%0 Journal Article
%T Similar image search for histopathology: SMILY
%A Carrie J. Cai
%A Craig H. Mermel
%A Daniel Smilkov
%A Emily Reif
%A Greg S. Corrado
%A Jason D. Hipp
%A Lily H. Peng
%A Mahul B. Amin
%A Martin C. Stumpe
%A Michael Emmert-Buck
%A Michael Terry
%A Narayan Hegde
%A Phil Q. Nelson
%A Yun Liu
%J Archive of "NPJ Digital Medicine".
%D 2019
%R 10.1038/s41746-019-0131-z
%X Overview of Similar Medical Images Like Yours (SMILY). First, a database of image patches and a numerical characterization of each patch¡¯s image contents (termed the embedding) is created. SMILY uses a convolutional neural network to compute this embedding (schematic used for illustration purposes only, see Methods for architecture descriptions). Next, when a query image is selected, SMILY computes the embedding of that query image and compares the embedding with those in the database in a computationally efficient manner. Finally, SMILY returns the k most similar patches, where k is customizabl
%K Machine learning
%K Machine learning
%K Medical imaging
%K Image processing
%K Software
%U https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6588631/