Table 4.xls (5.5 kB)
Download fileClassification performance achieved with the model trained on non-bone-suppressed and bone-suppressed images.
dataset
posted on 2022-03-31, 17:48 authored by Sivaramakrishnan Rajaraman, Gregg Cohen, Lillian Spear, Les Folio, Sameer AntaniData in parenthesis denote the 95% binomial CI measured as the Exact Clopper Pearson interval for the MCC metric. Bold numerical values denote superior performance in respective columns.
History
Usage metrics
Categories
Keywords
impacted adversely duefeature pyramid networksbony structures like7977 ± 16207 ), multidiv >< pdetecting findings consistent9848 ± 03 performing modelsimprove disease detectionautomatic bone suppressionfindings consistentautomatic detectionperforming boneindividual models0073 ),suppression modeldisease classificationbone suppressionsuppresses bonessuppressed imagessuppressed cxrssuppressed counterpartsseveral sourcesrays mayprivate collectionpeak signalp noise ratiomodel trainedhypothesis usingfrontal cxrscxr imagesconstructed usingconfidence interval8255 ))
