Matches in SemOpenAlex for { <https://semopenalex.org/work/W3150625474> ?p ?o ?g. }
- W3150625474 abstract "Abstract Newly developed technologies have made it feasible to routinely collect highly multiplexed (20-60 channel) images at subcellular resolution from human tissues for research and diagnostic purposes. Extracting single cell data from such images requires efficient and accurate image segmentation. This starts with identification of nuclei, a challenging problem in tissue imaging that has recently benefited from the use of deep learning. In this paper, we demonstrate two generally applicable approaches to improving segmentation accuracy for multiple human tissues. The first involves the use of “real augmentations” during training. These augmentations comprise defocused and saturated image data and improve model accuracy whereas computational augmentation (Gaussian blurring) does not. The second involves collection of nuclear envelope data to better identify nuclear outlines. The two approaches cumulatively and substantially improve segmentation with three different deep learning frameworks, yielding a set of highly accurate segmentation models. We speculate that the use of real augmentations may have applications in image processing outside of microscopy." @default.
- W3150625474 created "2021-04-13" @default.
- W3150625474 creator A5009819619 @default.
- W3150625474 creator A5010234110 @default.
- W3150625474 creator A5013576797 @default.
- W3150625474 creator A5029778986 @default.
- W3150625474 creator A5030146315 @default.
- W3150625474 creator A5038566732 @default.
- W3150625474 creator A5043151044 @default.
- W3150625474 creator A5049217703 @default.
- W3150625474 creator A5051189984 @default.
- W3150625474 creator A5078284942 @default.
- W3150625474 creator A5085365474 @default.
- W3150625474 date "2021-06-21" @default.
- W3150625474 modified "2023-09-26" @default.
- W3150625474 title "UnMICST: Deep learning with real augmentation for robust segmentation of highly multiplexed images of human tissues" @default.
- W3150625474 cites W151377110 @default.
- W3150625474 cites W1560814177 @default.
- W3150625474 cites W1861492603 @default.
- W3150625474 cites W1873848535 @default.
- W3150625474 cites W1901129140 @default.
- W3150625474 cites W1977544680 @default.
- W3150625474 cites W1999045972 @default.
- W3150625474 cites W2003345727 @default.
- W3150625474 cites W2004915807 @default.
- W3150625474 cites W2012050899 @default.
- W3150625474 cites W2015255108 @default.
- W3150625474 cites W2019062120 @default.
- W3150625474 cites W2026448092 @default.
- W3150625474 cites W2043565262 @default.
- W3150625474 cites W2048992185 @default.
- W3150625474 cites W2053129129 @default.
- W3150625474 cites W2062083469 @default.
- W3150625474 cites W2067903551 @default.
- W3150625474 cites W2095705004 @default.
- W3150625474 cites W2107751484 @default.
- W3150625474 cites W2108598243 @default.
- W3150625474 cites W2133059825 @default.
- W3150625474 cites W2142332605 @default.
- W3150625474 cites W2161092951 @default.
- W3150625474 cites W2163605009 @default.
- W3150625474 cites W2189343552 @default.
- W3150625474 cites W2194775991 @default.
- W3150625474 cites W2312947295 @default.
- W3150625474 cites W2398665893 @default.
- W3150625474 cites W2471088120 @default.
- W3150625474 cites W2499316477 @default.
- W3150625474 cites W2507783863 @default.
- W3150625474 cites W2538840351 @default.
- W3150625474 cites W2553978783 @default.
- W3150625474 cites W2560023338 @default.
- W3150625474 cites W2573152477 @default.
- W3150625474 cites W2601810315 @default.
- W3150625474 cites W2689259083 @default.
- W3150625474 cites W2791711748 @default.
- W3150625474 cites W2798643036 @default.
- W3150625474 cites W2811106513 @default.
- W3150625474 cites W2832881433 @default.
- W3150625474 cites W2887439422 @default.
- W3150625474 cites W2891113118 @default.
- W3150625474 cites W2895303488 @default.
- W3150625474 cites W2902652978 @default.
- W3150625474 cites W2919115771 @default.
- W3150625474 cites W2922020904 @default.
- W3150625474 cites W2949238013 @default.
- W3150625474 cites W2954996726 @default.
- W3150625474 cites W2956683695 @default.
- W3150625474 cites W2963803174 @default.
- W3150625474 cites W2964282006 @default.
- W3150625474 cites W2965013520 @default.
- W3150625474 cites W2968292465 @default.
- W3150625474 cites W2972737141 @default.
- W3150625474 cites W2975634117 @default.
- W3150625474 cites W2980998394 @default.
- W3150625474 cites W2981435216 @default.
- W3150625474 cites W2982049401 @default.
- W3150625474 cites W3003771668 @default.
- W3150625474 cites W3014464364 @default.
- W3150625474 cites W3014831329 @default.
- W3150625474 cites W3015600294 @default.
- W3150625474 cites W3016787828 @default.
- W3150625474 cites W3023126733 @default.
- W3150625474 cites W3034457289 @default.
- W3150625474 cites W3036637668 @default.
- W3150625474 cites W3040981459 @default.
- W3150625474 cites W3045580189 @default.
- W3150625474 cites W3048399453 @default.
- W3150625474 cites W3084433974 @default.
- W3150625474 cites W3084995528 @default.
- W3150625474 cites W3092564080 @default.
- W3150625474 cites W3100296314 @default.
- W3150625474 cites W3105222690 @default.
- W3150625474 cites W3106310718 @default.
- W3150625474 cites W3111521801 @default.
- W3150625474 cites W3137493842 @default.
- W3150625474 cites W3148551472 @default.
- W3150625474 cites W3159807469 @default.
- W3150625474 cites W832971097 @default.
- W3150625474 cites W855272188 @default.
- W3150625474 cites W2801765418 @default.