Multi-Class Skin Lesions Classification Using Deep Features
Skin cancer classification is a complex and time-consuming task. Existing approaches use segmentation to improve accuracy and efficiency, but due to different sizes and shapes of lesions, segmentation is not a suitable approach. In this research study, we proposed an improved automated system based...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/21/8311 |
| _version_ | 1797466565973639168 |
|---|---|
| author | Muhammad Usama M. Asif Naeem Farhaan Mirza |
| author_facet | Muhammad Usama M. Asif Naeem Farhaan Mirza |
| author_sort | Muhammad Usama |
| collection | DOAJ |
| description | Skin cancer classification is a complex and time-consuming task. Existing approaches use segmentation to improve accuracy and efficiency, but due to different sizes and shapes of lesions, segmentation is not a suitable approach. In this research study, we proposed an improved automated system based on hybrid and optimal feature selections. Firstly, we balanced our dataset by applying three different transformation techniques, which include brightness, sharpening, and contrast enhancement. Secondly, we retrained two CNNs, Darknet53 and Inception V3, using transfer learning. Thirdly, the retrained models were used to extract deep features from the dataset. Lastly, optimal features were selected using moth flame optimization (MFO) to overcome the curse of dimensionality. This helped us in improving accuracy and efficiency of our model. We achieved 95.9%, 95.0%, and 95.8% on cubic SVM, quadratic SVM, and ensemble subspace discriminants, respectively. We compared our technique with state-of-the-art approach. |
| first_indexed | 2024-03-09T18:40:38Z |
| format | Article |
| id | doaj.art-f419a838126546c4b50841ccfcbf44f4 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T18:40:38Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-f419a838126546c4b50841ccfcbf44f42023-11-24T06:46:04ZengMDPI AGSensors1424-82202022-10-012221831110.3390/s22218311Multi-Class Skin Lesions Classification Using Deep FeaturesMuhammad Usama0M. Asif Naeem1Farhaan Mirza2School of Computing, National University of Computer & Emerging Sciences, Islamabad 44000, PakistanSchool of Computing, National University of Computer & Emerging Sciences, Islamabad 44000, PakistanSchool of Engineering, Computer and Mathematical Sciences, Auckland University of Technology, Auckland 1010, New ZealandSkin cancer classification is a complex and time-consuming task. Existing approaches use segmentation to improve accuracy and efficiency, but due to different sizes and shapes of lesions, segmentation is not a suitable approach. In this research study, we proposed an improved automated system based on hybrid and optimal feature selections. Firstly, we balanced our dataset by applying three different transformation techniques, which include brightness, sharpening, and contrast enhancement. Secondly, we retrained two CNNs, Darknet53 and Inception V3, using transfer learning. Thirdly, the retrained models were used to extract deep features from the dataset. Lastly, optimal features were selected using moth flame optimization (MFO) to overcome the curse of dimensionality. This helped us in improving accuracy and efficiency of our model. We achieved 95.9%, 95.0%, and 95.8% on cubic SVM, quadratic SVM, and ensemble subspace discriminants, respectively. We compared our technique with state-of-the-art approach.https://www.mdpi.com/1424-8220/22/21/8311skin canceraugmentationdeep learningmoth flame optimizationSVMfeature optimization |
| spellingShingle | Muhammad Usama M. Asif Naeem Farhaan Mirza Multi-Class Skin Lesions Classification Using Deep Features Sensors skin cancer augmentation deep learning moth flame optimization SVM feature optimization |
| title | Multi-Class Skin Lesions Classification Using Deep Features |
| title_full | Multi-Class Skin Lesions Classification Using Deep Features |
| title_fullStr | Multi-Class Skin Lesions Classification Using Deep Features |
| title_full_unstemmed | Multi-Class Skin Lesions Classification Using Deep Features |
| title_short | Multi-Class Skin Lesions Classification Using Deep Features |
| title_sort | multi class skin lesions classification using deep features |
| topic | skin cancer augmentation deep learning moth flame optimization SVM feature optimization |
| url | https://www.mdpi.com/1424-8220/22/21/8311 |
| work_keys_str_mv | AT muhammadusama multiclassskinlesionsclassificationusingdeepfeatures AT masifnaeem multiclassskinlesionsclassificationusingdeepfeatures AT farhaanmirza multiclassskinlesionsclassificationusingdeepfeatures |