A GAN-based image synthesis method for skin lesion classification
- PMID: 32526536
- DOI: 10.1016/j.cmpb.2020.105568
A GAN-based image synthesis method for skin lesion classification
Abstract
Background and objective: There are many types of skin cancer, and melanoma is the most lethal one. Dermoscopy is an important imaging technique to screen melanoma and other skin lesions. However, Skin lesion classification based on computer-aided diagnostic techniques is a challenging task owing to the scarcity of labeled data and class-imbalanced dataset. It is necessary to apply data augmentation technique based on generative adversarial networks (GANs) to skin lesion classification for helping dermatologists in more accurate diagnostic decisions.
Methods: A whole process of using GAN-based data augmentation technology to improve the skin lesion classification performance has been established in this article. First of all, the skin lesion style-based GANs is proposed according to the basic architecture of style-based GANs. The proposed model modifies the structure of style control and noise input in the original generator, adjusts both the generator and discriminator to efficiently synthesize high-quality skin lesion images. As for image classification, the classifier is constructed on the pretrained deep neural network using transfer learning method. The synthetic images from the proposed skin lesion style-based GANs are finally added to the training set to help train the classifier for better classification performance.
Results: The proposed skin lesion style-based GAN has been evaluated by Inception Score (IS), Fréchet Inception Distance (FID), Precision and Recall, and is superior to other compared GAN models in these quantitative evaluation metrics. By adding the synthesized images to the training set, the main classification indicators like accuracy, sensitivity, specificity, average precision and balanced multiclass accuracy are 95.2%, 83.2%, 74.3%, 96.6% and 83.1% on the dataset of International Skin Imaging Collaboration (ISIC) 2018 Challenge, which have been improved by 1.6%, 24.4%, 3.6%, 23.2% and 5.6% respectively compared to the CNN model.
Conclusions: The proposed skin lesion style-based GANs can generate high-quality skin lesion images efficiently, leading to the performance improvement of the classification model. This work provides a valuable reference for medical image analysis based on deep learning.
Keywords: Data augmentation; Generative adversarial networks; Image synthesis; Skin lesion classification; Transfer learning.
Copyright © 2020 Elsevier B.V. All rights reserved.
Conflict of interest statement
Declaration of Competing Interest The authors have no conflict of interest.
Similar articles
-
Skin Lesion Synthesis and Classification Using an Improved DCGAN Classifier.Diagnostics (Basel). 2023 Aug 9;13(16):2635. doi: 10.3390/diagnostics13162635. Diagnostics (Basel). 2023. PMID: 37627894 Free PMC article.
-
Multiple skin lesions diagnostics via integrated deep convolutional networks for segmentation and classification.Comput Methods Programs Biomed. 2020 Jul;190:105351. doi: 10.1016/j.cmpb.2020.105351. Epub 2020 Jan 23. Comput Methods Programs Biomed. 2020. PMID: 32028084
-
Enhancing classification of cells procured from bone marrow aspirate smears using generative adversarial networks and sequential convolutional neural network.Comput Methods Programs Biomed. 2022 Sep;224:107019. doi: 10.1016/j.cmpb.2022.107019. Epub 2022 Jul 10. Comput Methods Programs Biomed. 2022. PMID: 35878483
-
Deep Learning Approaches Towards Skin Lesion Segmentation and Classification from Dermoscopic Images - A Review.Curr Med Imaging. 2020;16(5):513-533. doi: 10.2174/1573405615666190129120449. Curr Med Imaging. 2020. PMID: 32484086 Review.
-
Combating COVID-19 Using Generative Adversarial Networks and Artificial Intelligence for Medical Images: Scoping Review.JMIR Med Inform. 2022 Jun 29;10(6):e37365. doi: 10.2196/37365. JMIR Med Inform. 2022. PMID: 35709336 Free PMC article. Review.
Cited by
-
Brain tumor segmentation using synthetic MR images - A comparison of GANs and diffusion models.Sci Data. 2024 Feb 29;11(1):259. doi: 10.1038/s41597-024-03073-x. Sci Data. 2024. PMID: 38424097 Free PMC article.
-
Artificial Intelligence Applied to Non-Invasive Imaging Modalities in Identification of Nonmelanoma Skin Cancer: A Systematic Review.Cancers (Basel). 2024 Feb 1;16(3):629. doi: 10.3390/cancers16030629. Cancers (Basel). 2024. PMID: 38339380 Free PMC article. Review.
-
Multimodal data fusion for cancer biomarker discovery with deep learning.Nat Mach Intell. 2023 Apr;5(4):351-362. doi: 10.1038/s42256-023-00633-5. Epub 2023 Apr 6. Nat Mach Intell. 2023. PMID: 37693852 Free PMC article.
-
Precision in Dermatology: Developing an Optimal Feature Selection Framework for Skin Lesion Classification.Diagnostics (Basel). 2023 Sep 2;13(17):2848. doi: 10.3390/diagnostics13172848. Diagnostics (Basel). 2023. PMID: 37685386 Free PMC article.
-
A synthetic data generation system for myalgic encephalomyelitis/chronic fatigue syndrome questionnaires.Sci Rep. 2023 Aug 31;13(1):14256. doi: 10.1038/s41598-023-40364-6. Sci Rep. 2023. PMID: 37652910 Free PMC article.
MeSH terms
LinkOut - more resources
Full Text Sources
Medical
Research Materials