In recent years,with the development of artificial intelligence,especially deep learning technology,researches on automatic detection of cerebrovascular diseases on medical images have made tremendous progress and the...In recent years,with the development of artificial intelligence,especially deep learning technology,researches on automatic detection of cerebrovascular diseases on medical images have made tremendous progress and these models are gradually entering into clinical practice.However,because of the complexity and flexibility of the deep learning algorithms,these researches have great variability on model building,validation process,performance description and results interpretation.The lack of a reliable,consistent,standardized design protocol has,to a certain extent,affected the progress of clinical translation and technology development of computer aided detection systems.After reviewing a large number of literatures and extensive discussion with domestic experts,this position paper put forward recommendations of standardized design on the key steps of deep learning-based automatic image detection models for cerebrovascular diseases.With further research and application expansion,this position paper would continue to be updated and gradually extended to evaluate the generalizability and clinical application efficacy of such tools.展开更多
基金Project supported by the Key Program of the National Natural Sci-ence Foundation of China(Grant Nos.81830057 and 82230068)the Young Scientists Fund of the National Natural Science Foundation of China(Grant No.82102155).
文摘In recent years,with the development of artificial intelligence,especially deep learning technology,researches on automatic detection of cerebrovascular diseases on medical images have made tremendous progress and these models are gradually entering into clinical practice.However,because of the complexity and flexibility of the deep learning algorithms,these researches have great variability on model building,validation process,performance description and results interpretation.The lack of a reliable,consistent,standardized design protocol has,to a certain extent,affected the progress of clinical translation and technology development of computer aided detection systems.After reviewing a large number of literatures and extensive discussion with domestic experts,this position paper put forward recommendations of standardized design on the key steps of deep learning-based automatic image detection models for cerebrovascular diseases.With further research and application expansion,this position paper would continue to be updated and gradually extended to evaluate the generalizability and clinical application efficacy of such tools.