Redox proteomics identification of 4‐hydroxynonenal‐modified brain proteins in Alzheimer's disease: Role of lipid peroxidation in Alzheimer's disease pathogenesis

Numerous studies have shown that neuronal lipids are highly susceptible to oxidative stress including in those brain areas directly involved in the neurodegenerative process of Alzheimer's disease (AD). Lipid peroxidation directly damages membranes and also generates a number of secondary biologically active products (toxic aldehydes)that are capable of easily attacking lipids, proteins, and DNA. Accumulating evidence has demonstrated regionally increased brain lipid peroxidation in patients with AD; however, extensive studies on specific targets of lipid peroxidation‐induced damage are still missing. The present study represents a further step in understanding the relationship between oxidative modification of protein and neuronal death associated with AD. We used a proteomics approach to determine specific targets of lipid peroxidation in AD brain, both in hippocampus and inferior parietal lobule, by coupling immunochemical detection of 4‐hydroxynonenal‐bound proteins with 2‐D polyacrylamide gel electrophoresis and MS analysis. We identified 4‐hydroxynonenal‐bound proteins in the hippocampus and inferior parietal lobule brain regions of subjects with AD. The identified proteins play different biological functions including energy metabolism, antioxidant system, and structural proteins, thus impairing multiple molecular pathways. Our results provide further evidence for the role of lipid peroxidation in the pathogenesis of AD.     

Proteomic analysis of sera of asymptomatic,early‐stage patients with Wilson's disease

Wilson's disease (WD) is characterized by excessive accumulation of intracellular copper in liver and extrahepatic tissues, leading to significant oxidative stress and tissue damage. To date, several diagnostic biomarkers for WD such as serum ceruloplasmin, serum or urine copper levels and copper content in liver have been identified. However, these biomarkers may not be convincing for the diagnosis in some WD patients. To identify additional novel diagnostic biomarkers, we compared the serum protein profiles of asymptomatic childhood WD patients (n=20), without neurologic manifestation or liver cirrhosis, with normal controls (n=13). Fourteen spots, five up‐regulated and nine down‐regulated (>2‐fold), were differentially expressed in WD patients in comparison to normal control on 2‐DE. Among them, three spots were down‐regulated in both male and female WD. MS/MS analysis revealed that the three spots were complement component C3, complement factor B and alpha‐2 macroglobulin. By comparative proteome analysis, complement component C3, complement factor B and alpha‐2 macroglobulin, which are related to oxidative stress and inflammation, turned out to be good candidates for novel diagnostic biomarkers for early stages of WD.     

Thymosin β4 is differentially expressed in the cerebrospinal fluid of Creutzfeldt‐Jakob disease patients: a MALDI‐TOF MS protein profiling study

MALDI‐TOF protein profiling analysis permits the detection of peptides and small proteins in complex protein mixtures with great accuracy. We applied this analysis to cerebrospinal fluid (CSF) from 15 patients affected by Creutzfeldt‐Jakob disease (CJD). We compared the levels of the normalized ion signals of 11 sporadic and 4 genetic CJD forms with those from ten healthy control subjects and eight non‐CJD relapsing‐remitting multiple sclerosis patients. In so doing, we detected 61 differentially expressed ion signals in CJD samples compared to controls. Among the 61 signals, 3 signals had significantly increased levels with high statistical significance (p <0.0001) and were located at 3238.3 m/z, 4963.7 m/z, and 8565.3 m/z. We characterized the 5.0 and 8.6 kDa proteins as thymosin β4 N‐acetylated and free ubiquitin, respectively, while the 3.2‐kDa peptide remained uncharacterized. Although elevated ubiquitin levels have previously been described in CJD, we have demonstrated for the first time the involvement of thymosin β4 in a neurodegenerative disease. To support the validity of thymosin β4 levels obtained by MALDI‐TOF analysis, an independent enzyme immunoassay analysis was performed. Moreover, a validation cohort consisting of CSF from three CJD patients, five healthy subjects, and six non‐CJD relapsing‐remitting multiple sclerosis patients was analyzed in a similar way, yielding superimposable results. We propose that thymosin β4 is a potential new candidate marker for the ante mortem diagnosis of CJD disease.     

Proteomic analysis in cerebrospinal fluid of patients with atypical nonketotic hyperglycinemia and pulmonary hypertension - A pilot study

A variant phenotype of nonketotic hyperglycinemia has been described by our group associated with pulmonary hypertension. The aim of this study is to investigate the cerebrospinal fluid proteomes to get an insight into this neurodegenerative process producing leukoencephalopathy with white matter spongiform degeneration. DIGE and MALDI-TOF-TOF analyses were performed to carry out the proteomic study of four patients against three normal controls and one additional control of a classical nonketotic hyperglycinemia. The differential proteomic analysis showed a displacement of some series of spots toward the acidic side. The shifted proteins showed a high degree of carbonylation and increased methionine sulfoxidation was found in cystatin C and in vitamin-D-binding protein. These findings in addition to the increase of serum malondialdehyde concentration provide evidence of an oxidative stress in the patients under study, which is probably systemic rather than mainly confined to the CNS. The similarities of our findings with those found in other neurodegenerative diseases suggest that oxidative damage is commonly involved in these pathologies. DIGE technology improves the 2-D PAGE differential analysis and it is suitable in proteomic studies with a small number of cases.     

基于圆形约束C-V水平集的肺部CT图像病灶分割

针对肺部CT图像中圆形病灶区域的分割问题,对Chan-Vese水平集图像分割方法进行了分析和改进,提出了基于圆形约束的C-V水平集模型,进而提出了基于圆形约束水平集的肺部图像病灶分割算法,解决了图像中大小不同的多圆检测问题。对合成图像和实际临床肺部CT图像进行了分割实验,结果表明,该方法可以较好地分割出图像中的多个圆形区域,算法具有较好的抗噪性,实现速度较快,有利于实现肺部CT图像肺结节自动检测。     

Ensemble feature selection and classification methods for machine learning-based coronary artery disease diagnosis

Coronary artery disease (CAD) is a condition in which the heart is not fed sufficiently as a result of the accumulation of fatty matter. As reported by the World Health Organization, around 32% of the total deaths in the world are caused by CAD, and it is estimated that approximately 23.6 million people will die from this disease in 2030. CAD develops over time, and the diagnosis of this disease is difficult until a blockage or a heart attack occurs. In order to bypass the side effects and high costs of the current methods, researchers have proposed to diagnose CADs with computer-aided systems, which analyze some physical and biochemical values at a lower cost. In this study, for the CAD diagnosis, (i) seven different computational feature selection (FS) methods, one domain knowledge-based FS method, and different classification algorithms have been evaluated; (ii) an exhaustive ensemble FS method and a probabilistic ensemble FS method have been proposed. The proposed approach is tested on three publicly available CAD data sets using six different classification algorithms and four different variants of voting algorithms. The performance metrics have been comparatively evaluated with numerous combinations of classifiers and FS methods. The multi-layer perceptron classifier obtained satisfactory results on three data sets. Performance evaluations show that the proposed approach resulted in 91.78%, 85.55%, and 85.47% accuracy for the Z-Alizadeh Sani, Statlog, and Cleveland data sets, respectively.     

Magnetic Large-Mesoporous Nanoreactors Enable Enzymatically Regulated Background-Free and Persistently Signalling Diseases Diagnosis

Diverse diseases and increasing prevalence pose a serious threat to public health. Point-of-care testing (POCT) techniques have imposed superior requirements over sensitivity, selectivity, robustness, affordability, and high-throughput. However, transient signal, complex sample pretreatment, and low signal-to-noise ratio make POCT severely limited in detection accuracy, efficiency, and sensitivity. Here, an enzyme-assisted magnetic large-mesoporous nanoreactor (FS) is constructed for achieving persistent-chemiluminescence signal output and eliminating matrix interference in disease diagnosis. The core-shell structured FS synthesized via an interface coassembly method exhibits uniform size, large and open mesopores (≈22 nm), and intrinsic magnetic separability. Such unique FS acts as efficient nanoreactor for confined cascade reactions enable efficient persistent-chemiluminescence (pCL) signal transduction and high-SNR chromogenic analysis of diverse biomarkers. The developed pCL assays facilitate high-sensitive determination of chronic disease biomarkers glucose and uric acid with detection limits (DL) of 5.4 mg L⁻¹ and 151.2 ng L⁻¹, respectively. The proposed chromogenic immunoassay enables an ultrasensitive and visual determination of alpha-fetoprotein with a DL of 1.2 ng L⁻¹, which is superior to previously published immunoassays. The feasibility of the developed methods for real-world applications are demonstrated in 159 clinical serum samples, and the determination results agree well with the clinical data. The proposed technique is expected to promote highly sensitive disease diagnosis in primary medical institutions and resource-limited areas since not relying on expensive automatic sampling and testing instruments. The good flexibility of the customizable nanoreactor makes it a powerful tool for developing various POCT techniques for rapid, sensitive, and accurate diseases diagnosis.     

Towards Sustainable Agricultural Systems: A Lightweight Deep Learning Model for Plant Disease Detection

A country’s economy heavily depends on agricultural development. However, due to several plant diseases, crop growth rate and quality are highly suffered. Accurate identification of these diseases via a manual procedure is very challenging and time-consuming because of the deficiency of domain experts and low-contrast information. Therefore, the agricultural management system is searching for an automatic early disease detection technique. To this end, an efficient and lightweight Deep Learning (DL)-based framework (E-GreenNet) is proposed to overcome these problems and precisely classify the various diseases. In the end-to-end architecture, a MobileNetV3Small model is utilized as a backbone that generates refined, discriminative, and prominent features. Moreover, the proposed model is trained over the PlantVillage (PV), Data Repository of Leaf Images (DRLI), and a new Plant Composite (PC) dataset individually, and later on test samples, its actual performance is evaluated. After extensive experimental analysis, the proposed model obtained 1.00%, 0.96% and 0.99% accuracies on all three included datasets. Moreover, the proposed method achieves better inference speed when compared with other State-Of-The-Art (SOTA) approaches. In addition, a comparative analysis is conducted where the proposed strategy shows tremendous discriminative scores as compared to the various pre-trained models and other Machine Learning (ML) and DL methods.     

基于机器学习的超声造影分析综述

超声造影（Contrast-enhanced ultrasound, CEUS）通过外周静脉注入超声造影剂,显著增强来自肿瘤微血管的血流信号,便于临床医生以实时、动态的方式评估肿瘤血管生成、周边浸润等,广泛应用于多器官病变诊断、预后评估和治疗方案规划等方面。近年来,以深度学习为代表的机器学习方法快速发展,为动态超声造影智能分析带来新的机遇。深度学习方法很大程度上拓宽了超声造影临床应用范围,提高了其诊疗效能。但与常规超声影像类似,超声造影仍然存在斑点噪声、呼吸运动干扰和标准化程度低等问题,使得动态灌注时间、空间信息挖掘面临挑战。本文系统性回顾了近年来超声造影智能分析相关工作,涵盖良恶性鉴别、恶性分级、疗效预测和诊疗方案选择等方面应用,总结了当前影像组学及深度学习方法在超声造影分析领域的最新进展,并指出当前研究的局限性和未来发展方向。     

融合隐向量对齐和Swin Transformer的OCTA血管分割

目的 光学相干断层扫描血管造影（optical coherence tomography angiography,OCTA）是一种非侵入式的新兴技术,越来越多地应用于视网膜血管成像。与传统眼底彩照相比,OCTA技术能够显示黄斑周围的微血管信息,在视网膜血管成像邻域具有显著优势。临床实践中,医生可以通过OCTA图像观察不同层的血管结构,并通过分析血管结构的变化来判断是否存在相关疾病。大量研究表明,血管结构的任何异常变化通常都意味着存在某种眼科疾病。因此,对OCTA图像中的视网膜血管结构进行自动分割提取,对众多眼部相关疾病量化分析和临床决策具有重大意义。然而,OCTA图像存在视网膜血管结构复杂、图像整体对比度低等问题,给自动分割带来极大挑战。为此,提出了一种新颖的融合隐向量对齐和Swin Transformer的视网膜血管结构的分割方法,能够实现血管结构的精准分割。方法 以ResU-Net为主干网络,通过Swin Transformer编码器获取丰富的血管特征信息。此外,设计了一种基于隐向量的特征对齐损失函数,能够在隐空间层次对网络进行优化,提升分割性能。结果 在3个OCTA图像数据集上的...