Deep Hybrid Convolutional Neural Network for Segmentation of Melanoma Skin Lesion

Melanoma is a type of skin cancer that often leads to poor prognostic responses and survival rates. Melanoma usually develops in the limbs, including in fingers, palms, and the margins of the nails. When melanoma is detected early, surgical treatment may achieve a higher cure rate. The early diagnos...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Cheng-Hong Yang, Jai-Hong Ren, Hsiu-Chen Huang, Li-Yeh Chuang, Po-Yin Chang
Formato: article
Lenguaje:EN
Publicado: Hindawi Limited 2021
Materias:
Acceso en línea:https://doaj.org/article/4f918cb3d1004e2ab6efe45a5cc2fb1e
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:4f918cb3d1004e2ab6efe45a5cc2fb1e
record_format dspace
spelling oai:doaj.org-article:4f918cb3d1004e2ab6efe45a5cc2fb1e2021-11-22T01:11:34ZDeep Hybrid Convolutional Neural Network for Segmentation of Melanoma Skin Lesion1687-527310.1155/2021/9409508https://doaj.org/article/4f918cb3d1004e2ab6efe45a5cc2fb1e2021-01-01T00:00:00Zhttp://dx.doi.org/10.1155/2021/9409508https://doaj.org/toc/1687-5273Melanoma is a type of skin cancer that often leads to poor prognostic responses and survival rates. Melanoma usually develops in the limbs, including in fingers, palms, and the margins of the nails. When melanoma is detected early, surgical treatment may achieve a higher cure rate. The early diagnosis of melanoma depends on the manual segmentation of suspected lesions. However, manual segmentation can lead to problems, including misclassification and low efficiency. Therefore, it is essential to devise a method for automatic image segmentation that overcomes the aforementioned issues. In this study, an improved algorithm is proposed, termed EfficientUNet++, which is developed from the U-Net model. In EfficientUNet++, the pretrained EfficientNet model is added to the UNet++ model to accelerate segmentation process, leading to more reliable and precise results in skin cancer image segmentation. Two skin lesion datasets were used to compare the performance of the proposed EfficientUNet++ algorithm with other common models. In the PH2 dataset, EfficientUNet++ achieved a better Dice coefficient (93% vs. 76%–91%), Intersection over Union (IoU, 96% vs. 74%–95%), and loss value (30% vs. 44%–32%) compared with other models. In the International Skin Imaging Collaboration dataset, EfficientUNet++ obtained a similar Dice coefficient (96% vs. 94%–96%) but a better IoU (94% vs. 89%–93%) and loss value (11% vs. 13%–11%) than other models. In conclusion, the EfficientUNet++ model efficiently detects skin lesions by improving composite coefficients and structurally expanding the size of the convolution network. Moreover, the use of residual units deepens the network to further improve performance.Cheng-Hong YangJai-Hong RenHsiu-Chen HuangLi-Yeh ChuangPo-Yin ChangHindawi LimitedarticleComputer applications to medicine. Medical informaticsR858-859.7Neurosciences. Biological psychiatry. NeuropsychiatryRC321-571ENComputational Intelligence and Neuroscience, Vol 2021 (2021)
institution DOAJ
collection DOAJ
language EN
topic Computer applications to medicine. Medical informatics
R858-859.7
Neurosciences. Biological psychiatry. Neuropsychiatry
RC321-571
spellingShingle Computer applications to medicine. Medical informatics
R858-859.7
Neurosciences. Biological psychiatry. Neuropsychiatry
RC321-571
Cheng-Hong Yang
Jai-Hong Ren
Hsiu-Chen Huang
Li-Yeh Chuang
Po-Yin Chang
Deep Hybrid Convolutional Neural Network for Segmentation of Melanoma Skin Lesion
description Melanoma is a type of skin cancer that often leads to poor prognostic responses and survival rates. Melanoma usually develops in the limbs, including in fingers, palms, and the margins of the nails. When melanoma is detected early, surgical treatment may achieve a higher cure rate. The early diagnosis of melanoma depends on the manual segmentation of suspected lesions. However, manual segmentation can lead to problems, including misclassification and low efficiency. Therefore, it is essential to devise a method for automatic image segmentation that overcomes the aforementioned issues. In this study, an improved algorithm is proposed, termed EfficientUNet++, which is developed from the U-Net model. In EfficientUNet++, the pretrained EfficientNet model is added to the UNet++ model to accelerate segmentation process, leading to more reliable and precise results in skin cancer image segmentation. Two skin lesion datasets were used to compare the performance of the proposed EfficientUNet++ algorithm with other common models. In the PH2 dataset, EfficientUNet++ achieved a better Dice coefficient (93% vs. 76%–91%), Intersection over Union (IoU, 96% vs. 74%–95%), and loss value (30% vs. 44%–32%) compared with other models. In the International Skin Imaging Collaboration dataset, EfficientUNet++ obtained a similar Dice coefficient (96% vs. 94%–96%) but a better IoU (94% vs. 89%–93%) and loss value (11% vs. 13%–11%) than other models. In conclusion, the EfficientUNet++ model efficiently detects skin lesions by improving composite coefficients and structurally expanding the size of the convolution network. Moreover, the use of residual units deepens the network to further improve performance.
format article
author Cheng-Hong Yang
Jai-Hong Ren
Hsiu-Chen Huang
Li-Yeh Chuang
Po-Yin Chang
author_facet Cheng-Hong Yang
Jai-Hong Ren
Hsiu-Chen Huang
Li-Yeh Chuang
Po-Yin Chang
author_sort Cheng-Hong Yang
title Deep Hybrid Convolutional Neural Network for Segmentation of Melanoma Skin Lesion
title_short Deep Hybrid Convolutional Neural Network for Segmentation of Melanoma Skin Lesion
title_full Deep Hybrid Convolutional Neural Network for Segmentation of Melanoma Skin Lesion
title_fullStr Deep Hybrid Convolutional Neural Network for Segmentation of Melanoma Skin Lesion
title_full_unstemmed Deep Hybrid Convolutional Neural Network for Segmentation of Melanoma Skin Lesion
title_sort deep hybrid convolutional neural network for segmentation of melanoma skin lesion
publisher Hindawi Limited
publishDate 2021
url https://doaj.org/article/4f918cb3d1004e2ab6efe45a5cc2fb1e
work_keys_str_mv AT chenghongyang deephybridconvolutionalneuralnetworkforsegmentationofmelanomaskinlesion
AT jaihongren deephybridconvolutionalneuralnetworkforsegmentationofmelanomaskinlesion
AT hsiuchenhuang deephybridconvolutionalneuralnetworkforsegmentationofmelanomaskinlesion
AT liyehchuang deephybridconvolutionalneuralnetworkforsegmentationofmelanomaskinlesion
AT poyinchang deephybridconvolutionalneuralnetworkforsegmentationofmelanomaskinlesion
_version_ 1718418280720367616