|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Development and validation of an endoscopic images-based deep learning model for detection with nasopharyngeal malignancies显示文摘Background:Due to the occult anatomic location of the nasopharynx and frequent presence of adenoid hyperpla-sia,the positive rate for malignancy identification during biopsy is low,thus leading to delayed or missed diagnosis for nasopharyngeal malignancies upon initial attempt.Here,we aimed to develop an artificial intelligence tool to detect nasopharyngeal malignancies under endoscopic examination based on deep learning.Methods:An endoscopic images-based nasopharyngeal malignancy detection model(eNPM-DM)consisting of a fully convolutional network based on the inception architecture was developed and fine-tuned using separate training and validation sets for both classification and segmentation.Briefly,a total of 28,966 qualified images were collected.Among these images,27,536 biopsy-proven images from 7951 individuals obtained from January 1st,2008,to December 31st,2016,were split into the training,validation and test sets at a ratio of 7:1:2 using simple randomiza-tion.Additionally,1430 images obtained from January 1st,2017,to March 31st,2017,were used as a prospective test set to compare the performance of the established model against oncologist evaluation.The dice similarity coef-ficient(DSC)was used to evaluate the efficiency of eNPM-DM in automatic segmentation of malignant area from the background of nasopharyngeal endoscopic images,by comparing automatic segmentation with manual segmenta-tion performed by the experts.Results:All images were histopathologically confirmed,and included 5713(19.7%)normal control,19,107(66.0%)nasopharyngeal carcinoma(NPC),335(1.2%)NPC and 3811(13.2%)benign diseases.The eNPM-DM attained an overall accuracy of 88.7%(95%confidence interval(CI)87.8%-89.5%)in detecting malignancies in the test set.In the prospective comparison phase,eNPM-DM outperformed the experts:the overall accuracy was 88.0%(95%CI 86.1%-89.6%)vs.80.5%(95%CI 77.0%-84.0%).The eNPM-DM required less time(40 s vs.110.0±5.8 min)and exhibited encouraging performance in automatic segmentation of nasopharyngeal malignant area from the background,with an average DSC of 0.78±0.24 and 0.75±0.26 in the test and prospective test sets,respectively.Conclusions:The eNPM-DM outperformed oncologist evaluation in diagnostic classification of nasopharyngeal mass into benign versus malignant,and realized automatic segmentation of malignant area from the background of nasopharyngeal endoscopic images. | Chaofeng Li Bingzhong Jing Liangru Ke Bin Li Weixiong Xia Caisheng He Chaonan Qian Chong Zhao Haiqiang Mai Mingyuan Chen Kajia Cao Haoyuan Mo Ling Guo Qiuyan Chen Linquan Tang Wenze Qiu Yahui Yu Hu Liang Xinjun Huang Guoying Liu Wangzhong Li Lin Wang Rui Sun Xiong Zou Shanshan Guo Peiyu Huang Donghua Luo Fang Qiu Yishan Wu Yijun Hua Kuiyuan Liu Shuhui Lv Jingjing Miao Yanqun Xiang Ying Sun Xiang Guo Xing Lv | 2018 | Cancer Communications2018，38，1： | 9 |
| 2 | Soil total organic carbon/total nitrogen ratio as a key driver deterministically shapes diazotrophic community assemblages during the succession of biological soil crusts显示文摘The diazotrophic community in biological soil crusts(biocrusts)is the key supplier of nitrogen in dryland.To date,there is still limited information on how biocrust development influences the succession of diazotrophic community,and what are the most important factors mediating diazotrophic communities during biocrust succession.Using the high throughput nifH amplicon sequencing,the diazotrophs in soils at different developmental stages of biocrust were comparatively studied.The results evidenced the decreases of TOC/TN ratio and pH value with biocrust development.Nostoc and Scytonema were the most dominant diazotrophic genera at all biocrust stages,while Azospirillum and Bradyrhizobium were abundant only in bare soil.Diazotrophic co-occurrence networks tended to be less complex and less connected with biocrust succession.The soil TOC/TN ratio was the most dominant factor mediating diazotrophic diversity,community composition and assembly processes,while diazotrophic-diversity and NO3–-N/NH4+-N ratio were positively correlated with the nitrogenase activity during biocrust succession.This study provided novel understandings of nitrogen fixation and succession patterns of diazotrophic community,by showing the effects of biocrust succession on diazotrophic diversity,community composition,community assembly and co-occurrence networks,and recognizing TOC/TN ratio as the most dominant factor mediating diazotrophs during biocrust succession. | Lin Xu Bingchang Zhang Entao Wang Bingjian Zhu Minjie Yao Chaonan Li Xiangzhen Li | 2021 | Soil Ecology Letters2021，3，4： | 3 |
| 3 | SynBioEcoli: a comprehensive metabolism network of engineered E. coil in three dimensional visualization显示文摘设计 E 的一个全面新陈代谢网络。coli 在系统生物学是很重要的, metabolomics 学习。许多工具集中于二维的空格在新陈代谢的网络显示小径。然而,三维的可视化的用法可以帮助更好理解新陈代谢、规章的网络的复杂拓扑学。方法我们手工地从文学的大量试验性的数据(包括的小径,反应和代谢物) 与设计 E 的不同类型联系了的 curated。coli 然后利用了三维的可视化的一种新奇技术开发一个全面新陈代谢的网络命名 SynBioEcoli。结果 SynBioEoli 包含 740 条 biosynthetic 小径, 3,889 新陈代谢的反应, 2,255 化学药品手工地从与设计 E 的不同类型联系的大约 11,000 份新陈代谢出版物加重 curated。coli。而且, SynBioEcoli 与各种各样的信息科学技术集成。结论 SynBioEcoli 能被认为是设计 E 的全面 knowledgebase。coli 并且代表下一代细胞的新陈代谢网络可视化技术。它能经由浏览器被存取(例如 Google 铬) 支持 WebGL,在 http://gffzz849681930f04473chqn69kwbvpobk6c5u.ffgz.tsg.suse.edu.cn/synbioecoli/ 。 | Weizhong Tu Shaozhen Ding Ling Wu Zhe Deng Hui Zhu Xiaotong Xu Chen Lin Chaonan Ye Minlu Han Mengna Zhao Juan Liu Zixin Deng Junni Chen Dong-Qing Wei Qian-Nan Hu | 2017 | Frontiers of Electrical and Electronic Engineering in China2017，5，1： | 2 |
| 4 | Image Normalization for Pattern Recognition 显示文摘 | Pei Soo-chang Lin Chaonan | 1995 | Image and Vision Computing1995，13，10： | 1 |
| 5 | DHD4,a CONSTANS-like family transcription factor,delays heading date by affecting the formation of the FAC complex in rice显示文摘Heading date(or flowering time)is one of the most important agronomic traits in rice,influencing its regional adaptability and crop yield.Many major-effect genes for rice heading date have been identified,but in practice they are difficult to be used for rice molecular breeding because of their dramatic effects on heading date.Genes with minor effects on heading date,which are more desirable for fine-tuning flowering time without significant yield penalty,were seldom reported.In this study,we identified a new minor-effect heading date repressor,Delayed Heading Date 4(DHD4).The dhd4 mutant shows a slightly earlier flowering phenotype without a notable yield penalty compared with wild-type plants under natural long-day conditions.DHD4 encodes a CONSTANS-like transcription factor localized in the nucleus.Molecular,biochemical,and genetic assays show that DHD4 can compete with 14-3-3 to interact with OsFD1,thus affecting the formation of the Hd3a-14-3-3-OsFD1 triprotein FAC complex,resulting in reduced expression of OsMADS14 and OsMADS15,and ultimately delaying flowering.Taken together,these results shed new light on the regulation of flowering time in rice and provide a promising target for fine-tuning flowering time to improve the regional adaptability of rice. | Maohong Cai Shanshan Zhu Mingming Wu Xiaoming Zheng Jiachang Wang Liang Zhou Tianhui Zheng Song Cui Shirong Zhou Chaonan Li Huan Zhang Juntao Chai Xinyue Zhang Xin Jin Zhijun Cheng Xin Zhang Cailin Lei Yulong Ren Qibing Lin Xiuping Guo Lei Zhao Jie Wang Zhichao Zhao Ling Jiang Haiyang Wang Jianmin Wan | 2021 | Molecular Plant2021，14，2： | 1 |
| 6 | Ga2O3 solar-blind position-sensitive detectors显示文摘Monoclinic Ga2O3(β-Ga2O3)is a promising material for achieving solar-blind photodetection because of its unique characteristics,including its high breakdown electric field,radiation hardness,thermal and chemical stabilities,and intrinsic visible/solar-blind properties.Until now,several studies have investigated the development of high-performanceβ-Ga2O3 solar-blind photodetectors.However,these photodetectors can only detect the light intensity but not the light position.In this work,fourquadrant position-sensitive detectors(4Q-PSDs)were developed and demonstrated based onβ-Ga2O3.4Q-PSDs,comprising four identical metal-semiconductor-metal-structured photodetector components,demonstrate high uniformity,large signal-tonoise ratio,good ultraviolet/visible rejection ratio,and fast response/recovery time.Subsequently,the position of the illumination beam can be determined by analyzing the output signals of the four photodetector components.This work may indicate the promising application potential of the Ga2O3-based photodetectors in the fields of positioning,aligning,and monitoring the solarblind beams. | Kaiyong Li Xun Yang Yongzhi Tian Yancheng Chen Chaonan Lin Zhenfeng Zhang Zhiyang Xu Jinhao Zang Chongxin Shan | 2020 | Science China(Physics,Mechanics & Astronomy)2020，63，11： | 0 |
| 7 | Implications of vitamin D for flesh quality of grass carp(Ctenopharyngodon idella):antioxidant ability,nutritional value,sensory quality,and myofiber characteristics显示文摘Background Muscle represents a unique and complex system with many components and comprises the major edible part of animals.Vitamin D is a critical nutrient for animals and is known to enhance calcium absorption and immune response.In recent years,dietary vitamin D supplementation in livestock has received increased attention due to biological responses including improving shear force in mammalian meat.However,the vitamin D acquisition and myofiber development processes in fish differ from those in mammals,and the effect of vitamin D on fish flesh quality is poorly understood.Here,the influence of dietary vitamin D on fillet quality,antioxidant ability,and myofiber development was examined in grass carp(Ctenopharyngodon idella).Methods A total of 540 healthy grass carp,with an initial average body weight of 257.24±0.63 g,were allotted in 6 experimental groups with 3 replicates each,and respectively fed corresponding diets with 15.2,364.3,782.5,1,167.9,1,573.8,and 1,980.1 IU/kg vitamin D for 70 d.Results Supplementation with 1,167.9 IU/kg vitamin D significantly improved nutritional value and sensory quality of fillets,enhancing crude protein,free amino acid,lipid,and collagen contents;maintaining an ideal pH;and reduc-ing lactate content,shear force,and cooking loss relative to respective values in the control(15.2 IU/kg)group.Average myofiber diameter and the frequency of myofibers>50μm in diameter increased under supplementation with 782.5–1,167.9 IU/kg vitamin D.Levels of oxidative damage biomarkers decreased,and the expression of antioxi-dant enzymes and nuclear factor erythroid 2-related factor 2 signaling molecules was upregulated in the 1,167.9 IU/kg vitamin D treatment compared to respective values in the control group.Furthermore,vitamin D supplementation activated cell differentiation by enhancing the expression of myogenic regulatory factors and myocyte enhancer factors compared to that in the control group.In addition,supplementation with 1,167.9 IU/kg vitamin D improved protein deposition associated with protein synthesis molecule(target of rapamycin)signaling and vitamin D receptor paralogs,along with inhibition of protein degradation(forkhead box protein 1)signaling.Conclusions Overall,the results demonstrated that vitamin D strengthened antioxidant ability and myofiber devel-opment,thereby enhancing nutritional value and sensory quality of fish flesh.These findings suggest that dietary vitamin D supplementation is conducive to the production of nutrient-rich,high quality aquaculture products. | Yao Zhang Chaonan Li Xiaoqiu Zhou Weidan Jiang Pei Wu Yang Liu Hongmei Ren Lu Zhang Haifeng Mi Jiayong Tang Ruinan Zhang Lin Feng | 2023 | Journal of Animal Science and Biotechnology2023，14，6： | 0 |
| 8 | 基于内镜图像深度学习的鼻咽恶性肿瘤检测模型的建立与验证显示文摘背景与目的由于鼻咽部解剖位置隐匿且腺体增生频发,活检时恶性肿瘤的阳性率较低,从而导致初诊时鼻咽恶性肿瘤确诊延时或漏诊。本文旨在建立一种人工智能工具——基于深度学习的内镜检查,来检测鼻咽恶性肿瘤。方法建立了一种基于内镜图像的鼻咽恶性肿瘤检测模型(endoscopic imagesbased nasopharyngeal malignancies detection model,eNPM-DM),该模型由基于空间结构的全卷积网络构成,采用单独训练集和验证集对分类和分割进行微调。总共收集了28,966张合格图像。其中,自2008年1月1日至2016年12月31日,从7951例个体中获得了27,536张经活检证实的图像,按照7∶1∶2的比例随机分为训练、验证和测试集。此外,将2017年1月1日到2017年3月31日获得的1430张图像纳入预测集,用以对建立模型的性能与肿瘤专家的评价进行比较。以鼻咽镜图像为背景,对自动分割和专家手工分割进行比较,采用dice相似系数(dice similarity coefficient,DSC)评价eNPM-DM从鼻咽部内镜图像的背景中自动分割出恶性肿瘤区域的效率。结果所有图像经过病理组织学验证,包括正常对照5713(19.7%)例、鼻咽癌(nasopharyngeal carcinoma,NPC)19,107(66.0%)例、其他恶性肿瘤335(1.2%)例和3811(13.2%)例良性病变。在测试集中,eNPM-DM检测恶性肿瘤的总准确率达88.7%[95%置信区间(confidence interval,CI):87.8%–89.5%]。在预测比较阶段,eNPM-DM表现优于专家:总准确率分别为88.0%(95%CI:86.1%–89.6%)和80.5%(95%CI:77.0%–84.0%)。eNPM-DM耗时更短(40 s vs. 110.0±5.8 min),且从背景中自动分割出鼻咽恶性肿瘤区域方面表现优秀,测试集和预测集中的平均DSC分别为0.78±0.24和0.75±0.26。结论 eNPM-DM在鼻咽肿块良性/恶性诊断分类方面优于肿瘤学家评估,并且实现了从鼻咽内镜图像背景中对恶性区域自动分割。 | Chaofeng Li Bingzhong Jing Liangru Ke Bin Li Weixiong Xia Caisheng He Chaonan Qian Chong Zhao Haiqiang Mai Mingyuan Chen Kajia Cao Haoyuan Mo Ling Guo Qiuyan Chen Linquan Tang Wenze Qiu Yahui Yu Hu Liang Xinjun Huang Guoying Liu Wangzhong Li Lin Wang Rui Sun Xiong Zou Shanshan Guo Peiyu Huang Donghua Luo Fang Qiu Yishan Wu Yijun Hua Kuiyuan Liu Shuhui Lv Jingjing Miao Yanqun Xiang Ying Sun Xiang Guo Xing Lv | 2019 | 癌症2019，38，7： | 0 |
| 9 | Co_(13)O_(8)—metalloxocubes:a new class of perovskite-like neutral clusters with cubic aromaticity显示文摘Exploring stable clusters to understand structural evolution from atoms to macroscopic matter and to construct new materials is interesting yet challenging in chemistry.Utilizing our newly developed deep-ultraviolet laser ionization mass spectrometry technique,here we observe the reactions of neutral cobalt clusters with oxygen and find a very stable cluster species of Co13O8 that dominates the mass distribution in the presence of a large flow rate of oxygen gas.The results of global-minimum structural search reveal a unique cubic structure and distinctive stability of the neutral Co13O8 cluster that forms a new class of metal oxides that we named as‘metalloxocubes’.Thermodynamics and kinetics calculations illustrate the structural evolution from icosahedral Co13 to the metalloxocube Co13O8 with decreased energy,enhanced stability and aromaticity.This class of neutral oxygen-passivated metal clusters may be an ideal candidate for genetic materials because of the cubic nature of the building blocks and the stability due to cubic aromaticity. | Lijun Geng Mouyi Weng Cong-Qiao Xu Hanyu Zhang Chaonan Cui Haiming Wu Xin Chen Mingyu Hu Hai Lin Zhen-Dong Sun Xi Wang Han-Shi Hu Jun Li Jiaxin Zheng Zhixun Luo Feng Pan Jiannian Yao | 2021 | National Science Review2021，8，1： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员