Multi-class Semantic Segmentation of Skin Lesions via Fully Convolutional Networks

被引:4
作者
Goyal, Manu [1 ]
Yap, Moi Hoon [2 ]
Hassanpour, Saeed [1 ,3 ,4 ]
机构
[1] Dartmouth Coll, Dept Biomed Data Sci, Hanover, NH 03755 USA
[2] Manchester Metropolitan Univ, Visual Comp Lab, Manchester, Lancs, England
[3] Dartmouth Coll, Dept Comp Sci, Hanover, NH 03755 USA
[4] Dartmouth Coll, Dept Epidemiol, Hanover, NH 03755 USA
来源
PROCEEDINGS OF THE 13TH INTERNATIONAL JOINT CONFERENCE ON BIOMEDICAL ENGINEERING SYSTEMS AND TECHNOLOGIES, VOL 3: BIOINFORMATICS | 2020年
关键词
Skin Cancer; Fully Convolutional Networks; Multi-class Segmentation; Lesion Diagnosis;
D O I
10.5220/0009380302900295
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
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.
引用
收藏
页码:290 / 295
页数:6
相关论文
共 18 条
  • [1] [Anonymous], 2015, P IEEE C COMP VIS PA P IEEE C COMP VIS PA, DOI DOI 10.1109/CVPR.2015.7298965
  • [2] [Anonymous], 2015, Nature, DOI [DOI 10.1038/NATURE14539, 10.1038/nature14539]
  • [3] [Anonymous], 2017, 2017 INT S BIOM IM I
  • [4] [Anonymous], 2017, IEEE T MED IMAGING
  • [5] [Anonymous], 2014, INT J COMPUT VISION
  • [6] Bi L., 2017, IEEE T BIOMEDICAL EN
  • [7] Dvorankova B., 2017, PROTOPLASMA, P1
  • [8] The PASCAL Visual Object Classes Challenge: A Retrospective
    Everingham, Mark
    Eslami, S. M. Ali
    Van Gool, Luc
    Williams, Christopher K. I.
    Winn, John
    Zisserman, Andrew
    [J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 2015, 111 (01) : 98 - 136
  • [9] Garcia-Garcia A., 2017, ARXIV170406857
  • [10] Goyal M., 2017, ARXIV170801928