Unmanned aerial vehicle(UAV)-based imaging systems have many superiorities compared with other platforms,such as high flexibility and low cost in collecting images,providing wide application prospects.However,the acqu...Unmanned aerial vehicle(UAV)-based imaging systems have many superiorities compared with other platforms,such as high flexibility and low cost in collecting images,providing wide application prospects.However,the acquisition of the UAV-based image commonly results in very high resolution and very large-scale images,which poses great challenges for subsequent applications.Therefore,an efficient representation of large-scale UAV images is necessary for the extraction of the required information in a reasonable time.In this work,we proposed a multi-scale hierarchical representation,i.e.binary partition tree,for analyzing large-scale UAV images.More precisely,we first obtained an initial partition of images by an oversegmentation algorithm,i.e.the simple linear iterative clustering.Next,we merged the similar superpixels to build an object-based hierarchical structure by fully considering the spectral and spatial information of the superpixels and their topological relationships.Moreover,objects of interest and optimal segmentation were obtained using object-based analysis methods with the hierarchical structure.Experimental results on processing the post-seismic UAV images of the 2013 Ya’an earthquake and the mosaic of images in the South-west of Munich demonstrate the effectiveness and efficiency of our proposed method.展开更多
Objective:Microchannels are associated with the progression of atherosclerotic vulnerable plaques.However,in patients with culprit optical coherence tomography(OCT)-defined plaque erosion,the knowledge of microchannel...Objective:Microchannels are associated with the progression of atherosclerotic vulnerable plaques.However,in patients with culprit optical coherence tomography(OCT)-defined plaque erosion,the knowledge of microchannels and culprit lesion vulnerability is limited.The aim of this study was to investigate culprit lesion characteristics in patients with ST-segment elevated myocardial infarction(STEMI)caused by plaque erosion with and without microchannels using OCT.Methods:In all,348 STEMI patients with plaque erosion who underwent OCT of the culprit lesion at the 2nd Affiliated Hospital of Harbin Medical University(Harbin,China)from August 2014 to December 2017 were included and divided into the microchannel group(n=116,33.3%)and no-microchannel group(n=232,66.7%).The clinical characteristics and OCT-derived plaque features were compared between both groups.Results:Among the 348 STEMI patients with plaque erosion,culprit lesions with microchannels had higher incidence of lipid plaque(59.5%vs.45.3%,P=0.012);calcification(41.4%vs.24.6%,P=0.002);spotty calcification(30.2%vs.18.1%,P=0.014);macrophages accumulation(72.4%vs.45.7%,P<0.001);and cholesterol crystals(32.8%vs.14.2%,P<0.001)than those without microchannels.In addition,minimal lumen area was smaller((1.9±0.9)mm2 vs.(2.8±2.3)mm2,P<0.001)and lumen area stenosis was greater((71.3%±13.4%)vs.(65.3%±19.3%),P=0.001)in the microchannel group than in the no-microchannel group.Conclusion:In patients with STEMI caused by plaque erosion,one-third manifested typical microchannel characteristics,and those with microchannels were associated with more severe luminal stenosis and more vulnerable plaque features than those without microchannels.展开更多
基金This work was supported in part by the National Key Basic Research and Development Program of China[grant number 2013CB733404]the National Natural Science Foundation of China[grant number 61271401],[grant number 91338113].
文摘Unmanned aerial vehicle(UAV)-based imaging systems have many superiorities compared with other platforms,such as high flexibility and low cost in collecting images,providing wide application prospects.However,the acquisition of the UAV-based image commonly results in very high resolution and very large-scale images,which poses great challenges for subsequent applications.Therefore,an efficient representation of large-scale UAV images is necessary for the extraction of the required information in a reasonable time.In this work,we proposed a multi-scale hierarchical representation,i.e.binary partition tree,for analyzing large-scale UAV images.More precisely,we first obtained an initial partition of images by an oversegmentation algorithm,i.e.the simple linear iterative clustering.Next,we merged the similar superpixels to build an object-based hierarchical structure by fully considering the spectral and spatial information of the superpixels and their topological relationships.Moreover,objects of interest and optimal segmentation were obtained using object-based analysis methods with the hierarchical structure.Experimental results on processing the post-seismic UAV images of the 2013 Ya’an earthquake and the mosaic of images in the South-west of Munich demonstrate the effectiveness and efficiency of our proposed method.
基金supported by the National Key R&D Program of China(grant No.2016YFC1301100 to BY)National Natural Science Foundation of China(grant No.81827806 to BY and No.82072091 to JD)Natural Science Foundation of Heilongjiang Province(grant No.YQ2020H017 to JD).
文摘Objective:Microchannels are associated with the progression of atherosclerotic vulnerable plaques.However,in patients with culprit optical coherence tomography(OCT)-defined plaque erosion,the knowledge of microchannels and culprit lesion vulnerability is limited.The aim of this study was to investigate culprit lesion characteristics in patients with ST-segment elevated myocardial infarction(STEMI)caused by plaque erosion with and without microchannels using OCT.Methods:In all,348 STEMI patients with plaque erosion who underwent OCT of the culprit lesion at the 2nd Affiliated Hospital of Harbin Medical University(Harbin,China)from August 2014 to December 2017 were included and divided into the microchannel group(n=116,33.3%)and no-microchannel group(n=232,66.7%).The clinical characteristics and OCT-derived plaque features were compared between both groups.Results:Among the 348 STEMI patients with plaque erosion,culprit lesions with microchannels had higher incidence of lipid plaque(59.5%vs.45.3%,P=0.012);calcification(41.4%vs.24.6%,P=0.002);spotty calcification(30.2%vs.18.1%,P=0.014);macrophages accumulation(72.4%vs.45.7%,P<0.001);and cholesterol crystals(32.8%vs.14.2%,P<0.001)than those without microchannels.In addition,minimal lumen area was smaller((1.9±0.9)mm2 vs.(2.8±2.3)mm2,P<0.001)and lumen area stenosis was greater((71.3%±13.4%)vs.(65.3%±19.3%),P=0.001)in the microchannel group than in the no-microchannel group.Conclusion:In patients with STEMI caused by plaque erosion,one-third manifested typical microchannel characteristics,and those with microchannels were associated with more severe luminal stenosis and more vulnerable plaque features than those without microchannels.