The automatic and accurate classification of Magnetic Resonance Imaging(MRI)radiology report is essential for the analysis and interpretation epilepsy and non-epilepsy.Since the majority of MRI radiology reports are u...The automatic and accurate classification of Magnetic Resonance Imaging(MRI)radiology report is essential for the analysis and interpretation epilepsy and non-epilepsy.Since the majority of MRI radiology reports are unstructured,the manual information extraction is time-consuming and requires specific expertise.In this paper,a comprehensive method is proposed to classify epilepsy and non-epilepsy real brain MRI radiology text reports automatically.This method combines the Natural Language Processing technique and statisticalMachine Learning methods.122 realMRI radiology text reports(97 epilepsy,25 non-epilepsy)are studied by our proposed method which consists of the following steps:(i)for a given text report our systems first cleans HTML/XML tags,tokenize,erase punctuation,normalize text,(ii)then it converts into MRI text reports numeric sequences by using indexbased word encoding,(iii)then we applied the deep learning models that are uni-directional long short-term memory(LSTM)network,bidirectional long short-term memory(BiLSTM)network and convolutional neural network(CNN)for the classifying comparison of the data,(iv)finally,we used 70%of used for training,15%for validation,and 15%for test observations.Unlike previous methods,this study encompasses the following objectives:(a)to extract significant text features from radiologic reports of epilepsy disease;(b)to ensure successful classifying accuracy performance to enhance epilepsy data attributes.Therefore,our study is a comprehensive comparative study with the epilepsy dataset obtained from numeric sequences by using index-based word encoding method applied for the deep learning models.The traditionalmethod is numeric sequences by using index-based word encoding which has been made for the first time in the literature,is successful feature descriptor in the epilepsy data set.The BiLSTM network has shown a promising performance regarding the accuracy rates.We show that the larger sizedmedical text reports can be analyzed by our proposed method.展开更多
Recently,a new kind of machine intelligence was born,called as UI(Ubit intelligence).The basic difference between UI and AI is encoding;UI is based on word encoding;but AI is based on character encoding.UI machine can...Recently,a new kind of machine intelligence was born,called as UI(Ubit intelligence).The basic difference between UI and AI is encoding;UI is based on word encoding;but AI is based on character encoding.UI machine can learn from human,remember the characters,pronunciation,and meaning of a word like human.UI machine can think among the character,pronunciation,and meaning of words like human.Turing Test is similar to a teacher testing a student;Before Test,tester must teach the content of the test questions to UI machine first;after UI machine learning,tester asks testee questions;to check testee has remembered what he taught;to check testee can think among character,pronunciation,and meaning of words.This paper demonstrates that testee can remember what testee taught;and answer all 6 questions correctly by thinking.UI machine passes Turing Test easily and successfully with score 100.Following on,the works related to this study is briefly introduced.At last,this paper concludes that UI machine is based on word encoding,can form word,form concept,can possess brain like intelligence,also can possess human like Intelligence;therefore UI machine passes Turing Test easily and successfully.On the contrary,AI machine is based on character encoding;can’t form word;can’t form concept,AI machine can’t possess brain like intelligence,nor possess human like Intelligence.Therefore,AI machine can’t pass Turing Test.展开更多
文摘The automatic and accurate classification of Magnetic Resonance Imaging(MRI)radiology report is essential for the analysis and interpretation epilepsy and non-epilepsy.Since the majority of MRI radiology reports are unstructured,the manual information extraction is time-consuming and requires specific expertise.In this paper,a comprehensive method is proposed to classify epilepsy and non-epilepsy real brain MRI radiology text reports automatically.This method combines the Natural Language Processing technique and statisticalMachine Learning methods.122 realMRI radiology text reports(97 epilepsy,25 non-epilepsy)are studied by our proposed method which consists of the following steps:(i)for a given text report our systems first cleans HTML/XML tags,tokenize,erase punctuation,normalize text,(ii)then it converts into MRI text reports numeric sequences by using indexbased word encoding,(iii)then we applied the deep learning models that are uni-directional long short-term memory(LSTM)network,bidirectional long short-term memory(BiLSTM)network and convolutional neural network(CNN)for the classifying comparison of the data,(iv)finally,we used 70%of used for training,15%for validation,and 15%for test observations.Unlike previous methods,this study encompasses the following objectives:(a)to extract significant text features from radiologic reports of epilepsy disease;(b)to ensure successful classifying accuracy performance to enhance epilepsy data attributes.Therefore,our study is a comprehensive comparative study with the epilepsy dataset obtained from numeric sequences by using index-based word encoding method applied for the deep learning models.The traditionalmethod is numeric sequences by using index-based word encoding which has been made for the first time in the literature,is successful feature descriptor in the epilepsy data set.The BiLSTM network has shown a promising performance regarding the accuracy rates.We show that the larger sizedmedical text reports can be analyzed by our proposed method.
文摘Recently,a new kind of machine intelligence was born,called as UI(Ubit intelligence).The basic difference between UI and AI is encoding;UI is based on word encoding;but AI is based on character encoding.UI machine can learn from human,remember the characters,pronunciation,and meaning of a word like human.UI machine can think among the character,pronunciation,and meaning of words like human.Turing Test is similar to a teacher testing a student;Before Test,tester must teach the content of the test questions to UI machine first;after UI machine learning,tester asks testee questions;to check testee has remembered what he taught;to check testee can think among character,pronunciation,and meaning of words.This paper demonstrates that testee can remember what testee taught;and answer all 6 questions correctly by thinking.UI machine passes Turing Test easily and successfully with score 100.Following on,the works related to this study is briefly introduced.At last,this paper concludes that UI machine is based on word encoding,can form word,form concept,can possess brain like intelligence,also can possess human like Intelligence;therefore UI machine passes Turing Test easily and successfully.On the contrary,AI machine is based on character encoding;can’t form word;can’t form concept,AI machine can’t possess brain like intelligence,nor possess human like Intelligence.Therefore,AI machine can’t pass Turing Test.
