Abstract | ||
---|---|---|
Melanoma is clinically difficult to distinguish from common benign skin lesions, particularly melanocytic naevus and seborrhoeic keratosis. The dermoscopic appearance of these lesions has huge intra-class variations and high inter-class visual similarities. Most current research is focusing on single-class segmentation irrespective of classes of skin lesions. In this work, we evaluate the performance of deep learning on multi-class segmentation of ISIC-2017 challenge dataset, which consists of 2,750 dermoscopic images. We propose an end-to-end solution using fully convolutional networks (FCNs) for multi-class semantic segmentation to automatically segment the melanoma, seborrhoeic keratosis and naevus. To improve the performance of FCNs, transfer learning and a hybrid loss function are used. We evaluate the performance of the deep learning segmentation methods for multi-class segmentation and lesion diagnosis (with post-processing method) on the testing set of the ISIC-2017 challenge dataset. The results showed that the two-tier level transfer learning RCN-8s achieved the overall best result with Dice score of 78.5% in a naevus category, 65.3% in melanoma, and 55.7% in seborrhoeic keratosis in multi-class segmentation and Accuracy of 84.62% for recognition of melanoma in lesion diagnosis. |
Year | DOI | Venue |
---|---|---|
2017 | 10.5220/0009380302900295 | arXiv: Computer Vision and Pattern Recognition |
Keywords | Field | DocType |
Skin Cancer, Fully Convolutional Networks, Multi-class Segmentation, Lesion Diagnosis | Early detection,Pattern recognition,Skin lesion,Computer science,Segmentation,Skin cancer,Transfer of learning,Artificial intelligence,Melanoma,Deep learning,Dice,Machine learning | Journal |
Volume | Citations | PageRank |
abs/1711.10449 | 3 | 0.38 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Manu Goyal | 1 | 4 | 0.76 |
Moi Hoon Yap | 2 | 190 | 27.82 |
Saeed Hassanpour | 3 | 52 | 10.54 |