Classification of dermoscopy patterns using deep convolutional neural networks Conference Paper
| Authors: | Demyanov, S.; Chakravorty, R.; Abedini, M.; Halpern, A.; Garnavi, R. |
| Title: | Classification of dermoscopy patterns using deep convolutional neural networks |
| Conference Title: | 2016 IEEE 13th International Symposium on Biomedical Imaging: From Nano to Macro |
| Abstract: | Detection of dermoscopic patterns, such as typical network and regular globules, is an important step in the skin lesion analysis. This is one of the steps, required to compute the ABCD-score, commonly used for lesion type classification. In this article, we investigate the possibility of automatically detect dermoscopic patterns using deep convolutional neural networks and other image classification algorithms. For the evaluation, we employ the dataset obtained through collaboration with the International Skin Imaging Collaboration (ISIC), including 211 lesions manually annotated by domain experts, generating over 2000 samples of each class (network and globules). Experimental results demonstrates that we can correctly classify 88% of network examples, and 83% of globules example. The best results are achieved by a convolutional neural network with 8 layers. © 2016 IEEE. |
| Keywords: | dermoscopy; medical imaging; diagnosis; pattern recognition; neural networks; skin imaging; deep learning; image classification; convolution; convolutional networks; dermoscopy patterns; network layers; convolutional neural network; domain experts; image classification algorithms; type classifications |
| Journal Title | International Symposium on Biomedical Imaging. Proceedings |
| Conference Dates: | 2016 Apr 13-16 |
| Conference Location: | Prague, Czech Republic |
| ISBN: | 1945-7928 |
| Publisher: | IEEE |
| Date Published: | 2016-01-01 |
| Start Page: | 364 |
| End Page: | 368 |
| Language: | English |
| DOI: | 10.1109/isbi.2016.7493284 |
| PROVIDER: | scopus |
| DOI/URL: | |
| Notes: | Conference Paper -- Conference code: 122357 -- Export Date: 2 August 2016 -- 13 April 2016 through 16 April 2016 -- Source: Scopus |
