000180490 001__ 180490
000180490 005__ 20181203035952.0
000180490 037__ $$aCONF
000180490 245__ $$aEfficient Scanning for EM Based Target Localization
000180490 269__ $$a2012
000180490 260__ $$c2012
000180490 336__ $$aConference Papers
000180490 520__ $$aFor biologists studying the morphology of cells, Electron Microscopy (EM) is the method of choice with its {\it nm} resolution, across increasingly larger volumes. However, the time necessary to acquire such image series is long and often limits the amount samples are imaged. This paper presents a strategy for fast imaging and automated selection of regions of interest that significantly accelerates this process. In particular, this strategy involves scanning a tissue sample once, finding regions of interest in which target structures might be located, scanning these regions once again, and iterating the process until only relevant regions of the block face have been scanned repeatedly. For mitochondria and synapses, this approach is shown to produce near equal localization results to current state-of-the art techniques, and does so in almost a tenth of the time.
000180490 6531_ $$aComputer Vision, Electron Microscopy, Fast Imaging
000180490 700__ $$0245861$$aSznitman, Raphael$$g177109
000180490 700__ $$0242715$$aLucchi, Aurélien$$g185205
000180490 700__ $$0242720$$aPjescic-Emedi, Natasa$$g197227
000180490 700__ $$0240043$$aKnott, Graham$$g159872
000180490 700__ $$0240252$$aFua, Pascal$$g112366
000180490 7112_ $$a15th International Conference on Medical Image Computing and Computer Assisted Intervention$$cNice, France$$dOctober, 2012
000180490 8564_ $$s3894239$$uhttps://infoscience.epfl.ch/record/180490/files/MICCAI2012a.pdf$$yPreprint$$zPreprint
000180490 909C0 $$0252087$$pCVLAB$$xU10659
000180490 909C0 $$0252025$$pCIME$$xU10192
000180490 909CO $$ooai:infoscience.tind.io:180490$$pconf$$pIC$$pSB$$qGLOBAL_SET
000180490 917Z8 $$x177109
000180490 937__ $$aEPFL-CONF-180490
000180490 973__ $$aEPFL$$rREVIEWED$$sACCEPTED
000180490 980__ $$aCONF