Отрывок: All images are of high definition. To suit processing on our computing sys- tem, we resize all images to standard size 256 × 256 pix- els and store them in PNG format. We select 20 images to present the visual results of the proposed skin lesion segmentation method. Moreo- ver, the acquired results for a test set are used for com- parison. Fig. 2 shows all selected images (20 images) for test- ing. All images used for the test are c...
Полная запись метаданных
Поле DC | Значение | Язык |
---|---|---|
dc.contributor.author | Thanh, Dang N.H. | - |
dc.contributor.author | Hai, Nguyen Hoang | - |
dc.contributor.author | Hieu, Le Minh | - |
dc.contributor.author | Tiwari, Prayag | - |
dc.contributor.author | Prasath, V.B. Surya | - |
dc.date.accessioned | 2021-03-01 10:20:37 | - |
dc.date.available | 2021-03-01 10:20:37 | - |
dc.date.issued | 2021-02 | - |
dc.identifier | Dspace\SGAU\20210228\87759 | ru |
dc.identifier.citation | Thanh DNH, Hai NH, Hieu LM, Tiwari P, Prasath VBS. Skin lesion segmentation method for dermoscopic images with convolutional neural networks and semantic segmentation. Computer Optics 2021; 45(1): 122-129. DOI: 10.18287/2412-6179-CO-748. | ru |
dc.identifier.uri | https://dx.doi.org/10.18287/2412-6179-CO-748 | - |
dc.identifier.uri | http://repo.ssau.ru/handle/Zhurnal-Komputernaya-optika/Skin-lesion-segmentation-method-for-dermoscopic-images-with-convolutional-neural-networks-and-semantic-segmentation-87759 | - |
dc.description.abstract | Melanoma skin cancer is one of the most dangerous forms of skin cancer because it grows fast and causes most of the skin cancer deaths. Hence, early detection is a very important task to treat melanoma. In this article, we propose a skin lesion segmentation method for dermoscopic images based on the U-Net architecture with VGG-16 encoder and the semantic segmentation. Base on the segmented skin lesion, diagnostic imaging systems can evaluate skin lesion features to classify them. The proposed method requires fewer resources for training, and it is suitable for computing systems without powerful GPUs, but the training accuracy is still high enough (above 95 %). In the experiments, we train the model on the ISIC dataset – a common dermoscopic image dataset. To assess the performance of the proposed skin lesion segmentation method, we evaluate the Sorensen-Dice and the Jaccard scores and compare to other deep learning-based skin lesion segmentation methods. Experimental results showed that skin lesion segmentation quality of the proposed method are better than ones of the compared methods. | ru |
dc.description.sponsorship | This research was funded by University of Economics Ho Chi Minh City, Vietnam. | ru |
dc.language.iso | en | ru |
dc.publisher | Самарский национальный исследовательский университет | ru |
dc.relation.ispartofseries | 45;1 | - |
dc.subject | image segmentation | ru |
dc.subject | medical image segmentation | ru |
dc.subject | semantic segmentation | ru |
dc.subject | melanoma | ru |
dc.subject | skin cancer | ru |
dc.subject | skin lesion | ru |
dc.subject | deep learning | ru |
dc.subject | cancer | ru |
dc.title | Skin lesion segmentation method for dermoscopic images with convolutional neural networks and semantic segmentation | ru |
dc.type | Article | ru |
dc.textpart | All images are of high definition. To suit processing on our computing sys- tem, we resize all images to standard size 256 × 256 pix- els and store them in PNG format. We select 20 images to present the visual results of the proposed skin lesion segmentation method. Moreo- ver, the acquired results for a test set are used for com- parison. Fig. 2 shows all selected images (20 images) for test- ing. All images used for the test are c... | - |
Располагается в коллекциях: | Журнал "Компьютерная оптика" |
Файлы этого ресурса:
Файл | Описание | Размер | Формат | |
---|---|---|---|---|
450114.pdf | Основная статья | 1.05 MB | Adobe PDF | Просмотреть/Открыть |
Показать базовое описание ресурса
Просмотр статистики
Поделиться:
Все ресурсы в архиве электронных ресурсов защищены авторским правом, все права сохранены.