Transformer-Based Approach to Melanoma Detection
Melanoma is a malignant cancer type which develops when DNA damage occurs (mainly due to environmental factors such as ultraviolet rays). Often, melanoma results in intense and aggressive cell growth that, if not caught in time, can bring one toward death. Thus, early identification at the initial s...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/12/5677 |
| _version_ | 1797592663821647872 |
|---|---|
| author | Giansalvo Cirrincione Sergio Cannata Giovanni Cicceri Francesco Prinzi Tiziana Currieri Marta Lovino Carmelo Militello Eros Pasero Salvatore Vitabile |
| author_facet | Giansalvo Cirrincione Sergio Cannata Giovanni Cicceri Francesco Prinzi Tiziana Currieri Marta Lovino Carmelo Militello Eros Pasero Salvatore Vitabile |
| author_sort | Giansalvo Cirrincione |
| collection | DOAJ |
| description | Melanoma is a malignant cancer type which develops when DNA damage occurs (mainly due to environmental factors such as ultraviolet rays). Often, melanoma results in intense and aggressive cell growth that, if not caught in time, can bring one toward death. Thus, early identification at the initial stage is fundamental to stopping the spread of cancer. In this paper, a ViT-based architecture able to classify melanoma versus non-cancerous lesions is presented. The proposed predictive model is trained and tested on public skin cancer data from the ISIC challenge, and the obtained results are highly promising. Different classifier configurations are considered and analyzed in order to find the most discriminating one. The best one reached an accuracy of 0.948, sensitivity of 0.928, specificity of 0.967, and AUROC of 0.948. |
| first_indexed | 2024-03-11T01:57:20Z |
| format | Article |
| id | doaj.art-c031540b54c64271b7c49190d36c8760 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T01:57:20Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-c031540b54c64271b7c49190d36c87602023-11-18T12:34:31ZengMDPI AGSensors1424-82202023-06-012312567710.3390/s23125677Transformer-Based Approach to Melanoma DetectionGiansalvo Cirrincione0Sergio Cannata1Giovanni Cicceri2Francesco Prinzi3Tiziana Currieri4Marta Lovino5Carmelo Militello6Eros Pasero7Salvatore Vitabile8Département Electronique-Electrotechnique-Automatique (EEA), University of Picardie Jules Verne, 80000 Amiens, FranceDepartment of Electronics and Telecommunications, Politecnico di Torino, 10129 Turin, ItalyDepartment of Biomedicine, Neuroscience and Advanced Diagnostics (BiND), University of Palermo, 90127 Palermo, ItalyDepartment of Biomedicine, Neuroscience and Advanced Diagnostics (BiND), University of Palermo, 90127 Palermo, ItalyDepartment of Biomedicine, Neuroscience and Advanced Diagnostics (BiND), University of Palermo, 90127 Palermo, ItalyDepartment of Engineering Enzo Ferrari, University of Modena and Reggio Emilia, 41125 Modena, ItalyInstitute for High-Performance Computing and Networking (ICAR-CNR), Italian National Research Council, 90146 Palermo, ItalyDepartment of Electronics and Telecommunications, Politecnico di Torino, 10129 Turin, ItalyDepartment of Biomedicine, Neuroscience and Advanced Diagnostics (BiND), University of Palermo, 90127 Palermo, ItalyMelanoma is a malignant cancer type which develops when DNA damage occurs (mainly due to environmental factors such as ultraviolet rays). Often, melanoma results in intense and aggressive cell growth that, if not caught in time, can bring one toward death. Thus, early identification at the initial stage is fundamental to stopping the spread of cancer. In this paper, a ViT-based architecture able to classify melanoma versus non-cancerous lesions is presented. The proposed predictive model is trained and tested on public skin cancer data from the ISIC challenge, and the obtained results are highly promising. Different classifier configurations are considered and analyzed in order to find the most discriminating one. The best one reached an accuracy of 0.948, sensitivity of 0.928, specificity of 0.967, and AUROC of 0.948.https://www.mdpi.com/1424-8220/23/12/5677skin cancermelanoma detectionvision transformersartificial intelligencedecision-making support |
| spellingShingle | Giansalvo Cirrincione Sergio Cannata Giovanni Cicceri Francesco Prinzi Tiziana Currieri Marta Lovino Carmelo Militello Eros Pasero Salvatore Vitabile Transformer-Based Approach to Melanoma Detection Sensors skin cancer melanoma detection vision transformers artificial intelligence decision-making support |
| title | Transformer-Based Approach to Melanoma Detection |
| title_full | Transformer-Based Approach to Melanoma Detection |
| title_fullStr | Transformer-Based Approach to Melanoma Detection |
| title_full_unstemmed | Transformer-Based Approach to Melanoma Detection |
| title_short | Transformer-Based Approach to Melanoma Detection |
| title_sort | transformer based approach to melanoma detection |
| topic | skin cancer melanoma detection vision transformers artificial intelligence decision-making support |
| url | https://www.mdpi.com/1424-8220/23/12/5677 |
| work_keys_str_mv | AT giansalvocirrincione transformerbasedapproachtomelanomadetection AT sergiocannata transformerbasedapproachtomelanomadetection AT giovannicicceri transformerbasedapproachtomelanomadetection AT francescoprinzi transformerbasedapproachtomelanomadetection AT tizianacurrieri transformerbasedapproachtomelanomadetection AT martalovino transformerbasedapproachtomelanomadetection AT carmelomilitello transformerbasedapproachtomelanomadetection AT erospasero transformerbasedapproachtomelanomadetection AT salvatorevitabile transformerbasedapproachtomelanomadetection |