Artificial soft actuators,featured with non-equilibrium internal circumstance and fast,programmable shape transformations,have attracted strong research interest recently due to their flexibility,highly controllable,a...Artificial soft actuators,featured with non-equilibrium internal circumstance and fast,programmable shape transformations,have attracted strong research interest recently due to their flexibility,highly controllable,and designability.However,wireless soft actuators,achieving the locomotion on different large slopes with multiple energy conversion,have been rarely reported.Herein,we create a asymmetric bilayer strategy to construct autonomous soft crawler via“breathing”moisture to motivate the mechanical deformation.The soft crawlers present conspicuous performances including periodic tumbler locomotion predicted via improved Timoshenko’s equation,multiple reversible shape-morphing(circle,helix,despiralization,etc.)determined by their fiber orientation,controlled drive mode(front drive and rear drive)and rapid climb speed(4.76 cm/min)at wide slope angles.Through architecture design,they can be series-wound or shunt-wound to construct multijoint complex actuators.Besides climbing,a intelligent soft ring-pull with admirable cycle performance for preventing overheating or something untouchable,has been proposed.The soft crawlers also realize multiple energy conversion to be actuated by light irradiation.We envision that this soft crawler system has an enormous potential in intelligent machine,microscopic diagnosis and treatment,biosensing,energy harvesting and conversion.展开更多
AIM:To propose an algorithm for automatic detection of diabetic retinopathy(DR)lesions based on ultra-widefield scanning laser ophthalmoscopy(SLO).METHODS:The algorithm utilized the FasterRCNN(Faster Regions with CNN ...AIM:To propose an algorithm for automatic detection of diabetic retinopathy(DR)lesions based on ultra-widefield scanning laser ophthalmoscopy(SLO).METHODS:The algorithm utilized the FasterRCNN(Faster Regions with CNN features)+ResNet50(Residua Network 50)+FPN(Feature Pyramid Networks)method for detecting hemorrhagic spots,cotton wool spots,exudates,and microaneurysms in DR ultra-widefield SLO.Subimage segmentation combined with a deeper residual network FasterRCNN+ResNet50 was employed for feature extraction to enhance intelligent learning rate.Feature fusion was carried out by the feature pyramid network FPN,which significantly improved lesion detection rates in SLO fundus images.RESULTS:By analyzing 1076 ultra-widefield SLO images provided by our hospital,with a resolution of 2600×2048 dpi,the accuracy rates for hemorrhagic spots,cotton wool spots,exudates,and microaneurysms were found to be 87.23%,83.57%,86.75%,and 54.94%,respectively.CONCLUSION:The proposed algorithm demonstrates intelligent detection of DR lesions in ultra-widefield SLO,providing significant advantages over traditional fundus color imaging intelligent diagnosis algorithms.展开更多
基金financially supported by the National Natural Science Foundation of China(Nos.22001175,51973118,22175121 and 52003160)Key-Area Research and Development Program of Guangdong Province(Nos.2019B010929002 and 2019B010941001)+3 种基金the Natural Science Foundation of Guangdong Province(No.2020A1515010644)the Program for Guangdong Introducing Innovative and Enterpreneurial Teams(No.2019ZT08C642)Shenzhen Science and Technology Program(Nos.JCYJ20210324095412035,JCYJ20190808113005643,JCYJ20170818093832350 and JCYJ20180507184711069)the start-up fund of Shenzhen University(No.000002110820)。
文摘Artificial soft actuators,featured with non-equilibrium internal circumstance and fast,programmable shape transformations,have attracted strong research interest recently due to their flexibility,highly controllable,and designability.However,wireless soft actuators,achieving the locomotion on different large slopes with multiple energy conversion,have been rarely reported.Herein,we create a asymmetric bilayer strategy to construct autonomous soft crawler via“breathing”moisture to motivate the mechanical deformation.The soft crawlers present conspicuous performances including periodic tumbler locomotion predicted via improved Timoshenko’s equation,multiple reversible shape-morphing(circle,helix,despiralization,etc.)determined by their fiber orientation,controlled drive mode(front drive and rear drive)and rapid climb speed(4.76 cm/min)at wide slope angles.Through architecture design,they can be series-wound or shunt-wound to construct multijoint complex actuators.Besides climbing,a intelligent soft ring-pull with admirable cycle performance for preventing overheating or something untouchable,has been proposed.The soft crawlers also realize multiple energy conversion to be actuated by light irradiation.We envision that this soft crawler system has an enormous potential in intelligent machine,microscopic diagnosis and treatment,biosensing,energy harvesting and conversion.
基金Supported by Hunan Provincial Science and Technology Department Clinical Medical Technology Innovation Guidance Project(No.2021SK50103)。
文摘AIM:To propose an algorithm for automatic detection of diabetic retinopathy(DR)lesions based on ultra-widefield scanning laser ophthalmoscopy(SLO).METHODS:The algorithm utilized the FasterRCNN(Faster Regions with CNN features)+ResNet50(Residua Network 50)+FPN(Feature Pyramid Networks)method for detecting hemorrhagic spots,cotton wool spots,exudates,and microaneurysms in DR ultra-widefield SLO.Subimage segmentation combined with a deeper residual network FasterRCNN+ResNet50 was employed for feature extraction to enhance intelligent learning rate.Feature fusion was carried out by the feature pyramid network FPN,which significantly improved lesion detection rates in SLO fundus images.RESULTS:By analyzing 1076 ultra-widefield SLO images provided by our hospital,with a resolution of 2600×2048 dpi,the accuracy rates for hemorrhagic spots,cotton wool spots,exudates,and microaneurysms were found to be 87.23%,83.57%,86.75%,and 54.94%,respectively.CONCLUSION:The proposed algorithm demonstrates intelligent detection of DR lesions in ultra-widefield SLO,providing significant advantages over traditional fundus color imaging intelligent diagnosis algorithms.
