿素氨。Logistic完全二次回归模型准确率84.17%，输出2条主效应、8条二次交互效应。主效应中有统计学意义(P<0.05)的特征有年龄、锻炼频率，二次交互效应中有统计学意义(P<0.05)的特征有年龄、糖尿病、体质指数、总胆固醇、吸烟情况、饮酒情况、甘油三酯、血尿素氨。结论 随机森林与logistic完全二次回归模型相结合，解决了经典方法难以从多因素、样本有限的数据中挖掘交互效应的问题，获得高血压影响因素与因素间的交互效应，为高血压干预提供有益的指导。     

Machine intelligence in peptide therapeutics: A next-generation tool for rapid disease screening

Discovery and development of biopeptides are time-consuming, laborious, and dependent on various factors. Data-driven computational methods, especially machine learning (ML) approach, can rapidly and efficiently predict the utility of therapeutic peptides. ML methods offer an array of tools that can accelerate and enhance decision making and discovery for well-defined queries with ample and sophisticated data quality. Various ML approaches, such as support vector machines, random forest, extremely randomized tree, and more recently deep learning methods, are useful in peptide-based drug discovery. These approaches leverage the peptide data sets, created via high-throughput sequencing and computational methods, and enable the prediction of functional peptides with increased levels of accuracy. The use of ML approaches in the development of peptide-based therapeutics is relatively recent; however, these techniques are already revolutionizing protein research by unraveling their novel therapeutic peptide functions. In this review, we discuss several ML-based state-of-the-art peptide-prediction tools and compare these methods in terms of their algorithms, feature encodings, prediction scores, evaluation methodologies, and software utilities. We also assessed the prediction performance of these methods using well-constructed independent data sets. In addition, we discuss the common pitfalls and challenges of using ML approaches for peptide therapeutics. Overall, we show that using ML models in peptide research can streamline the development of targeted peptide therapies.     

Azoles versus conventional amphotericin B for the treatment of candidemia: A meta-analysis of randomized controlled trials

Because exclusive use of echinocandins can induce the drug-resistant strains, appropriate use of azoles and polyenes is still necessary in the treatment of candidemia. In this study, we conducted a meta-analysis of randomized controlled trials regarding the efficacy and safety of azole and polyene antifungals in the treatment of candidemia. MEDLINE and the Cochrane Register of Controlled Trials were used as reference databases, and papers published up to June 10, 2019 were searched. The search results were carefully scrutinized, duplicate references were removed, and the study was ultimately carried out using three reports. Among azole antifungals, fluconazole and voriconazole were extracted, however; only conventional amphotericin B (AMPH-B) was extracted among polyene antifungals. Treatment successes with the use of azoles and AMPH-B were compared, and findings showed that AMPH-B was significantly superior (RR = 0.90, 95% CI 0.82–1.00, p = 0.04). However, there was no significant difference in mortality (RR = 0.87, 95% CI 0.72–1.07, p = 0.19). Analysis of adverse events showed that renal disorders were significantly less common with azoles than with AMPH-B (RR = 0.26, 95% CI 0.10–0.68, p = 0.006). In conclusion, AMPH-B were superior to azoles in terms of efficacy, but had a risk of causing renal disorders.     

Prioritization of candidate disease genes by combining topological similarity and semantic similarity

The identification of gene–phenotype relationships is very important for the treatment of human diseases. Studies have shown that genes causing the same or similar phenotypes tend to interact with each other in a protein–protein interaction (PPI) network. Thus, many identification methods based on the PPI network model have achieved good results. However, in the PPI network, some interactions between the proteins encoded by candidate gene and the proteins encoded by known disease genes are very weak. Therefore, some studies have combined the PPI network with other genomic information and reported good predictive performances. However, we believe that the results could be further improved. In this paper, we propose a new method that uses the semantic similarity between the candidate gene and known disease genes to set the initial probability vector of a random walk with a restart algorithm in a human PPI network. The effectiveness of our method was demonstrated by leave-one-out cross-validation, and the experimental results indicated that our method outperformed other methods. Additionally, our method can predict new causative genes of multifactor diseases, including Parkinson’s disease, breast cancer and obesity. The top predictions were good and consistent with the findings in the literature, which further illustrates the effectiveness of our method.     

Joint 3-D vessel segmentation and centerline extraction using oblique Hough forests with steerable filters

ContributionsWe propose a novel framework for joint 3-D vessel segmentation and centerline extraction. The approach is based on multivariate Hough voting and oblique random forests (RFs) that we learn from noisy annotations. It relies on steerable filters for the efficient computation of local image features at different scales and orientations.ExperimentsWe validate both the segmentation performance and the centerline accuracy of our approach both on synthetic vascular data and four 3-D imaging datasets of the rat visual cortex at 700 nm resolution. First, we evaluate the most important structural components of our approach: (1) Orthogonal subspace filtering in comparison to steerable filters that show, qualitatively, similarities to the eigenspace filters learned from local image patches. (2) Standard RF against oblique RF. Second, we compare the overall approach to different state-of-the-art methods for (1) vessel segmentation based on optimally oriented flux (OOF) and the eigenstructure of the Hessian, and (2) centerline extraction based on homotopic skeletonization and geodesic path tracing.ResultsOur experiments reveal the benefit of steerable over eigenspace filters as well as the advantage of oblique split directions over univariate orthogonal splits. We further show that the learning-based approach outperforms different state-of-the-art methods and proves highly accurate and robust with regard to both vessel segmentation and centerline extraction in spite of the high level of label noise in the training data.     

Toll-like receptor 2 expression on monocytes and microvascular complications in type 2 diabetic patients

Diabetes mellitus (DM) is a chronic debilitating illness, and atherosclerotic changes are inevitable and usually neglected during the follow-up of diabetic patients. Toll-like receptor 2 (TLR2) is under trial in many studies to hold responsibility for atherosclerosis process progression as they suggest a malfunction of these receptors expressed on monocytes in diabetic patients. This study aimed to assess the association between the TLR2 and type 2 diabetes mellitus (T2DM) in Egyptian diabetic patients and to investigate its relationship with some diabetic complications.MethodsThis study included a 60 diabetic patients group 1 (diabetic complicated), group 2 (diabetic non-complicated) and 30 age-matched normal healthy blood donors.ResultsToll-like receptors (TLRs) expression was significantly associated with T2DM. In this study, the mean fluorescent intensity (MFI) of TLR2 was 596.9 ± 84.78 in group 1, 326.23 ± 62.98 in group 2 while in group 3 it was 208.47 ± 156.73. There was a significant correlation between MFI of TLR2 and random blood sugar (RBS) and glycated haemoglobin (HbA1c) (p < 0.05).ConclusionTLR2 was overexpressed in diabetic patients with microvascular complications compared to diabetic non-complicated patients and normal healthy controls.