Robustness and sex differences in skin cancer detection: logistic regression vs CNNs
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915526745260032 |
|---|---|
| author | Pedersen, Nikolette Sydendal, Regitze Wulff, Andreas Raumanns, Ralf Petersen, Eike Cheplygina, Veronika |
| author_facet | Pedersen, Nikolette Sydendal, Regitze Wulff, Andreas Raumanns, Ralf Petersen, Eike Cheplygina, Veronika |
| contents | Deep learning has been reported to achieve high performances in the detection of skin cancer, yet many challenges regarding the reproducibility of results and biases remain. This study is a replication (different data, same analysis) of a previous study on Alzheimer's disease detection, which studied the robustness of logistic regression (LR) and convolutional neural networks (CNN) across patient sexes. We explore sex bias in skin cancer detection, using the PAD-UFES-20 dataset with LR trained on handcrafted features reflecting dermatological guidelines (ABCDE and the 7-point checklist), and a pre-trained ResNet-50 model. We evaluate these models in alignment with the replicated study: across multiple training datasets with varied sex composition to determine their robustness. Our results show that both the LR and the CNN were robust to the sex distribution, but the results also revealed that the CNN had a significantly higher accuracy (ACC) and area under the receiver operating characteristics (AUROC) for male patients compared to female patients. The data and relevant scripts to reproduce our results are publicly available (https://github.com/ nikodice4/Skin-cancer-detection-sex-bias). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_11415 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Robustness and sex differences in skin cancer detection: logistic regression vs CNNs Pedersen, Nikolette Sydendal, Regitze Wulff, Andreas Raumanns, Ralf Petersen, Eike Cheplygina, Veronika Computer Vision and Pattern Recognition Machine Learning Deep learning has been reported to achieve high performances in the detection of skin cancer, yet many challenges regarding the reproducibility of results and biases remain. This study is a replication (different data, same analysis) of a previous study on Alzheimer's disease detection, which studied the robustness of logistic regression (LR) and convolutional neural networks (CNN) across patient sexes. We explore sex bias in skin cancer detection, using the PAD-UFES-20 dataset with LR trained on handcrafted features reflecting dermatological guidelines (ABCDE and the 7-point checklist), and a pre-trained ResNet-50 model. We evaluate these models in alignment with the replicated study: across multiple training datasets with varied sex composition to determine their robustness. Our results show that both the LR and the CNN were robust to the sex distribution, but the results also revealed that the CNN had a significantly higher accuracy (ACC) and area under the receiver operating characteristics (AUROC) for male patients compared to female patients. The data and relevant scripts to reproduce our results are publicly available (https://github.com/ nikodice4/Skin-cancer-detection-sex-bias). |
| title | Robustness and sex differences in skin cancer detection: logistic regression vs CNNs |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2504.11415 |