Melanoma Skin Cancer Identification with Explainability Utilizing Mask Guided Technique
Melanoma is a highly prevalent and lethal form of skin cancer, which has a significant impact globally. The chances of recovery for melanoma patients substantially improve with early detection. Currently, deep learning (DL) methods are gaining popularity in assisting with the identification of disea...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/13/4/680 |
| _version_ | 1797298390052110336 |
|---|---|
| author | Lahiru Gamage Uditha Isuranga Dulani Meedeniya Senuri De Silva Pratheepan Yogarajah |
| author_facet | Lahiru Gamage Uditha Isuranga Dulani Meedeniya Senuri De Silva Pratheepan Yogarajah |
| author_sort | Lahiru Gamage |
| collection | DOAJ |
| description | Melanoma is a highly prevalent and lethal form of skin cancer, which has a significant impact globally. The chances of recovery for melanoma patients substantially improve with early detection. Currently, deep learning (DL) methods are gaining popularity in assisting with the identification of diseases using medical imaging. The paper introduces a computational model for classifying melanoma skin cancer images using convolutional neural networks (CNNs) and vision transformers (ViT) with the HAM10000 dataset. Both approaches utilize mask-guided techniques, employing a specialized U2-Net segmentation module to generate masks. The CNN-based approach utilizes ResNet50, VGG16, and Xception with transfer learning. The training process is enhanced using a Bayesian hyperparameter tuner. Moreover, this study applies gradient-weighted class activation mapping (Grad-CAM) and Grad-CAM++ to generate heatmaps to explain the classification models. These visual heatmaps elucidate the contribution of each input region to the classification outcome. The CNN-based model approach achieved the highest accuracy at 98.37% in the Xception model with a sensitivity and specificity of 95.92% and 99.01%, respectively. The ViT-based model approach achieved high values for accuracy, sensitivity, and specificity, such as 92.79%, 91.09%, and 93.54%, respectively. Furthermore, the performance of the model was assessed through intersection over union (IOU) and other qualitative evaluations. Finally, we developed the proposed model as a web application that can be used as a support tool for medical practitioners in real-time. The system usability study score of 86.87% is reported, which shows the usefulness of the proposed solution. |
| first_indexed | 2024-03-07T22:34:10Z |
| format | Article |
| id | doaj.art-043436a5095040b49e7501429d8c856c |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-07T22:34:10Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-043436a5095040b49e7501429d8c856c2024-02-23T15:14:39ZengMDPI AGElectronics2079-92922024-02-0113468010.3390/electronics13040680Melanoma Skin Cancer Identification with Explainability Utilizing Mask Guided TechniqueLahiru Gamage0Uditha Isuranga1Dulani Meedeniya2Senuri De Silva3Pratheepan Yogarajah4Department of Computer Science and Engineering, University of Moratuwa, Moratuwa 10400, Sri LankaDepartment of Computer Science and Engineering, University of Moratuwa, Moratuwa 10400, Sri LankaDepartment of Computer Science and Engineering, University of Moratuwa, Moratuwa 10400, Sri LankaDepartment of Anatomy, Yong Loo Lin School of Medicine, National University of Singapore, 4 Medical Drive, MD10, Singapore 117594, SingaporeSchool of Computing, Engineering and Intelligent System, Ulster University, Londonderry BT48 7JL, UKMelanoma is a highly prevalent and lethal form of skin cancer, which has a significant impact globally. The chances of recovery for melanoma patients substantially improve with early detection. Currently, deep learning (DL) methods are gaining popularity in assisting with the identification of diseases using medical imaging. The paper introduces a computational model for classifying melanoma skin cancer images using convolutional neural networks (CNNs) and vision transformers (ViT) with the HAM10000 dataset. Both approaches utilize mask-guided techniques, employing a specialized U2-Net segmentation module to generate masks. The CNN-based approach utilizes ResNet50, VGG16, and Xception with transfer learning. The training process is enhanced using a Bayesian hyperparameter tuner. Moreover, this study applies gradient-weighted class activation mapping (Grad-CAM) and Grad-CAM++ to generate heatmaps to explain the classification models. These visual heatmaps elucidate the contribution of each input region to the classification outcome. The CNN-based model approach achieved the highest accuracy at 98.37% in the Xception model with a sensitivity and specificity of 95.92% and 99.01%, respectively. The ViT-based model approach achieved high values for accuracy, sensitivity, and specificity, such as 92.79%, 91.09%, and 93.54%, respectively. Furthermore, the performance of the model was assessed through intersection over union (IOU) and other qualitative evaluations. Finally, we developed the proposed model as a web application that can be used as a support tool for medical practitioners in real-time. The system usability study score of 86.87% is reported, which shows the usefulness of the proposed solution.https://www.mdpi.com/2079-9292/13/4/680explainable AIdeep learningartificial intelligencemedical imagingCNNVIT |
| spellingShingle | Lahiru Gamage Uditha Isuranga Dulani Meedeniya Senuri De Silva Pratheepan Yogarajah Melanoma Skin Cancer Identification with Explainability Utilizing Mask Guided Technique Electronics explainable AI deep learning artificial intelligence medical imaging CNN VIT |
| title | Melanoma Skin Cancer Identification with Explainability Utilizing Mask Guided Technique |
| title_full | Melanoma Skin Cancer Identification with Explainability Utilizing Mask Guided Technique |
| title_fullStr | Melanoma Skin Cancer Identification with Explainability Utilizing Mask Guided Technique |
| title_full_unstemmed | Melanoma Skin Cancer Identification with Explainability Utilizing Mask Guided Technique |
| title_short | Melanoma Skin Cancer Identification with Explainability Utilizing Mask Guided Technique |
| title_sort | melanoma skin cancer identification with explainability utilizing mask guided technique |
| topic | explainable AI deep learning artificial intelligence medical imaging CNN VIT |
| url | https://www.mdpi.com/2079-9292/13/4/680 |
| work_keys_str_mv | AT lahirugamage melanomaskincanceridentificationwithexplainabilityutilizingmaskguidedtechnique AT udithaisuranga melanomaskincanceridentificationwithexplainabilityutilizingmaskguidedtechnique AT dulanimeedeniya melanomaskincanceridentificationwithexplainabilityutilizingmaskguidedtechnique AT senuridesilva melanomaskincanceridentificationwithexplainabilityutilizingmaskguidedtechnique AT pratheepanyogarajah melanomaskincanceridentificationwithexplainabilityutilizingmaskguidedtechnique |