Deep Semantic Segmentation and Multi-Class Skin Lesion Classification Based on Convolutional Neural Network
Skin cancer is developed due to abnormal cell growth. These cells are grown rapidly and destroy the normal skin cells. However, it's curable at an initial stage to reduce the patient's mortality rate. In this article, the method is proposed for localization, segmentation and classification...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9139937/ |
| _version_ | 1819172924410560512 |
|---|---|
| author | Muhammad Almas Anjum Javaria Amin Muhammad Sharif Habib Ullah Khan Muhammad Sheraz Arshad Malik Seifedine Kadry |
| author_facet | Muhammad Almas Anjum Javaria Amin Muhammad Sharif Habib Ullah Khan Muhammad Sheraz Arshad Malik Seifedine Kadry |
| author_sort | Muhammad Almas Anjum |
| collection | DOAJ |
| description | Skin cancer is developed due to abnormal cell growth. These cells are grown rapidly and destroy the normal skin cells. However, it's curable at an initial stage to reduce the patient's mortality rate. In this article, the method is proposed for localization, segmentation and classification of the skin lesion at an early stage. The proposed method contains three phases. In phase I, different types of the skin lesion are localized using tinyYOLOv2 model in which open neural network (ONNX) and squeeze Net model are used as a backbone. The features are extracted from depthconcat7 layer of squeeze Net and passed as an input to the tinyYOLOv2. The propose model accurately localize the affected part of the skin. In Phase II, 13-layer 3D-semantic segmentation model (01 input, 04 convolutional, 03 batch-normalization, 03 ReLU, softmax and pixel classification) is used for segmentation. In the proposed segmentation model, pixel classification layer is used for computing the overlap region between the segmented and ground truth images. Later in Phase III, extract deep features using ResNet-18 model and optimized features are selected using ant colony optimization (ACO) method. The optimized features vector is passed to the classifiers such as optimized (O)-SVM and O-NB. The proposed method is evaluated on the top MICCAI ISIC challenging 2017, 2018 and 2019 datasets. The proposed method accurately localized, segmented and classified the skin lesion at an early stage. |
| first_indexed | 2024-12-22T20:14:55Z |
| format | Article |
| id | doaj.art-4304e0da749e4b5c86eef52aa24c5d04 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-22T20:14:55Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-4304e0da749e4b5c86eef52aa24c5d042022-12-21T18:13:58ZengIEEEIEEE Access2169-35362020-01-01812966812967810.1109/ACCESS.2020.30092769139937Deep Semantic Segmentation and Multi-Class Skin Lesion Classification Based on Convolutional Neural NetworkMuhammad Almas Anjum0Javaria Amin1Muhammad Sharif2https://orcid.org/0000-0002-1355-2168Habib Ullah Khan3https://orcid.org/0000-0001-8373-2781Muhammad Sheraz Arshad Malik4https://orcid.org/0000-0002-0944-6362Seifedine Kadry5https://orcid.org/0000-0002-1939-4842College of Electrical and Mechanical Engineering, National University of Sciences & Technology (NUST), Islamabad, PakistanDepartment of Computer Science, University of Wah, Wah, PakistanDepartment of Computer Science, COMSATS University Islamabad, Wah Campus, Wah, PakistanDepartment of Accounting and Information System, College of Business & Economics, Qatar University, Doha, QatarDepartment of Information Technology, Government College University Faisalabad, Faisalabad, PakistanDepartment of Mathematics and Computer Science, Faculty of Science, Beirut Arab University, Beirut, LebanonSkin cancer is developed due to abnormal cell growth. These cells are grown rapidly and destroy the normal skin cells. However, it's curable at an initial stage to reduce the patient's mortality rate. In this article, the method is proposed for localization, segmentation and classification of the skin lesion at an early stage. The proposed method contains three phases. In phase I, different types of the skin lesion are localized using tinyYOLOv2 model in which open neural network (ONNX) and squeeze Net model are used as a backbone. The features are extracted from depthconcat7 layer of squeeze Net and passed as an input to the tinyYOLOv2. The propose model accurately localize the affected part of the skin. In Phase II, 13-layer 3D-semantic segmentation model (01 input, 04 convolutional, 03 batch-normalization, 03 ReLU, softmax and pixel classification) is used for segmentation. In the proposed segmentation model, pixel classification layer is used for computing the overlap region between the segmented and ground truth images. Later in Phase III, extract deep features using ResNet-18 model and optimized features are selected using ant colony optimization (ACO) method. The optimized features vector is passed to the classifiers such as optimized (O)-SVM and O-NB. The proposed method is evaluated on the top MICCAI ISIC challenging 2017, 2018 and 2019 datasets. The proposed method accurately localized, segmented and classified the skin lesion at an early stage.https://ieeexplore.ieee.org/document/9139937/YOLOv2ant colony optimizationsqueeze NetResNet-18SVMONNX |
| spellingShingle | Muhammad Almas Anjum Javaria Amin Muhammad Sharif Habib Ullah Khan Muhammad Sheraz Arshad Malik Seifedine Kadry Deep Semantic Segmentation and Multi-Class Skin Lesion Classification Based on Convolutional Neural Network IEEE Access YOLOv2 ant colony optimization squeeze Net ResNet-18 SVM ONNX |
| title | Deep Semantic Segmentation and Multi-Class Skin Lesion Classification Based on Convolutional Neural Network |
| title_full | Deep Semantic Segmentation and Multi-Class Skin Lesion Classification Based on Convolutional Neural Network |
| title_fullStr | Deep Semantic Segmentation and Multi-Class Skin Lesion Classification Based on Convolutional Neural Network |
| title_full_unstemmed | Deep Semantic Segmentation and Multi-Class Skin Lesion Classification Based on Convolutional Neural Network |
| title_short | Deep Semantic Segmentation and Multi-Class Skin Lesion Classification Based on Convolutional Neural Network |
| title_sort | deep semantic segmentation and multi class skin lesion classification based on convolutional neural network |
| topic | YOLOv2 ant colony optimization squeeze Net ResNet-18 SVM ONNX |
| url | https://ieeexplore.ieee.org/document/9139937/ |
| work_keys_str_mv | AT muhammadalmasanjum deepsemanticsegmentationandmulticlassskinlesionclassificationbasedonconvolutionalneuralnetwork AT javariaamin deepsemanticsegmentationandmulticlassskinlesionclassificationbasedonconvolutionalneuralnetwork AT muhammadsharif deepsemanticsegmentationandmulticlassskinlesionclassificationbasedonconvolutionalneuralnetwork AT habibullahkhan deepsemanticsegmentationandmulticlassskinlesionclassificationbasedonconvolutionalneuralnetwork AT muhammadsherazarshadmalik deepsemanticsegmentationandmulticlassskinlesionclassificationbasedonconvolutionalneuralnetwork AT seifedinekadry deepsemanticsegmentationandmulticlassskinlesionclassificationbasedonconvolutionalneuralnetwork |