Improving Diagnostic Accuracy of Pigmented Skin Lesions With CNNs: an Application on the DermaMNIST Dataset
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911061295235072 |
|---|---|
| author | Kadric, Nerma Akagic, Amila Kapo, Medina |
| author_facet | Kadric, Nerma Akagic, Amila Kapo, Medina |
| contents | Pigmented skin lesions represent localized areas of increased melanin and can indicate serious conditions like melanoma, a major contributor to skin cancer mortality. The MedMNIST v2 dataset, inspired by MNIST, was recently introduced to advance research in biomedical imaging and includes DermaMNIST, a dataset for classifying pigmented lesions based on the HAM10000 dataset. This study assesses ResNet-50 and EfficientNetV2L models for multi-class classification using DermaMNIST, employing transfer learning and various layer configurations. One configuration achieves results that match or surpass existing methods. This study suggests that convolutional neural networks (CNNs) can drive progress in biomedical image analysis, significantly enhancing diagnostic accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_12961 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Improving Diagnostic Accuracy of Pigmented Skin Lesions With CNNs: an Application on the DermaMNIST Dataset Kadric, Nerma Akagic, Amila Kapo, Medina Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Pigmented skin lesions represent localized areas of increased melanin and can indicate serious conditions like melanoma, a major contributor to skin cancer mortality. The MedMNIST v2 dataset, inspired by MNIST, was recently introduced to advance research in biomedical imaging and includes DermaMNIST, a dataset for classifying pigmented lesions based on the HAM10000 dataset. This study assesses ResNet-50 and EfficientNetV2L models for multi-class classification using DermaMNIST, employing transfer learning and various layer configurations. One configuration achieves results that match or surpass existing methods. This study suggests that convolutional neural networks (CNNs) can drive progress in biomedical image analysis, significantly enhancing diagnostic accuracy. |
| title | Improving Diagnostic Accuracy of Pigmented Skin Lesions With CNNs: an Application on the DermaMNIST Dataset |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.12961 |