Assessing the effectiveness of artificial intelligence methods for melanoma: A retrospective review - 11/10/19
, Zeyin Zhao, MS a, Hongduo Chen, MD b, Kaixin Song, BA a, Amer A.A. Abdulrahman, MD b, Yining Wang, BM b, John Z.S. Chen, MD c, Shuo Chen, PhD a, Yue Zhao, PhD a, Xinghua Gao, MD bAbstract |
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.
Le texte complet de cet article est disponible en PDF.Key words : artificial intelligence, classification, deep learning, melanoma diagnosis, segmentation, traditional machine learning
Abbreviations used : LR, SVM, VGG
Plan
| Authors Cui and Wei contributed equally to this article. |
|
| Funding sources: Supported by the National Natural Science Foundation of China (71621061, 61605025, 81673070, 81872538), the 111 Project (B16009, D18011), and the Fundamental Research Funds for the Central Universities (N171904006, N171902001, N172410006-2). |
|
| Conflicts of interest: None disclosed. |
Vol 81 - N° 5
P. 1176-1180 - novembre 2019 Retour au numéro
Article précédent
- Immune checkpoint inhibitors and the development of granulomatous reactions
- Christine M. Cornejo, Paul Haun, Joseph English, Misha Rosenbach
- A case for case reports: A retrospective evaluation of the case reports published in the Journal of the American Academy of Dermatology in 2000
- Reid A. Waldman, Eric Chen, Justin Finch, Jane M. Grant-Kels
Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.
Déjà abonné à cette revue ?