Two-Stage Deep Neural Network via Ensemble Learning for Melanoma Classification
Melanoma is a skin disease with a high fatality rate. Early diagnosis of melanoma can effectively increase the survival rate of patients. There are three types of dermoscopy images, malignant melanoma, benign nevis, and seborrheic keratosis, so using dermoscopy images to classify melanoma is an indi...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-01-01
|
| Series: | Frontiers in Bioengineering and Biotechnology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fbioe.2021.758495/full |
| _version_ | 1818988067915038720 |
|---|---|
| author | Jiaqi Ding Jie Song Jiawei Li Jijun Tang Fei Guo |
| author_facet | Jiaqi Ding Jie Song Jiawei Li Jijun Tang Fei Guo |
| author_sort | Jiaqi Ding |
| collection | DOAJ |
| description | Melanoma is a skin disease with a high fatality rate. Early diagnosis of melanoma can effectively increase the survival rate of patients. There are three types of dermoscopy images, malignant melanoma, benign nevis, and seborrheic keratosis, so using dermoscopy images to classify melanoma is an indispensable task in diagnosis. However, early melanoma classification works can only use the low-level information of images, so the melanoma cannot be classified efficiently; the recent deep learning methods mainly depend on a single network, although it can extract high-level features, the poor scale and type of the features limited the results of the classification. Therefore, we need an automatic classification method for melanoma, which can make full use of the rich and deep feature information of images for classification. In this study, we propose an ensemble method that can integrate different types of classification networks for melanoma classification. Specifically, we first use U-net to segment the lesion area of images to generate a lesion mask, thus resize images to focus on the lesion; then, we use five excellent classification models to classify dermoscopy images, and adding squeeze-excitation block (SE block) to models to emphasize the more informative features; finally, we use our proposed new ensemble network to integrate five different classification results. The experimental results prove the validity of our results. We test our method on the ISIC 2017 challenge dataset and obtain excellent results on multiple metrics; especially, we get 0.909 on accuracy. Our classification framework can provide an efficient and accurate way for melanoma classification using dermoscopy images, laying the foundation for early diagnosis and later treatment of melanoma. |
| first_indexed | 2024-12-20T19:16:42Z |
| format | Article |
| id | doaj.art-58bd36ed7af444b0a12f3510f475179b |
| institution | Directory Open Access Journal |
| issn | 2296-4185 |
| language | English |
| last_indexed | 2024-12-20T19:16:42Z |
| publishDate | 2022-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Bioengineering and Biotechnology |
| spelling | doaj.art-58bd36ed7af444b0a12f3510f475179b2022-12-21T19:29:05ZengFrontiers Media S.A.Frontiers in Bioengineering and Biotechnology2296-41852022-01-01910.3389/fbioe.2021.758495758495Two-Stage Deep Neural Network via Ensemble Learning for Melanoma ClassificationJiaqi Ding0Jie Song 1Jiawei Li2Jijun Tang3Fei Guo4School of Computer Science and Technology, College of Intelligence and Computing, Tianjin University, Tianjin, ChinaSchool of Computer Science and Technology, College of Intelligence and Computing, Tianjin University, Tianjin, ChinaSchool of Computer Science and Technology, College of Intelligence and Computing, Tianjin University, Tianjin, ChinaShenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, ChinaSchool of Computer Science and Engineering, Central South University, Changsha, ChinaMelanoma is a skin disease with a high fatality rate. Early diagnosis of melanoma can effectively increase the survival rate of patients. There are three types of dermoscopy images, malignant melanoma, benign nevis, and seborrheic keratosis, so using dermoscopy images to classify melanoma is an indispensable task in diagnosis. However, early melanoma classification works can only use the low-level information of images, so the melanoma cannot be classified efficiently; the recent deep learning methods mainly depend on a single network, although it can extract high-level features, the poor scale and type of the features limited the results of the classification. Therefore, we need an automatic classification method for melanoma, which can make full use of the rich and deep feature information of images for classification. In this study, we propose an ensemble method that can integrate different types of classification networks for melanoma classification. Specifically, we first use U-net to segment the lesion area of images to generate a lesion mask, thus resize images to focus on the lesion; then, we use five excellent classification models to classify dermoscopy images, and adding squeeze-excitation block (SE block) to models to emphasize the more informative features; finally, we use our proposed new ensemble network to integrate five different classification results. The experimental results prove the validity of our results. We test our method on the ISIC 2017 challenge dataset and obtain excellent results on multiple metrics; especially, we get 0.909 on accuracy. Our classification framework can provide an efficient and accurate way for melanoma classification using dermoscopy images, laying the foundation for early diagnosis and later treatment of melanoma.https://www.frontiersin.org/articles/10.3389/fbioe.2021.758495/fullmelanoma classificationensemble learningdeep convolutional neural networkimage segmentationdermoscopy images |
| spellingShingle | Jiaqi Ding Jie Song Jiawei Li Jijun Tang Fei Guo Two-Stage Deep Neural Network via Ensemble Learning for Melanoma Classification Frontiers in Bioengineering and Biotechnology melanoma classification ensemble learning deep convolutional neural network image segmentation dermoscopy images |
| title | Two-Stage Deep Neural Network via Ensemble Learning for Melanoma Classification |
| title_full | Two-Stage Deep Neural Network via Ensemble Learning for Melanoma Classification |
| title_fullStr | Two-Stage Deep Neural Network via Ensemble Learning for Melanoma Classification |
| title_full_unstemmed | Two-Stage Deep Neural Network via Ensemble Learning for Melanoma Classification |
| title_short | Two-Stage Deep Neural Network via Ensemble Learning for Melanoma Classification |
| title_sort | two stage deep neural network via ensemble learning for melanoma classification |
| topic | melanoma classification ensemble learning deep convolutional neural network image segmentation dermoscopy images |
| url | https://www.frontiersin.org/articles/10.3389/fbioe.2021.758495/full |
| work_keys_str_mv | AT jiaqiding twostagedeepneuralnetworkviaensemblelearningformelanomaclassification AT jiesong twostagedeepneuralnetworkviaensemblelearningformelanomaclassification AT jiaweili twostagedeepneuralnetworkviaensemblelearningformelanomaclassification AT jijuntang twostagedeepneuralnetworkviaensemblelearningformelanomaclassification AT feiguo twostagedeepneuralnetworkviaensemblelearningformelanomaclassification |