Objective To explore the value of deep learning(DL)models semi-automatic training system for automatic optimization of clinical image quality control of transthoracic echocardiography(TTE).Methods Totally 1250 TTE vid...Objective To explore the value of deep learning(DL)models semi-automatic training system for automatic optimization of clinical image quality control of transthoracic echocardiography(TTE).Methods Totally 1250 TTE videos from 402 patients were retrospectively collected,including 490 apical four chamber(A4C),310 parasternal long axis view of left ventricle(PLAX)and 450 parasternal short axis view of great vessel(PSAX GV).The videos were divided into development set(245 A4C,155 PLAX,225 PSAX GV),semi-automated training set(98 A4C,62 PLAX,90 PSAX GV)and test set(147 A4C,93 PLAX,135 PSAX GV)at the ratio of 5∶2∶3.Based on development set and semi-automatic training set,DL model of quality control was semi-automatically iteratively optimized,and a semi-automatic training system was constructed,then the efficacy of DL models for recognizing TTE views and assessing imaging quality of TTE were verified in test set.Results After optimization,the overall accuracy,precision,recall,and F1 score of DL models for recognizing TTE views in test set improved from 97.33%,97.26%,97.26%and 97.26%to 99.73%,99.65%,99.77%and 99.71%,respectively,while the overall accuracy for assessing A4C,PLAX and PSAX GV TTE as standard views in test set improved from 89.12%,83.87%and 90.37%to 93.20%,90.32%and 93.33%,respectively.Conclusion The developed DL models semi-automatic training system could improve the efficiency of clinical imaging quality control of TTE and increase iteration speed.展开更多
Personal health records and electronic health records are considered as the most sensitive information in the healthcare domain.Several solutions have been provided for implementing the digital health system using blo...Personal health records and electronic health records are considered as the most sensitive information in the healthcare domain.Several solutions have been provided for implementing the digital health system using blockchain,but there are several challenges,such as secure access control and privacy is one of the prominent issues.Hence,we propose a novel framework and implemented an attribute-based access control system using blockchain.Moreover,we have also integrated artificial intelligence(AI)based approach to identify the behavior and activity for security reasons.The current methods only focus on the related clinical records received from a medical diagnosis.Moreover,existing methods are too inflexible to resourcefully sustenance metadata changes.A secure patient data access framework is proposed in this research,integrating blockchain,trust chain,and blockchain methods to overcome these problems in the literature for sharing and accessing digital healthcare data.We have used a neural network and classifier to categorize the user access to our proposed system.Our proposed scheme provides an intelligent and secure blockchain-based access control system in the digital healthcare system.Experimental results surpass the existing solutions by collecting attributes such as the number of transactions,number of nodes,transaction delay,block creation,and signature verification time.展开更多
Artificial intelligence(AI)has seen tremendous growth over the past decade and stands to disrupts the medical industry.In medicine,this has been applied in medical imaging and other digitised medical disciplines,but i...Artificial intelligence(AI)has seen tremendous growth over the past decade and stands to disrupts the medical industry.In medicine,this has been applied in medical imaging and other digitised medical disciplines,but in more traditional fields like medical physics,the adoption of AI is still at an early stage.Though AI is anticipated to be better than human in certain tasks,with the rapid growth of AI,there is increasing concerns for its usage.The focus of this paper is on the current landscape and potential future applications of artificial intelligence in medical physics and radiotherapy.Topics on AI for image acquisition,image segmentation,treatment delivery,quality assurance and outcome prediction will be explored as well as the interaction between human and AI.This will give insights into how we should approach and use the technology for enhancing the quality of clinical practice.展开更多
Electronic machines in the guise of digital computers have transformed our world―social,family,commerce,and politics―although not yet health.Each iteration spawns expectations of yet more astonishing wonders.We wait...Electronic machines in the guise of digital computers have transformed our world―social,family,commerce,and politics―although not yet health.Each iteration spawns expectations of yet more astonishing wonders.We wait for the next unbelievable invention to fall into our lap,possibly without limit.How realistic is this?What are the limits,and have we now reached them?A recent survey in The Economist suggests that we have.It describes cycles of misery,where inflated expectations are inevitably followed,a few years later,by disillusion.Yet another Artificial Intelligence(AI)winter is coming―“After years of hype,many people feel AI has failed to deliver”.The current paper not only explains why this was bound to happen,but offers a clear and simple pathway as to how to avoid it happening again.Costly investments in time and effort can only show solid,reliable benefits when full weight is given to the fundamental binary nature of the digital machine,and to the equally unique human faculty of‘intent’.‘Intent’is not easy to define;it suffers acutely from verbal fuzziness―a point made extensively in two earlier papers:“The scientific evidence that‘intent’is vital for healthcare”and“Why Quakerism is more scientific than Einstein”.This paper argues that by putting‘intent’centre stage,first healthcare,and then democracy can be rescued.Suppose every medical consultation were supported by realistic data usage?What if,using only your existing smartphone,your entire medical history were scanned,and instantly compared,within microseconds,with up-to-the-minute information on contraindications and efficacy,from around the globe,for the actual drug you were about to receive,before you actually received it?This is real-time retrieval of clinical data―it increases the security of both doctor and patient,in a way that is otherwise unachievable.My 1980 Ph.D.thesis extolled the merits of digitising the medical record―and,just as digitisation has changed our use of audio and video beyond recognition,so a data-rich medical consultation is unprecedented―prepare to be surprised.This paper has four sections:(1)where binaries help;(2)where binaries ensure extinction;(3)computers in healthcare and civilisation;and(4)data-rich doctoring.Health is vital for economic success,as the current pandemic demonstrates,inescapably.Politics,too,is routinely corrupted―unless we rectify both,failures in AI will be the least of our troubles.展开更多
文摘Objective To explore the value of deep learning(DL)models semi-automatic training system for automatic optimization of clinical image quality control of transthoracic echocardiography(TTE).Methods Totally 1250 TTE videos from 402 patients were retrospectively collected,including 490 apical four chamber(A4C),310 parasternal long axis view of left ventricle(PLAX)and 450 parasternal short axis view of great vessel(PSAX GV).The videos were divided into development set(245 A4C,155 PLAX,225 PSAX GV),semi-automated training set(98 A4C,62 PLAX,90 PSAX GV)and test set(147 A4C,93 PLAX,135 PSAX GV)at the ratio of 5∶2∶3.Based on development set and semi-automatic training set,DL model of quality control was semi-automatically iteratively optimized,and a semi-automatic training system was constructed,then the efficacy of DL models for recognizing TTE views and assessing imaging quality of TTE were verified in test set.Results After optimization,the overall accuracy,precision,recall,and F1 score of DL models for recognizing TTE views in test set improved from 97.33%,97.26%,97.26%and 97.26%to 99.73%,99.65%,99.77%and 99.71%,respectively,while the overall accuracy for assessing A4C,PLAX and PSAX GV TTE as standard views in test set improved from 89.12%,83.87%and 90.37%to 93.20%,90.32%and 93.33%,respectively.Conclusion The developed DL models semi-automatic training system could improve the efficiency of clinical imaging quality control of TTE and increase iteration speed.
基金This research was supported by Taif University Researchers Supporting Project number(TURSP-2020/98),Taif University,Taif,Saudi Arabia.
文摘Personal health records and electronic health records are considered as the most sensitive information in the healthcare domain.Several solutions have been provided for implementing the digital health system using blockchain,but there are several challenges,such as secure access control and privacy is one of the prominent issues.Hence,we propose a novel framework and implemented an attribute-based access control system using blockchain.Moreover,we have also integrated artificial intelligence(AI)based approach to identify the behavior and activity for security reasons.The current methods only focus on the related clinical records received from a medical diagnosis.Moreover,existing methods are too inflexible to resourcefully sustenance metadata changes.A secure patient data access framework is proposed in this research,integrating blockchain,trust chain,and blockchain methods to overcome these problems in the literature for sharing and accessing digital healthcare data.We have used a neural network and classifier to categorize the user access to our proposed system.Our proposed scheme provides an intelligent and secure blockchain-based access control system in the digital healthcare system.Experimental results surpass the existing solutions by collecting attributes such as the number of transactions,number of nodes,transaction delay,block creation,and signature verification time.
文摘Artificial intelligence(AI)has seen tremendous growth over the past decade and stands to disrupts the medical industry.In medicine,this has been applied in medical imaging and other digitised medical disciplines,but in more traditional fields like medical physics,the adoption of AI is still at an early stage.Though AI is anticipated to be better than human in certain tasks,with the rapid growth of AI,there is increasing concerns for its usage.The focus of this paper is on the current landscape and potential future applications of artificial intelligence in medical physics and radiotherapy.Topics on AI for image acquisition,image segmentation,treatment delivery,quality assurance and outcome prediction will be explored as well as the interaction between human and AI.This will give insights into how we should approach and use the technology for enhancing the quality of clinical practice.
文摘Electronic machines in the guise of digital computers have transformed our world―social,family,commerce,and politics―although not yet health.Each iteration spawns expectations of yet more astonishing wonders.We wait for the next unbelievable invention to fall into our lap,possibly without limit.How realistic is this?What are the limits,and have we now reached them?A recent survey in The Economist suggests that we have.It describes cycles of misery,where inflated expectations are inevitably followed,a few years later,by disillusion.Yet another Artificial Intelligence(AI)winter is coming―“After years of hype,many people feel AI has failed to deliver”.The current paper not only explains why this was bound to happen,but offers a clear and simple pathway as to how to avoid it happening again.Costly investments in time and effort can only show solid,reliable benefits when full weight is given to the fundamental binary nature of the digital machine,and to the equally unique human faculty of‘intent’.‘Intent’is not easy to define;it suffers acutely from verbal fuzziness―a point made extensively in two earlier papers:“The scientific evidence that‘intent’is vital for healthcare”and“Why Quakerism is more scientific than Einstein”.This paper argues that by putting‘intent’centre stage,first healthcare,and then democracy can be rescued.Suppose every medical consultation were supported by realistic data usage?What if,using only your existing smartphone,your entire medical history were scanned,and instantly compared,within microseconds,with up-to-the-minute information on contraindications and efficacy,from around the globe,for the actual drug you were about to receive,before you actually received it?This is real-time retrieval of clinical data―it increases the security of both doctor and patient,in a way that is otherwise unachievable.My 1980 Ph.D.thesis extolled the merits of digitising the medical record―and,just as digitisation has changed our use of audio and video beyond recognition,so a data-rich medical consultation is unprecedented―prepare to be surprised.This paper has four sections:(1)where binaries help;(2)where binaries ensure extinction;(3)computers in healthcare and civilisation;and(4)data-rich doctoring.Health is vital for economic success,as the current pandemic demonstrates,inescapably.Politics,too,is routinely corrupted―unless we rectify both,failures in AI will be the least of our troubles.
