Multi-Class Skin Lesion Classification Using a Lightweight Dynamic Kernel Deep-Learning-Based Convolutional Neural Network
Skin is the primary protective layer of the internal organs of the body. Nowadays, due to increasing pollution and multiple other factors, various types of skin diseases are growing globally. With variable shapes and multiple types, the classification of skin lesions is a challenging task. Motivated...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/12/9/2048 |
| _version_ | 1797489531558035456 |
|---|---|
| author | Theyazn H. H. Aldhyani Amit Verma Mosleh Hmoud Al-Adhaileh Deepika Koundal |
| author_facet | Theyazn H. H. Aldhyani Amit Verma Mosleh Hmoud Al-Adhaileh Deepika Koundal |
| author_sort | Theyazn H. H. Aldhyani |
| collection | DOAJ |
| description | Skin is the primary protective layer of the internal organs of the body. Nowadays, due to increasing pollution and multiple other factors, various types of skin diseases are growing globally. With variable shapes and multiple types, the classification of skin lesions is a challenging task. Motivated by this spreading deformity in society, a lightweight and efficient model is proposed for the highly accurate classification of skin lesions. Dynamic-sized kernels are used in layers to obtain the best results, resulting in very few trainable parameters. Further, both ReLU and leakyReLU activation functions are purposefully used in the proposed model. The model accurately classified all of the classes of the HAM10000 dataset. The model achieved an overall accuracy of 97.85%, which is much better than multiple state-of-the-art heavy models. Further, our work is compared with some popular state-of-the-art and recent existing models. |
| first_indexed | 2024-03-10T00:17:53Z |
| format | Article |
| id | doaj.art-64fb143b876d4540abb63c4b046e6718 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-10T00:17:53Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-64fb143b876d4540abb63c4b046e67182023-11-23T15:47:48ZengMDPI AGDiagnostics2075-44182022-08-01129204810.3390/diagnostics12092048Multi-Class Skin Lesion Classification Using a Lightweight Dynamic Kernel Deep-Learning-Based Convolutional Neural NetworkTheyazn H. H. Aldhyani0Amit Verma1Mosleh Hmoud Al-Adhaileh2Deepika Koundal3Applied College in Abqaiq, King Faisal University, P.O. Box 400, Al-Ahsa 31982, Saudi ArabiaSchool of Computer Science, University of Petroleum & Energy Studies, Dehradun 248007, IndiaDeanship of E-Learning and Distance Education, King Faisal University, P.O. Box 4000, Al-Ahsa 31982, Saudi ArabiaSchool of Computer Science, University of Petroleum & Energy Studies, Dehradun 248007, IndiaSkin is the primary protective layer of the internal organs of the body. Nowadays, due to increasing pollution and multiple other factors, various types of skin diseases are growing globally. With variable shapes and multiple types, the classification of skin lesions is a challenging task. Motivated by this spreading deformity in society, a lightweight and efficient model is proposed for the highly accurate classification of skin lesions. Dynamic-sized kernels are used in layers to obtain the best results, resulting in very few trainable parameters. Further, both ReLU and leakyReLU activation functions are purposefully used in the proposed model. The model accurately classified all of the classes of the HAM10000 dataset. The model achieved an overall accuracy of 97.85%, which is much better than multiple state-of-the-art heavy models. Further, our work is compared with some popular state-of-the-art and recent existing models.https://www.mdpi.com/2075-4418/12/9/2048deep learningskin diseasesbiomedical imageartificial intelligence |
| spellingShingle | Theyazn H. H. Aldhyani Amit Verma Mosleh Hmoud Al-Adhaileh Deepika Koundal Multi-Class Skin Lesion Classification Using a Lightweight Dynamic Kernel Deep-Learning-Based Convolutional Neural Network Diagnostics deep learning skin diseases biomedical image artificial intelligence |
| title | Multi-Class Skin Lesion Classification Using a Lightweight Dynamic Kernel Deep-Learning-Based Convolutional Neural Network |
| title_full | Multi-Class Skin Lesion Classification Using a Lightweight Dynamic Kernel Deep-Learning-Based Convolutional Neural Network |
| title_fullStr | Multi-Class Skin Lesion Classification Using a Lightweight Dynamic Kernel Deep-Learning-Based Convolutional Neural Network |
| title_full_unstemmed | Multi-Class Skin Lesion Classification Using a Lightweight Dynamic Kernel Deep-Learning-Based Convolutional Neural Network |
| title_short | Multi-Class Skin Lesion Classification Using a Lightweight Dynamic Kernel Deep-Learning-Based Convolutional Neural Network |
| title_sort | multi class skin lesion classification using a lightweight dynamic kernel deep learning based convolutional neural network |
| topic | deep learning skin diseases biomedical image artificial intelligence |
| url | https://www.mdpi.com/2075-4418/12/9/2048 |
| work_keys_str_mv | AT theyaznhhaldhyani multiclassskinlesionclassificationusingalightweightdynamickerneldeeplearningbasedconvolutionalneuralnetwork AT amitverma multiclassskinlesionclassificationusingalightweightdynamickerneldeeplearningbasedconvolutionalneuralnetwork AT moslehhmoudaladhaileh multiclassskinlesionclassificationusingalightweightdynamickerneldeeplearningbasedconvolutionalneuralnetwork AT deepikakoundal multiclassskinlesionclassificationusingalightweightdynamickerneldeeplearningbasedconvolutionalneuralnetwork |