Objectives:Chronic rhinosinusitis is one of the common diseases that cause morbidity and affects a person's quality of life.We tried to provide a more appropriate and effective approach to selecting patients for e...Objectives:Chronic rhinosinusitis is one of the common diseases that cause morbidity and affects a person's quality of life.We tried to provide a more appropriate and effective approach to selecting patients for endoscopic sinus surgery.Methods:The study population is chronic rhinosinusitis children referred to the ear,nose,and throat clinic of two general hospitals in Tehran,Iran,who have previously undergone sufficient drug treatment and have not recovered.The Lund–Mackay score is calculated by examining the computed tomography(CT)scan.The Sino-nasal Outcome Test-22(SNOT-22)questionnaire was provided to the patients before the operation,after the operation,and 3 and 6 months later in the clinic.Results:Before the operation,the most SNOT-22 score people were in the range of 40–59 points.The SNOT-22 score before the operation is significantly different from 3 and 6 months after the operation.The highest frequency of Lund–Mackay CT(LMCT)scan score was in the range of 18–23 points.The LMCT scan score did not show any significant relationship with the SNOT-22 score before surgery,3 months,and 6 months after surgery.Sensitivity to aspirin had a significant relationship with SNOT-22 scores and the history of asthma and nasal polyps had a significant relationship with the preoperative LMCT scan score.Conclusions:The LMCT scan scoring system cannot be a good measure of chronic rhinosinusitis severity or the prognosis of patients after surgery.The SNOT-22 questionnaire can be used as a predictive tool to help the doctor and the patient in deciding to operate and the possibility of obtaining a relative recovery.展开更多
An iterative procedure introduced in MacKay’s evidence framework is often used for estimating the hyperparameter in empirical Bayes.Together with the use of a particular form of prior,the estimation of the hyperparam...An iterative procedure introduced in MacKay’s evidence framework is often used for estimating the hyperparameter in empirical Bayes.Together with the use of a particular form of prior,the estimation of the hyperparameter reduces to an automatic relevance determination model,which provides a soft way of pruning model parameters.Despite the effectiveness of this estimation procedure,it has stayed primarily as a heuristic to date and its application to deep neural network has not yet been explored.This paper formally investigates the mathematical nature of this procedure and justifies it as a well-principled algorithm framework,which we call the MacKay algorithm.As an application,we demonstrate its use in deep neural networks,which have typically complicated structure with millions of parameters and can be pruned to reduce the memory requirement and boost computational efficiency.In experiments,we adopt MacKay algorithm to prune the parameters of both simple networks such as LeNet,deep convolution VGG-like networks,and residual netowrks for large image classification task.Experimental results show that the algorithm can compress neural networks to a high level of sparsity with little loss of prediction accuracy,which is comparable with the state-of-the-art.展开更多
文摘Objectives:Chronic rhinosinusitis is one of the common diseases that cause morbidity and affects a person's quality of life.We tried to provide a more appropriate and effective approach to selecting patients for endoscopic sinus surgery.Methods:The study population is chronic rhinosinusitis children referred to the ear,nose,and throat clinic of two general hospitals in Tehran,Iran,who have previously undergone sufficient drug treatment and have not recovered.The Lund–Mackay score is calculated by examining the computed tomography(CT)scan.The Sino-nasal Outcome Test-22(SNOT-22)questionnaire was provided to the patients before the operation,after the operation,and 3 and 6 months later in the clinic.Results:Before the operation,the most SNOT-22 score people were in the range of 40–59 points.The SNOT-22 score before the operation is significantly different from 3 and 6 months after the operation.The highest frequency of Lund–Mackay CT(LMCT)scan score was in the range of 18–23 points.The LMCT scan score did not show any significant relationship with the SNOT-22 score before surgery,3 months,and 6 months after surgery.Sensitivity to aspirin had a significant relationship with SNOT-22 scores and the history of asthma and nasal polyps had a significant relationship with the preoperative LMCT scan score.Conclusions:The LMCT scan scoring system cannot be a good measure of chronic rhinosinusitis severity or the prognosis of patients after surgery.The SNOT-22 questionnaire can be used as a predictive tool to help the doctor and the patient in deciding to operate and the possibility of obtaining a relative recovery.
基金This work was supported partly by China Scholarship Council(201706020062)by China 973 program(2015CB358700)+2 种基金by the National Natural Science Foundation of China(Grant Nos.61772059,61421003)by the Beijing Advanced Innovation Center for Big Data and Brain Computing(BDBC)State Key Laboratory of Software Development Environment(SKLSDE-2018ZX-17).
文摘An iterative procedure introduced in MacKay’s evidence framework is often used for estimating the hyperparameter in empirical Bayes.Together with the use of a particular form of prior,the estimation of the hyperparameter reduces to an automatic relevance determination model,which provides a soft way of pruning model parameters.Despite the effectiveness of this estimation procedure,it has stayed primarily as a heuristic to date and its application to deep neural network has not yet been explored.This paper formally investigates the mathematical nature of this procedure and justifies it as a well-principled algorithm framework,which we call the MacKay algorithm.As an application,we demonstrate its use in deep neural networks,which have typically complicated structure with millions of parameters and can be pruned to reduce the memory requirement and boost computational efficiency.In experiments,we adopt MacKay algorithm to prune the parameters of both simple networks such as LeNet,deep convolution VGG-like networks,and residual netowrks for large image classification task.Experimental results show that the algorithm can compress neural networks to a high level of sparsity with little loss of prediction accuracy,which is comparable with the state-of-the-art.
