Automatic Diagnosis of Melanoma Based on EfficientNet and Patch Strategy
Abstract Melanoma is a fatal skin disease, and there are many challenging tasks in the detection of melanoma through neural network at this stage. We propose a new method for melanoma diagnosis based on EfficientNet and patch strategy. The diagnosis method has three stages of operation. First, Cycle...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Springer
2023-05-01
|
Series: | International Journal of Computational Intelligence Systems |
Subjects: | |
Online Access: | https://doi.org/10.1007/s44196-023-00246-1 |
_version_ | 1797822698873683968 |
---|---|
author | Qingxu Zou Jinyong Cheng Zhenlu Liang |
author_facet | Qingxu Zou Jinyong Cheng Zhenlu Liang |
author_sort | Qingxu Zou |
collection | DOAJ |
description | Abstract Melanoma is a fatal skin disease, and there are many challenging tasks in the detection of melanoma through neural network at this stage. We propose a new method for melanoma diagnosis based on EfficientNet and patch strategy. The diagnosis method has three stages of operation. First, Cyclegan is applied offline to synthesize the under-represented category samples from the over-represented category samples, and the original image and the synthesized samples are combined into a new training set to complete the conditional image synthesis task; second, we creatively propose the patch strategy and implement the patch algorithm, and apply the patch strategy offline to obtain the patch image of the newly merged training set; finally, the newly merged training set and the obtained patch image are sent to the classification network. Where, the model we proposed is composed of three parts: Basic Convolutional Neural Network, Auxiliary Convolutional Neural Network, and Fusion Convolutional Neural Network, and applies a weighted integration strategy. We evaluated the proposed method on the ISIC 2016 Skin Injury Challenge classification dataset. Experiments show that the patch strategy plays an important role in the field of melanoma classification, and the melanoma detection method proposed in this paper obtains an accuracy of 0.852 and an AUC value of 0.854 on the test set. This method can focus the attention of the classification network on the meaningful area of the skin lesion image through manual intervention, and can effectively solve the problem of category imbalance, thereby improving the performance of skin lesion classification. |
first_indexed | 2024-03-13T10:12:58Z |
format | Article |
id | doaj.art-d0a95e16027e4d8aa1894c023bcb8f39 |
institution | Directory Open Access Journal |
issn | 1875-6883 |
language | English |
last_indexed | 2024-03-13T10:12:58Z |
publishDate | 2023-05-01 |
publisher | Springer |
record_format | Article |
series | International Journal of Computational Intelligence Systems |
spelling | doaj.art-d0a95e16027e4d8aa1894c023bcb8f392023-05-21T11:26:55ZengSpringerInternational Journal of Computational Intelligence Systems1875-68832023-05-0116111810.1007/s44196-023-00246-1Automatic Diagnosis of Melanoma Based on EfficientNet and Patch StrategyQingxu Zou0Jinyong Cheng1Zhenlu Liang2School of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences)School of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences)School of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences)Abstract Melanoma is a fatal skin disease, and there are many challenging tasks in the detection of melanoma through neural network at this stage. We propose a new method for melanoma diagnosis based on EfficientNet and patch strategy. The diagnosis method has three stages of operation. First, Cyclegan is applied offline to synthesize the under-represented category samples from the over-represented category samples, and the original image and the synthesized samples are combined into a new training set to complete the conditional image synthesis task; second, we creatively propose the patch strategy and implement the patch algorithm, and apply the patch strategy offline to obtain the patch image of the newly merged training set; finally, the newly merged training set and the obtained patch image are sent to the classification network. Where, the model we proposed is composed of three parts: Basic Convolutional Neural Network, Auxiliary Convolutional Neural Network, and Fusion Convolutional Neural Network, and applies a weighted integration strategy. We evaluated the proposed method on the ISIC 2016 Skin Injury Challenge classification dataset. Experiments show that the patch strategy plays an important role in the field of melanoma classification, and the melanoma detection method proposed in this paper obtains an accuracy of 0.852 and an AUC value of 0.854 on the test set. This method can focus the attention of the classification network on the meaningful area of the skin lesion image through manual intervention, and can effectively solve the problem of category imbalance, thereby improving the performance of skin lesion classification.https://doi.org/10.1007/s44196-023-00246-1Conditional image synthesisMelanomaPatch strategyFusion strategy |
spellingShingle | Qingxu Zou Jinyong Cheng Zhenlu Liang Automatic Diagnosis of Melanoma Based on EfficientNet and Patch Strategy International Journal of Computational Intelligence Systems Conditional image synthesis Melanoma Patch strategy Fusion strategy |
title | Automatic Diagnosis of Melanoma Based on EfficientNet and Patch Strategy |
title_full | Automatic Diagnosis of Melanoma Based on EfficientNet and Patch Strategy |
title_fullStr | Automatic Diagnosis of Melanoma Based on EfficientNet and Patch Strategy |
title_full_unstemmed | Automatic Diagnosis of Melanoma Based on EfficientNet and Patch Strategy |
title_short | Automatic Diagnosis of Melanoma Based on EfficientNet and Patch Strategy |
title_sort | automatic diagnosis of melanoma based on efficientnet and patch strategy |
topic | Conditional image synthesis Melanoma Patch strategy Fusion strategy |
url | https://doi.org/10.1007/s44196-023-00246-1 |
work_keys_str_mv | AT qingxuzou automaticdiagnosisofmelanomabasedonefficientnetandpatchstrategy AT jinyongcheng automaticdiagnosisofmelanomabasedonefficientnetandpatchstrategy AT zhenluliang automaticdiagnosisofmelanomabasedonefficientnetandpatchstrategy |