Detection and classification of breast lesions using multiple information on contrast-enhanced mammography by a multiprocess deep-learning system: A multicenter study

Objective: Accurate detection and classification of breast lesions in early stage is crucial to timely formulate effective treatments for patients. We aim to develop a fully automatic system to detect and classify breast lesions using multiple contrast-enhanced mammography(CEM) images.Methods: In this study, a total of 1,903 females who underwent CEM examination from three hospitals were enrolled as the training set, internal testing set, pooled external testing set and prospective testing set. Here we developed a CEM-based multiprocess detection and classification system(MDCS) to perform the task of detection and classification of breast lesions. In this system, we introduced an innovative auxiliary feature fusion(AFF)algorithm that could intelligently incorporates multiple types of information from CEM images. The average freeresponse receiver operating characteristic score(AFROC-Score) was presented to validate system’s detection performance, and the performance of classification was evaluated by area under the receiver operating characteristic curve(AUC). Furthermore, we assessed the diagnostic value of MDCS through visual analysis of disputed cases,comparing its performance and efficiency with that of radiologists and exploring whether it could augment radiologists’ performance.Results: On the pooled external and prospective testing sets, MDCS always maintained a high standalone performance, with AFROC-Scores of 0.953 and 0.963 for detection task, and AUCs for classification were 0.909[95% confidence interval(95% CI): 0.822-0.996] and 0.912(95% CI: 0.840-0.985), respectively. It also achieved higher sensitivity than all senior radiologists and higher specificity than all junior radiologists on pooled external and prospective testing sets. Moreover, MDCS performed superior diagnostic efficiency with an average reading time of 5 seconds, compared to the radiologists’ average reading time of 3.2 min. The average performance of all radiologists was also improved to varying degrees with MDCS assistance.Conclusions: MDCS demonstrated excellent performance in the detection and classification of breast lesions,and greatly enhanced the overall performance of radiologists.

单胺接枝耐溶剂聚酰亚胺分离膜的制备及染料截留性能

文中从分子结构设计角度出发,以聚酰亚胺(PI)为基质膜材料,引入单胺交联剂三羟甲基氨基甲烷(Tris),在制膜的中间环节对聚酰亚胺进行分子链修饰,采用相转化法制备接枝耐溶剂聚酰亚胺分离膜,对膜的分子结构、微观结构、分离性能和耐溶剂性能等进行考察。结果表明,当铸膜液中PI质量分数为20%时,膜分离效果最佳,对甲基蓝(MYB)的截留率可达97.81%,渗透通量达181L/(m^(2)·h),接枝后的膜具有优异的耐溶剂性。在0.3 MPa下对0.1g/L MYB水溶液进行30h的连续运行,膜对MYB的截留率保持在97%以上,渗透通量在180L/(m^(2)·h)左右,表现出良好的使用稳定性。

A strategy for mechanically integrating robust hydrogeltissue hybrid to promote the anti-calcification and endothelialization of bioprosthetic heart valve

Bioprosthetic heart valve(BHV)replacement has been the predo-minant treatment for severe heart valve diseases over decades.Most clinically available BHVs are crosslinked by glutaraldehyde(GLUT),while the high toxicity of residual GLUT could initiate calcification,severe thrombosis,and delayed endothelializa-tion.Here,we construed a mechanically integrating robust hydrogel-tissue hybrid to improve the performance of BHVs.In particular,recombinant humanized coilagen type Ⅲ(rhCOLⅢ),which was precisely customized with anti-coagulant and pro-endothelialization bioactivity,was first incorporated into the polyvinyl alcohol(PVA)-based hydrogel via hydrogen bond interactions.Then,tannic acid was introduced to enhance the mechanicalperfo of PVA-based hvdrogel and interfacial bonding between the hydrogel layer and bio-derived tissue due to the strong affinity for a wide range of substrates.In vitro and in vivo experimental results confirmed that the GLUT-crosslinked BHVs modified by the robust PVA-based hydrogel embedded rhCOLII and TA possessed long-term anti-coagulant,accelerated endothelialization,mild inflammatory response and anti-calcification properties.Therefore,our mechanically integrating robust hydrogel-tissue hybrid strategy showed the potential to enhance the service function and prolong the service life of the BHVs after implantation.

Co-culture of Schwann cells and endothelial cells for synergistically regulating dorsal root ganglion behavior on chitosan-based anisotropic topology for peripheral nerve regeneration

Background:Anisotropic topologies are known to regulate cell-oriented growth and induce cell differentiation,which is conducive to accelerating nerve regeneration,while co-culture of endothelial cells(ECs)and Schwann cells(SCs)can significantly promote the axon growth of dorsal root ganglion(DRG).However,the synergistic regulation of EC and SC co-culture of DRG behavior on anisotropic topologies is still rarely reported.The study aims to investigate the effect of anisotropic topology co-cultured with Schwann cells and endothelial cells on dorsal root ganglion behavior for promoting peripheral nerve regeneration.Methods:Chitosan/artemisia sphaerocephala(CS/AS)scaffolds with anisotropic topology were first prepared using micro-molding technology,and then the surface was modified with dopamine to facilitate cell adhesion and growth.The physical and chemical properties of the scaffolds were characterized through morphology,wettability,surface roughness and component variation.SCs and ECs were co-cultured with DRG cells on anisotropic topology scaffolds to evaluate the axon growth behavior.Results:Dopamine-modified topological CS/AS scaffolds had good hydrophilicity and provided an appropriate environment for cell growth.Cellular immunofluorescence showed that in contrast to DRG growth alone,co-culture of SCs and ECs could not only promote the growth of DRG axons,but also offered a stronger guidance for orientation growth of neurons,which could effectively prevent axons from tangling and knotting,and thus may significantly inhibit neurofibroma formation.Moreover,the co-culture of SCs and ECs could promote the release of nerve growth factor and vascular endothelial growth factor,and up-regulate genes relevant to cell proliferation,myelination and skeletal development via the PI3K-Akt,MAPK and cytokine and receptor chemokine pathways.Conclusions:The co-culture of SCs and ECs significantly improved the growth behavior of DRG on anisotropic topological scaffolds,which may provide an important basis for the development of nerve grafts in peripheral nerve regeneration.

增温驱动的核心微生物的迁移可指示土壤属性的改变

尽管微生物-气候的相互作用已得到越来越多的研究者和决策者的认可,但微生物的高多样性和对气候环境变化多变量的响应导致预测微生物在未来气候背景下的分布格局非常困难.本研究依托于中国土壤微生物组计划,基于采集自中国东部森林的1600多个样品的16S r RNA基因测序数据,首先证实了微生物群落组成和多样性的纬度分布规律且温度对微生物群落组成有显著的直接作用.其次,利用核心微生物代替整体群落来进行多样性的缩减,并将这些核心微生物根据其对环境的偏好性划分为不同的生态集群,这些生态集群在空间上的热点区域,即高丰度区域相互不重叠.此外,通过Cubist模型预测未来不同气候变化情景下(RCP2.6和RCP8.5)各生态集群的丰度变化并将其投影到中国森林生态系统分布区域,通过与现在的分布格局做对比得到增温驱动的生态集群空间分布格局的变化.这些变化一方面可以指示集群内微生物对未来气候变化的适应性,另一方面考虑到每一类生态集群所代表的环境偏好性,这些变化也可进一步用来指示未来气候变化背景下土壤属性的变化.