Dear editor,This letter presents an automatic data augmentation algorithm for medical image segmentation.To increase the scale and diversity of medical images,we propose a differentiable automatic data augmentation al...Dear editor,This letter presents an automatic data augmentation algorithm for medical image segmentation.To increase the scale and diversity of medical images,we propose a differentiable automatic data augmentation algorithm based on proximal update by finding an optimal augmentation policy.Specifically,on the one hand,a dedicated search space is designed for the medical image segmentation task.On the other hand,we introduce a proximal differentiable gradient descent strategy to update the data augmentation policy,which would increase the searching efficiency.Results of the experiments indicate that the proposed algorithm significantly outperforms state-of-the-art methods,and search speed is 10 times faster than state-of-the-art methods.展开更多
Although stimulus frequency otoacoustic emissions (SFOAEs) have been used as a non-invasive measure of cochlear mechanics, clinical and experimental application of SFOAEs has been limited by difficulties in accurately...Although stimulus frequency otoacoustic emissions (SFOAEs) have been used as a non-invasive measure of cochlear mechanics, clinical and experimental application of SFOAEs has been limited by difficulties in accurately deriving quantitative information from sound pressure measured in the ear canal. In this study, a novel signal processing method for multicomponent analysis (MCA) was used to measure the amplitude and delay of the SFOAE. This report shows the delay-frequency distribution of the SFOAE measured from the human ear. A low level acoustical suppressor near the probe tone significantly suppressed the SFOAE, strongly indicating that the SFOAE was generated at characteristic frequency locations. Information derived from this method may reveal more details of cochlear mechanics in the human ear.展开更多
基金This work was supported by the National Natural Science Foundation of China(62073126)the Hunan Provincial Natural Science Foundation of China(2020JJ2008)+1 种基金the Key Research and Development Program of Hunan Province(2022WK2011)the Science and Technology Program of Changsha(897202102345).
文摘Dear editor,This letter presents an automatic data augmentation algorithm for medical image segmentation.To increase the scale and diversity of medical images,we propose a differentiable automatic data augmentation algorithm based on proximal update by finding an optimal augmentation policy.Specifically,on the one hand,a dedicated search space is designed for the medical image segmentation task.On the other hand,we introduce a proximal differentiable gradient descent strategy to update the data augmentation policy,which would increase the searching efficiency.Results of the experiments indicate that the proposed algorithm significantly outperforms state-of-the-art methods,and search speed is 10 times faster than state-of-the-art methods.
基金Supported in part by research grants from the National Institute of Deafness and Other Communication Disorders(R01 DC 00141 and R03 DC033642)the National Institutes of Health+2 种基金the Research Fund of the American Otological Societythe Medical Research Foundation of OregonVA RR&D Center Grant RCTR-597-0160,Portland,VAMC
文摘Although stimulus frequency otoacoustic emissions (SFOAEs) have been used as a non-invasive measure of cochlear mechanics, clinical and experimental application of SFOAEs has been limited by difficulties in accurately deriving quantitative information from sound pressure measured in the ear canal. In this study, a novel signal processing method for multicomponent analysis (MCA) was used to measure the amplitude and delay of the SFOAE. This report shows the delay-frequency distribution of the SFOAE measured from the human ear. A low level acoustical suppressor near the probe tone significantly suppressed the SFOAE, strongly indicating that the SFOAE was generated at characteristic frequency locations. Information derived from this method may reveal more details of cochlear mechanics in the human ear.