Light-Dermo: A Lightweight Pretrained Convolution Neural Network for the Diagnosis of Multiclass Skin Lesions
Skin cancer develops due to the unusual growth of skin cells. Early detection is critical for the recognition of multiclass pigmented skin lesions (PSLs). At an early stage, the manual work by ophthalmologists takes time to recognize the PSLs. Therefore, several “computer-aided diagnosis (CAD)” syst...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/13/3/385 |
| _version_ | 1797624873885892608 |
|---|---|
| author | Abdul Rauf Baig Qaisar Abbas Riyad Almakki Mostafa E. A. Ibrahim Lulwah AlSuwaidan Alaa E. S. Ahmed |
| author_facet | Abdul Rauf Baig Qaisar Abbas Riyad Almakki Mostafa E. A. Ibrahim Lulwah AlSuwaidan Alaa E. S. Ahmed |
| author_sort | Abdul Rauf Baig |
| collection | DOAJ |
| description | Skin cancer develops due to the unusual growth of skin cells. Early detection is critical for the recognition of multiclass pigmented skin lesions (PSLs). At an early stage, the manual work by ophthalmologists takes time to recognize the PSLs. Therefore, several “computer-aided diagnosis (CAD)” systems are developed by using image processing, machine learning (ML), and deep learning (DL) techniques. Deep-CNN models outperformed traditional ML approaches in extracting complex features from PSLs. In this study, a special transfer learning (TL)-based CNN model is suggested for the diagnosis of seven classes of PSLs. A novel approach (Light-Dermo) is developed that is based on a lightweight CNN model and applies the channelwise attention (CA) mechanism with a focus on computational efficiency. The ShuffleNet architecture is chosen as the backbone, and squeeze-and-excitation (SE) blocks are incorporated as the technique to enhance the original ShuffleNet architecture. Initially, an accessible dataset with 14,000 images of PSLs from seven classes is used to validate the Light-Dermo model. To increase the size of the dataset and control its imbalance, we have applied data augmentation techniques to seven classes of PSLs. By applying this technique, we collected 28,000 images from the HAM10000, ISIS-2019, and ISIC-2020 datasets. The outcomes of the experiments show that the suggested approach outperforms compared techniques in many cases. The most accurately trained model has an accuracy of 99.14%, a specificity of 98.20%, a sensitivity of 97.45%, and an F1-score of 98.1%, with fewer parameters compared to state-of-the-art DL models. The experimental results show that Light-Dermo assists the dermatologist in the better diagnosis of PSLs. The Light-Dermo code is available to the public on GitHub so that researchers can use it and improve it. |
| first_indexed | 2024-03-11T09:48:53Z |
| format | Article |
| id | doaj.art-3923c1ab55754480982165ad7b0ead03 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-11T09:48:53Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-3923c1ab55754480982165ad7b0ead032023-11-16T16:23:57ZengMDPI AGDiagnostics2075-44182023-01-0113338510.3390/diagnostics13030385Light-Dermo: A Lightweight Pretrained Convolution Neural Network for the Diagnosis of Multiclass Skin LesionsAbdul Rauf Baig0Qaisar Abbas1Riyad Almakki2Mostafa E. A. Ibrahim3Lulwah AlSuwaidan4Alaa E. S. Ahmed5College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 11432, Saudi ArabiaCollege of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 11432, Saudi ArabiaCollege of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 11432, Saudi ArabiaCollege of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 11432, Saudi ArabiaCollege of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 11432, Saudi ArabiaCollege of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 11432, Saudi ArabiaSkin cancer develops due to the unusual growth of skin cells. Early detection is critical for the recognition of multiclass pigmented skin lesions (PSLs). At an early stage, the manual work by ophthalmologists takes time to recognize the PSLs. Therefore, several “computer-aided diagnosis (CAD)” systems are developed by using image processing, machine learning (ML), and deep learning (DL) techniques. Deep-CNN models outperformed traditional ML approaches in extracting complex features from PSLs. In this study, a special transfer learning (TL)-based CNN model is suggested for the diagnosis of seven classes of PSLs. A novel approach (Light-Dermo) is developed that is based on a lightweight CNN model and applies the channelwise attention (CA) mechanism with a focus on computational efficiency. The ShuffleNet architecture is chosen as the backbone, and squeeze-and-excitation (SE) blocks are incorporated as the technique to enhance the original ShuffleNet architecture. Initially, an accessible dataset with 14,000 images of PSLs from seven classes is used to validate the Light-Dermo model. To increase the size of the dataset and control its imbalance, we have applied data augmentation techniques to seven classes of PSLs. By applying this technique, we collected 28,000 images from the HAM10000, ISIS-2019, and ISIC-2020 datasets. The outcomes of the experiments show that the suggested approach outperforms compared techniques in many cases. The most accurately trained model has an accuracy of 99.14%, a specificity of 98.20%, a sensitivity of 97.45%, and an F1-score of 98.1%, with fewer parameters compared to state-of-the-art DL models. The experimental results show that Light-Dermo assists the dermatologist in the better diagnosis of PSLs. The Light-Dermo code is available to the public on GitHub so that researchers can use it and improve it.https://www.mdpi.com/2075-4418/13/3/385pigmented skin lesionsdeep learningconvolutional neural networktransfer learningpretrained modelsShuffleNet |
| spellingShingle | Abdul Rauf Baig Qaisar Abbas Riyad Almakki Mostafa E. A. Ibrahim Lulwah AlSuwaidan Alaa E. S. Ahmed Light-Dermo: A Lightweight Pretrained Convolution Neural Network for the Diagnosis of Multiclass Skin Lesions Diagnostics pigmented skin lesions deep learning convolutional neural network transfer learning pretrained models ShuffleNet |
| title | Light-Dermo: A Lightweight Pretrained Convolution Neural Network for the Diagnosis of Multiclass Skin Lesions |
| title_full | Light-Dermo: A Lightweight Pretrained Convolution Neural Network for the Diagnosis of Multiclass Skin Lesions |
| title_fullStr | Light-Dermo: A Lightweight Pretrained Convolution Neural Network for the Diagnosis of Multiclass Skin Lesions |
| title_full_unstemmed | Light-Dermo: A Lightweight Pretrained Convolution Neural Network for the Diagnosis of Multiclass Skin Lesions |
| title_short | Light-Dermo: A Lightweight Pretrained Convolution Neural Network for the Diagnosis of Multiclass Skin Lesions |
| title_sort | light dermo a lightweight pretrained convolution neural network for the diagnosis of multiclass skin lesions |
| topic | pigmented skin lesions deep learning convolutional neural network transfer learning pretrained models ShuffleNet |
| url | https://www.mdpi.com/2075-4418/13/3/385 |
| work_keys_str_mv | AT abdulraufbaig lightdermoalightweightpretrainedconvolutionneuralnetworkforthediagnosisofmulticlassskinlesions AT qaisarabbas lightdermoalightweightpretrainedconvolutionneuralnetworkforthediagnosisofmulticlassskinlesions AT riyadalmakki lightdermoalightweightpretrainedconvolutionneuralnetworkforthediagnosisofmulticlassskinlesions AT mostafaeaibrahim lightdermoalightweightpretrainedconvolutionneuralnetworkforthediagnosisofmulticlassskinlesions AT lulwahalsuwaidan lightdermoalightweightpretrainedconvolutionneuralnetworkforthediagnosisofmulticlassskinlesions AT alaaesahmed lightdermoalightweightpretrainedconvolutionneuralnetworkforthediagnosisofmulticlassskinlesions |