CANDI: An R package and Shiny app for annotating radiographs and evaluating computer-aided diagnosis. Badgeley, M., Liu, M., Glicksberg, B., Shervey, M., Zech, J., Shameer, K., Lehar, J., Oermann, E., McConnell, M., Snyder, T., & Dudley, J. Bioinformatics, 2019. abstract bibtex © The Author(s) 2018. Published by Oxford University Press. All rights reserved. Motivation: Radiologists have used algorithms for Computer-Aided Diagnosis (CAD) for decades. These algorithms use machine learning with engineered features, and there have been mixed findings on whether they improve radiologists' interpretations. Deep learning offers superior performance but requires more training data and has not been evaluated in joint algorithm-radiologist decision systems. Results: We developed the Computer-Aided Note and Diagnosis Interface (CANDI) for collaboratively annotating radiographs and evaluating how algorithms alter human interpretation. The annotation app collects classification, segmentation, and image captioning training data, and the evaluation app randomizes the availability of CAD tools to facilitate clinical trials on radiologist enhancement.
@article{
title = {CANDI: An R package and Shiny app for annotating radiographs and evaluating computer-aided diagnosis},
type = {article},
year = {2019},
identifiers = {[object Object]},
volume = {35},
id = {d3cda417-37dd-3a8f-95cd-2d920d725cd5},
created = {2020-02-12T23:00:35.242Z},
file_attached = {false},
profile_id = {dc457df6-1c54-3ce3-91fb-2bfb14727f31},
last_modified = {2020-02-12T23:00:35.242Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {false},
hidden = {false},
private_publication = {false},
abstract = {© The Author(s) 2018. Published by Oxford University Press. All rights reserved. Motivation: Radiologists have used algorithms for Computer-Aided Diagnosis (CAD) for decades. These algorithms use machine learning with engineered features, and there have been mixed findings on whether they improve radiologists' interpretations. Deep learning offers superior performance but requires more training data and has not been evaluated in joint algorithm-radiologist decision systems. Results: We developed the Computer-Aided Note and Diagnosis Interface (CANDI) for collaboratively annotating radiographs and evaluating how algorithms alter human interpretation. The annotation app collects classification, segmentation, and image captioning training data, and the evaluation app randomizes the availability of CAD tools to facilitate clinical trials on radiologist enhancement.},
bibtype = {article},
author = {Badgeley, M.A. and Liu, M. and Glicksberg, B.S. and Shervey, M. and Zech, J. and Shameer, K. and Lehar, J. and Oermann, E.K. and McConnell, M.V. and Snyder, T.M. and Dudley, J.T.},
journal = {Bioinformatics},
number = {9}
}
Downloads: 0
{"_id":"W8LAprRnmAhubh46X","bibbaseid":"badgeley-liu-glicksberg-shervey-zech-shameer-lehar-oermann-etal-candianrpackageandshinyappforannotatingradiographsandevaluatingcomputeraideddiagnosis-2019","authorIDs":["5e4481c4ec14b3de0100003f","vnw2XdwpRvyFDmjpf"],"author_short":["Badgeley, M.","Liu, M.","Glicksberg, B.","Shervey, M.","Zech, J.","Shameer, K.","Lehar, J.","Oermann, E.","McConnell, M.","Snyder, T.","Dudley, J."],"bibdata":{"title":"CANDI: An R package and Shiny app for annotating radiographs and evaluating computer-aided diagnosis","type":"article","year":"2019","identifiers":"[object Object]","volume":"35","id":"d3cda417-37dd-3a8f-95cd-2d920d725cd5","created":"2020-02-12T23:00:35.242Z","file_attached":false,"profile_id":"dc457df6-1c54-3ce3-91fb-2bfb14727f31","last_modified":"2020-02-12T23:00:35.242Z","read":false,"starred":false,"authored":"true","confirmed":false,"hidden":false,"private_publication":false,"abstract":"© The Author(s) 2018. Published by Oxford University Press. All rights reserved. Motivation: Radiologists have used algorithms for Computer-Aided Diagnosis (CAD) for decades. These algorithms use machine learning with engineered features, and there have been mixed findings on whether they improve radiologists' interpretations. Deep learning offers superior performance but requires more training data and has not been evaluated in joint algorithm-radiologist decision systems. Results: We developed the Computer-Aided Note and Diagnosis Interface (CANDI) for collaboratively annotating radiographs and evaluating how algorithms alter human interpretation. The annotation app collects classification, segmentation, and image captioning training data, and the evaluation app randomizes the availability of CAD tools to facilitate clinical trials on radiologist enhancement.","bibtype":"article","author":"Badgeley, M.A. and Liu, M. and Glicksberg, B.S. and Shervey, M. and Zech, J. and Shameer, K. and Lehar, J. and Oermann, E.K. and McConnell, M.V. and Snyder, T.M. and Dudley, J.T.","journal":"Bioinformatics","number":"9","bibtex":"@article{\n title = {CANDI: An R package and Shiny app for annotating radiographs and evaluating computer-aided diagnosis},\n type = {article},\n year = {2019},\n identifiers = {[object Object]},\n volume = {35},\n id = {d3cda417-37dd-3a8f-95cd-2d920d725cd5},\n created = {2020-02-12T23:00:35.242Z},\n file_attached = {false},\n profile_id = {dc457df6-1c54-3ce3-91fb-2bfb14727f31},\n last_modified = {2020-02-12T23:00:35.242Z},\n read = {false},\n starred = {false},\n authored = {true},\n confirmed = {false},\n hidden = {false},\n private_publication = {false},\n abstract = {© The Author(s) 2018. Published by Oxford University Press. All rights reserved. Motivation: Radiologists have used algorithms for Computer-Aided Diagnosis (CAD) for decades. These algorithms use machine learning with engineered features, and there have been mixed findings on whether they improve radiologists' interpretations. Deep learning offers superior performance but requires more training data and has not been evaluated in joint algorithm-radiologist decision systems. Results: We developed the Computer-Aided Note and Diagnosis Interface (CANDI) for collaboratively annotating radiographs and evaluating how algorithms alter human interpretation. The annotation app collects classification, segmentation, and image captioning training data, and the evaluation app randomizes the availability of CAD tools to facilitate clinical trials on radiologist enhancement.},\n bibtype = {article},\n author = {Badgeley, M.A. and Liu, M. and Glicksberg, B.S. and Shervey, M. and Zech, J. and Shameer, K. and Lehar, J. and Oermann, E.K. and McConnell, M.V. and Snyder, T.M. and Dudley, J.T.},\n journal = {Bioinformatics},\n number = {9}\n}","author_short":["Badgeley, M.","Liu, M.","Glicksberg, B.","Shervey, M.","Zech, J.","Shameer, K.","Lehar, J.","Oermann, E.","McConnell, M.","Snyder, T.","Dudley, J."],"bibbaseid":"badgeley-liu-glicksberg-shervey-zech-shameer-lehar-oermann-etal-candianrpackageandshinyappforannotatingradiographsandevaluatingcomputeraideddiagnosis-2019","role":"author","urls":{},"downloads":0},"bibtype":"article","biburl":"http://www.bibsonomy.org/bib/author/glicksberg?items=1000","creationDate":"2020-02-12T22:52:52.293Z","downloads":0,"keywords":["dblp"],"search_terms":["candi","package","shiny","app","annotating","radiographs","evaluating","computer","aided","diagnosis","badgeley","liu","glicksberg","shervey","zech","shameer","lehar","oermann","mcconnell","snyder","dudley"],"title":"CANDI: An R package and Shiny app for annotating radiographs and evaluating computer-aided diagnosis","year":2019,"dataSources":["aYHFHdNCGdBXvwdDZ"]}