1naresh
Array ( [urn:ac.highwire.org:guest:identity] => Array ( [runtime-id] => urn:ac.highwire.org:guest:identity [type] => guest [service-id] => ajnr-ac.highwire.org [access-type] => Controlled [privilege] => Array ( [urn:ac.highwire.org:guest:privilege] => Array ( [runtime-id] => urn:ac.highwire.org:guest:privilege [type] => privilege-set [privilege-set] => GUEST ) ) [credentials] => Array ( [method] => guest ) ) ) 1nareshArray ( [urn:ac.highwire.org:guest:identity] => Array ( [runtime-id] => urn:ac.highwire.org:guest:identity [type] => guest [service-id] => ajnr-ac.highwire.org [access-type] => Controlled [privilege] => Array ( [urn:ac.highwire.org:guest:privilege] => Array ( [runtime-id] => urn:ac.highwire.org:guest:privilege [type] => privilege-set [privilege-set] => GUEST ) ) [credentials] => Array ( [method] => guest ) ) )Table 3:Ablation study on CT cross-validation folds
Model ROC-AUC Accuracy Sensitivity Specificity NCCT-DL 0.7404 (0.0560) 0.7813 (0.0221) 0.7882 (0.1377) 0.7629 (0.0819) CTA-DL 0.7385 (0.0535) 0.7812 (0.0442) 0.7823 (0.1080) 0.8026 (0.1246) MNT-DL 0.7801 (0.0320) 0.7979 (0.0592) 0.7923 (0.1303) 0.8066 (0.0947) MNT-DL+SSL 0.8719 (0.0831)a 0.8688 (0.0640) 0.9381 (0.0852) 0.8058 (0.1202)
↵a Best performance.