|
|
|
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 | Efficient synthesis of poly(oxymethylene) dimethyl ethers over PVP-stabilized heteropolyacids through self-assembly显示文摘A series of polyvinylpyrrolidone-stabilized heteropolyacids(PVP-HPAs)are generated by self-assembly of HPAs and PVP in methanol.The PVP-HPAs are then employed as catalysts for the synthesis of poly(oxymethylene)dimethyl ethers(DMMn,n1)by the methanolysis of trioxane.The results suggest that the acidity of PVP-HPAs is tunable by changing the ratio of PVP and HPAs,which is a key factor for the selectivity of the DMMn product.By optimizing the composition and reaction conditions,two types of PVP-HPA,PVP-phosphotungstic acid(PVP-HPW)in a PVP/HPW ratio of 1/4:1 and PVP-silicotungstic acid(PVP-HSi W)in a PVP/HSi W ratio of 1/4:3/4,respectively afford 52.4%and 50.3%yields of DMM2–5.The optimized catalysts are reusable for a minimum of 10 times without a significant drop in performance. | Xiaolong Fang Jin Chen Linmin Ye Haiqiang Lin Youzhu Yuan | 2015 | Science China Chemistry2015，58，1： | 4 |
| 3 | Improved performance of magnetically recoverable Ce-promoted Ni/ A1203 catalysts for aqueous-phase hydrogenolysis of sorbi- tol to glycols显示文摘 | e Linmin Duma Xinping Lin Haiqiang | 2012 | Catalysis Today2012，183，1： | 1 |
| 4 | Performance of Gold Nanoparticles Supported on Carbon Nanotubes for Selective Oxidation of Cyclooctene with Use of O2 and TBHP显示文摘 | Bodong Li Ping He Guangquan Yi Haiqiang Lin Youzhu Yuan | 2009 | Catalysis Letters (-)2009，，1： | 1 |
| 5 | Effect of boric oxide doping on the stability and activity of a Cu-SiO2 catalyst for vapor-phase hydrogenation of dimethyl oxalate to ethylene glycol显示文摘 | He Zhe Lin Haiqiang He Ping | 2011 | J Catal2011，277，1： | 1 |
| 6 | Effect of boric oxide doping on the stability and activity of a Cu-SiO : catalyst for vapor-phase hydrogenation of dimethyl oxalate to ethylene glycol 显示文摘 | He Zhe Lin Haiqiang He Ping | 2011 | Journal of Catalysis2011，277，1： | 1 |
| 7 | Effect of boric oxide doping on the stability and activity of a Cu–SiO 2 catalyst for vapor-phase hydrogenation of dimethyl oxalate to ethylene glycol显示文摘 | Zhe He Haiqiang Lin Ping He Youzhu Yuan | 2010 | Journal of Catalysis2010，，1： | 1 |
| 8 | Improved performance of magnetically recoverable Ce-promoted Ni/Al 2 O 3 catalysts for aqueous-phase hydrogenolysis of sorbitol to glycols显示文摘 | Linmin Ye Xinping Duan Haiqiang Lin Youzhu Yuan | 2011 | Catalysis Today2011，，1： | 1 |
| 9 | Improved performance of magnetically recoverable Ce-promoted Ni/Al2O3 catalysts for aqueous-phase hydrogenolysis of sorbitol to glycols显示文摘 | Ye Linmin Duan Xinping Lin Haiqiang | | 0，，01： | 1 |
| 10 | Establishment of a prognostic scoring model for regional recurrent nasopharyngeal carcinoma after neck dissection显示文摘Objective:The main aim of this study was to establish a scoring model to predict risk of progression and survival in patients with regionally recurrent nasopharyngeal carcinoma(NPC).Methods:Three hundred and forty-eight patients subjected to neck dissection from 2003 to 2017 were included for study.Clinicopathologic information for each patient was analyzed.Independent prognostic factors were selected using the Cox proportional hazards model and incorporated into the scoring model.Concordance index(C-index)and calibration curves were used to verify discrimination and calibration,respectively and the results validated using bootstrap resampling.Results:Microscopic positive lymph node>2[hazard ratio(HR),2.19;95%confidence interval(CI),1.30–3.68;P=0.003],extranodal extension(HR,2.75;95%CI,1.69–4.47;P<0.001),and lower neck involvement(HR,1.78;95%CI,1.04–3.04;P=0.034)were identified from multivariate analysis as independent factors for overall survival(OS).A qualitative 4-point scale was generated to stratify patients into 4 risk groups for predicting OS and progression-free survival(PFS).The novel scoring model demonstrated enhanced discrimination(C-index=0.69;95%CI,0.62–0.76)relative to the original recurrent tumor-node-metastasis(rTNM)staging system(C-index=0.56;95%CI,0.50–0.62),and was internally validated with a bootstrap-adjusted C-index of 0.70.The calibration curve showed good agreement between predicted probabilities and actual observations.Conclusions:The scoring system established in this study based on a large regionally recurrent NPC cohort fills a gap regarding assessment of risk and prediction of survival outcomes after neck dissection in this population and could be further applied to identify high-risk patients who may benefit from more aggressive intervention. | Xiaoyun Li Chao Lin Jinjie Yan Qiuyan Chen Xuesong Sun Sailan Liu Shanshan Guo Liting Liu Haojun Xie Qingnan Tang Yujing Liang Ling Guo Hao Li Xuekui Liu Xiang Guo Linquan Tang Haiqiang Mai | 2020 | Cancer Biology & Medicine2020，17，1： | 0 |
| 11 | Reuse of Industrial Heritage Based on “Leisure-Holiday Tourism Complex”显示文摘Tourism development, as a novel approach in the reuse of industrial heritage, is conducive to the settlement of issues of urban industrial heritage conservation. However, in practical terms, the development of industrial heritage as tourist resources, has encountered problems including monotonous development projects, the lack of tourism facilities, low economic efficiency, poor sustainability of project operation, etc.. This paper, based on the transformation plan of Salt Manufacturing Plant in Qingjiang County of Zhangshu, Jiangxi, proposes that a leisure-holiday tourism complex can be used as the development model of the reuse of industrial heritage at a time when the reuse of industrial heritage is advised to shift from a single mode to a compound mode. Specifically, it is suggested that industrial raw materials are developed into tourism resources to fully excavate relevant history and culture, for the purpose of achieving the coordinated economic and social growth of the reuse of industrial heritage. | ZHOU Bo LIN Zhu YANG Haotian LIU Ting QU Haiqiang | 2017 | Journal of Landscape Research2017，9，3： | 0 |
| 12 | 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 |
您所在的机构暂未开通此部分的功能，请联系管理员