RT Journal Article
SR Electronic
T1 Skin Lesion Segmentation with Improved C-UNet Networks
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 382549
DO 10.1101/382549
A1 Jiang, Hongda
A1 Rong, Ruichen
A1 Wu, Junyan
A1 Li, Xiaoxiao
A1 Dong, Xu
A1 Chen, Eric Z
YR 2018
UL http://biorxiv.org/content/early/2018/08/01/382549.abstract
AB —This paper proposes an innovative method for Part1, skin lesion segmentation of the ISIC 2018 Challenge. Our network C-UNet is based on UNet network, we combined several methods on this basic network which made some improvements on Jaccard Index ultimately, our method yield an average Jaccard Index of 0.77 on the On-line validation dataset.