Skip to main content

Table 5 Evaluation of DilatedSkinNet trained with ISIC 2018 and tested on \(PH^{2}\), ISIC 2016 and 2017 tests sets

From: Automatic lesion segmentation using atrous convolutional deep neural networks in dermoscopic skin cancer images

Datatset

ACC

JAC

DICE

\(PH^{2}\)

0.900

0.891

0.708

ISIC 2016 test set

0.950

0.904

0.949

ISIC 2017 test set

0.888

0.818

0.884