CVMar 15, 2017
Automatic skin lesion segmentation with fully convolutional-deconvolutional networks
arXiv:1703.05165v218 citations
Originality Synthesis-oriented
AI Analysis
This work addresses a domain-specific medical imaging task for healthcare applications, with incremental improvements.
The paper tackled the problem of automatic skin lesion segmentation for melanoma detection, achieving competitive results in the ISBI Challenge 2017.
This paper summarizes our method and validation results for the ISBI Challenge 2017 - Skin Lesion Analysis Towards Melanoma Detection - Part I: Lesion Segmentation