Assessing the effectiveness of artificial intelligence methods for melanoma: A retrospective review
| Autor: | Kaixin Song, Amer A.A. Abdulrahman, Yining Wang, Yue Zhao, Hong-Duo Chen, Xiaoyu Cui, Xing-Hua Gao, Ran Wei, Gong Lixin, Ruiqun Qi, Zeyin Zhao, John Z. S. Chen, Shuo Chen |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Skin Neoplasms
business.industry Deep learning Big data Reproducibility of Results Dermoscopy Dermatology Convolutional neural network Sensitivity and Specificity Support vector machine Data set 030207 dermatology & venereal diseases 03 medical and health sciences 0302 clinical medicine Artificial Intelligence 030220 oncology & carcinogenesis Feature (machine learning) Medicine Humans Segmentation Artificial intelligence Transfer of learning business Melanoma Retrospective Studies |
| Zdroj: | Journal of the American Academy of Dermatology. 81(5) |
| ISSN: | 1097-6787 |
| Popis: | Background Artificial intelligence methods for the classification of melanoma have been studied extensively. However, few studies compare these methods under the same standards. Objective To seek the best artificial intelligence method for diagnosis of melanoma. Methods The contrast test used 2200 dermoscopic images. Image segmentations, feature extractions, and classifications were performed in sequence for evaluation of traditional machine learning algorithms. The recent popular convolutional neural network frameworks were used for transfer learning training classification. Results The region growing algorithm has the best segmentation performance, with an intersection over union of 70.06% and a false-positive rate of 17.67%. Classification performance was better with logistic regression, with a sensitivity of 76.36% and a specificity of 87.04%. The Inception V3 model (Google, Mountain View, CA) worked best in deep learning algorithms: the accuracy was 93.74%, the sensitivity was 94.36%, and the specificity was 85.64%. Limitations There was no division in the severity of melanoma samples used in this experiment. The data set was relatively small for deep learning. Conclusion The performance of traditional machine learning is satisfactory for the small data set of melanoma dermoscopic images, and the potential for deep learning in the future big data era is enormous. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect