Skin lesion segmentation based on preprocessing, thresholding and neural networks
Abstract
This abstract describes the segmentation system used to participate in the challenge ISIC 2017: Skin Lesion Analysis Towards Melanoma Detection. Several preprocessing techniques have been tested for three color representations (RGB, YCbCr and HSV) of 392 images. Results have been used to choose the better preprocessing for each channel. In each case a neural network is trained to predict the Jaccard Index based on object characteristics. The system includes black frames and reference circle detection algorithms but no special treatment is done for hair removal. Segmentation is performed in two steps first the best channel to be segmented is chosen by selecting the best neural network output. If this output does not predict a Jaccard Index over 0.5 a more aggressive preprocessing is performed using open and close morphological operations and the segmentation of the channel that obtains the best output from the neural networks is selected as the lesion.
- Publication:
-
arXiv e-prints
- Pub Date:
- March 2017
- DOI:
- 10.48550/arXiv.1703.04845
- arXiv:
- arXiv:1703.04845
- Bibcode:
- 2017arXiv170304845G
- Keywords:
-
- Computer Science - Computer Vision and Pattern Recognition
- E-Print:
- 4 pages, 4 figures, abstract submitted to participate in the challenge ISIC 2017