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 di...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.展开更多
Purpose-The purpose of the paper is to investigate the impact of various types of intergovernmental fiscal transfers on local public education expenditure at the county level in China and to estimate the leakage of ca...Purpose-The purpose of the paper is to investigate the impact of various types of intergovernmental fiscal transfers on local public education expenditure at the county level in China and to estimate the leakage of categorical subsidies for rural compulsory education.Design/Approach/Methods-It is a quantitative study.The paper constructs a quantile regression model and adopt data collected in 2007 for 1,985 counties in China to examine the impact of relevant fiscal transfers.Findings-The results reveal that most intergovernmental fiscal transfers exert a substitution effect on the local education expenditure,whereas subsidies for rural compulsory education from the Central Government have a crowding-out effect on education investments from local financial resources.Although the subsidy program generally narrows the education expenditure disparity across counties,there are heterogeneous effects across different regions.Originality/Value-The paper estimates and compares the impact of fiscal transfers on both the level and disparity of local public education in different regions,and provides a possible explanation for the crowding-out effect of fiscal transfers in China.展开更多
基金supported by the National Natural Science Foundation of China[Grant Nos.81572665,81672680,81472525,81702873]the International Cooperation Project of Science and Technology Plan of Guangdong Province[Grant No.2016A050502011]the Health&Medical Collaborative Innovation Project of Guangzhou City,China(Grant No.201604020003).
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.
基金This work has been supported by the National Social Science Foundation of China in Education(Grant No.:BFA140039).
文摘Purpose-The purpose of the paper is to investigate the impact of various types of intergovernmental fiscal transfers on local public education expenditure at the county level in China and to estimate the leakage of categorical subsidies for rural compulsory education.Design/Approach/Methods-It is a quantitative study.The paper constructs a quantile regression model and adopt data collected in 2007 for 1,985 counties in China to examine the impact of relevant fiscal transfers.Findings-The results reveal that most intergovernmental fiscal transfers exert a substitution effect on the local education expenditure,whereas subsidies for rural compulsory education from the Central Government have a crowding-out effect on education investments from local financial resources.Although the subsidy program generally narrows the education expenditure disparity across counties,there are heterogeneous effects across different regions.Originality/Value-The paper estimates and compares the impact of fiscal transfers on both the level and disparity of local public education in different regions,and provides a possible explanation for the crowding-out effect of fiscal transfers in China.
