Fairness Evolution in Continual Learning for Medical Imaging
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918083979902976 |
|---|---|
| author | Ceccon, Marina Pezze, Davide Dalle Fabris, Alessandro Susto, Gian Antonio |
| author_facet | Ceccon, Marina Pezze, Davide Dalle Fabris, Alessandro Susto, Gian Antonio |
| contents | Deep Learning has advanced significantly in medical applications, aiding disease diagnosis in Chest X-ray images. However, expanding model capabilities with new data remains a challenge, which Continual Learning (CL) aims to address. Previous studies have evaluated CL strategies based on classification performance; however, in sensitive domains such as healthcare, it is crucial to assess performance across socially salient groups to detect potential biases. This study examines how bias evolves across tasks using domain-specific fairness metrics and how different CL strategies impact this evolution. Our results show that Learning without Forgetting and Pseudo-Label achieve optimal classification performance, but Pseudo-Label is less biased. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_02480 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Fairness Evolution in Continual Learning for Medical Imaging Ceccon, Marina Pezze, Davide Dalle Fabris, Alessandro Susto, Gian Antonio Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Deep Learning has advanced significantly in medical applications, aiding disease diagnosis in Chest X-ray images. However, expanding model capabilities with new data remains a challenge, which Continual Learning (CL) aims to address. Previous studies have evaluated CL strategies based on classification performance; however, in sensitive domains such as healthcare, it is crucial to assess performance across socially salient groups to detect potential biases. This study examines how bias evolves across tasks using domain-specific fairness metrics and how different CL strategies impact this evolution. Our results show that Learning without Forgetting and Pseudo-Label achieve optimal classification performance, but Pseudo-Label is less biased. |
| title | Fairness Evolution in Continual Learning for Medical Imaging |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.02480 |