Skin Lesion Segmentation from Dermoscopic Images Using Convolutional Neural Network
Clinical treatment of skin lesion is primarily dependent on timely detection and delimitation of lesion boundaries for accurate cancerous region localization. Prevalence of skin cancer is on the higher side, especially that of melanoma, which is aggressive in nature due to its high metastasis rate....
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/6/1601 |
| _version_ | 1811263744123076608 |
|---|---|
| author | Kashan Zafar Syed Omer Gilani Asim Waris Ali Ahmed Mohsin Jamil Muhammad Nasir Khan Amer Sohail Kashif |
| author_facet | Kashan Zafar Syed Omer Gilani Asim Waris Ali Ahmed Mohsin Jamil Muhammad Nasir Khan Amer Sohail Kashif |
| author_sort | Kashan Zafar |
| collection | DOAJ |
| description | Clinical treatment of skin lesion is primarily dependent on timely detection and delimitation of lesion boundaries for accurate cancerous region localization. Prevalence of skin cancer is on the higher side, especially that of melanoma, which is aggressive in nature due to its high metastasis rate. Therefore, timely diagnosis is critical for its treatment before the onset of malignancy. To address this problem, medical imaging is used for the analysis and segmentation of lesion boundaries from dermoscopic images. Various methods have been used, ranging from visual inspection to the textural analysis of the images. However, accuracy of these methods is low for proper clinical treatment because of the sensitivity involved in surgical procedures or drug application. This presents an opportunity to develop an automated model with good accuracy so that it may be used in a clinical setting. This paper proposes an automated method for segmenting lesion boundaries that combines two architectures, the U-Net and the ResNet, collectively called Res-Unet. Moreover, we also used image inpainting for hair removal, which improved the segmentation results significantly. We trained our model on the ISIC 2017 dataset and validated it on the ISIC 2017 test set as well as the PH<sup>2</sup> dataset. Our proposed model attained a Jaccard Index of 0.772 on the ISIC 2017 test set and 0.854 on the PH<sup>2</sup> dataset, which are comparable results to the current available state-of-the-art techniques. |
| first_indexed | 2024-04-12T19:50:43Z |
| format | Article |
| id | doaj.art-29a7c037d3db40db9693d73d2554f479 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-12T19:50:43Z |
| publishDate | 2020-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-29a7c037d3db40db9693d73d2554f4792022-12-22T03:18:49ZengMDPI AGSensors1424-82202020-03-01206160110.3390/s20061601s20061601Skin Lesion Segmentation from Dermoscopic Images Using Convolutional Neural NetworkKashan Zafar0Syed Omer Gilani1Asim Waris2Ali Ahmed3Mohsin Jamil4Muhammad Nasir Khan5Amer Sohail Kashif6Department of Biomedical Engineering and Sciences, School of Mechanical and Manufacturing Engineering, National University of Sciences and Technology, Islamabad 44000, PakistanDepartment of Biomedical Engineering and Sciences, School of Mechanical and Manufacturing Engineering, National University of Sciences and Technology, Islamabad 44000, PakistanDepartment of Biomedical Engineering and Sciences, School of Mechanical and Manufacturing Engineering, National University of Sciences and Technology, Islamabad 44000, PakistanDepartment of Biomedical Engineering and Sciences, School of Mechanical and Manufacturing Engineering, National University of Sciences and Technology, Islamabad 44000, PakistanDepartment of Electrical and Computer Engineering, Memorial University of Newfoundland, Newfoundland, St. John’s, NL A1C 5S7 P.O. Box 4200, CanadaDepartment of Electrical Engineering, University of Lahore, Lahore 54590, PakistanDepartment of Biomedical Engineering and Sciences, School of Mechanical and Manufacturing Engineering, National University of Sciences and Technology, Islamabad 44000, PakistanClinical treatment of skin lesion is primarily dependent on timely detection and delimitation of lesion boundaries for accurate cancerous region localization. Prevalence of skin cancer is on the higher side, especially that of melanoma, which is aggressive in nature due to its high metastasis rate. Therefore, timely diagnosis is critical for its treatment before the onset of malignancy. To address this problem, medical imaging is used for the analysis and segmentation of lesion boundaries from dermoscopic images. Various methods have been used, ranging from visual inspection to the textural analysis of the images. However, accuracy of these methods is low for proper clinical treatment because of the sensitivity involved in surgical procedures or drug application. This presents an opportunity to develop an automated model with good accuracy so that it may be used in a clinical setting. This paper proposes an automated method for segmenting lesion boundaries that combines two architectures, the U-Net and the ResNet, collectively called Res-Unet. Moreover, we also used image inpainting for hair removal, which improved the segmentation results significantly. We trained our model on the ISIC 2017 dataset and validated it on the ISIC 2017 test set as well as the PH<sup>2</sup> dataset. Our proposed model attained a Jaccard Index of 0.772 on the ISIC 2017 test set and 0.854 on the PH<sup>2</sup> dataset, which are comparable results to the current available state-of-the-art techniques.https://www.mdpi.com/1424-8220/20/6/1601melanomadermoscopic imagesconvolutional neural networksu-netresnetimage inpaintingjaccard indexroc curve |
| spellingShingle | Kashan Zafar Syed Omer Gilani Asim Waris Ali Ahmed Mohsin Jamil Muhammad Nasir Khan Amer Sohail Kashif Skin Lesion Segmentation from Dermoscopic Images Using Convolutional Neural Network Sensors melanoma dermoscopic images convolutional neural networks u-net resnet image inpainting jaccard index roc curve |
| title | Skin Lesion Segmentation from Dermoscopic Images Using Convolutional Neural Network |
| title_full | Skin Lesion Segmentation from Dermoscopic Images Using Convolutional Neural Network |
| title_fullStr | Skin Lesion Segmentation from Dermoscopic Images Using Convolutional Neural Network |
| title_full_unstemmed | Skin Lesion Segmentation from Dermoscopic Images Using Convolutional Neural Network |
| title_short | Skin Lesion Segmentation from Dermoscopic Images Using Convolutional Neural Network |
| title_sort | skin lesion segmentation from dermoscopic images using convolutional neural network |
| topic | melanoma dermoscopic images convolutional neural networks u-net resnet image inpainting jaccard index roc curve |
| url | https://www.mdpi.com/1424-8220/20/6/1601 |
| work_keys_str_mv | AT kashanzafar skinlesionsegmentationfromdermoscopicimagesusingconvolutionalneuralnetwork AT syedomergilani skinlesionsegmentationfromdermoscopicimagesusingconvolutionalneuralnetwork AT asimwaris skinlesionsegmentationfromdermoscopicimagesusingconvolutionalneuralnetwork AT aliahmed skinlesionsegmentationfromdermoscopicimagesusingconvolutionalneuralnetwork AT mohsinjamil skinlesionsegmentationfromdermoscopicimagesusingconvolutionalneuralnetwork AT muhammadnasirkhan skinlesionsegmentationfromdermoscopicimagesusingconvolutionalneuralnetwork AT amersohailkashif skinlesionsegmentationfromdermoscopicimagesusingconvolutionalneuralnetwork |