On the Interplay of Human-AI Alignment,Fairness, and Performance Trade-offs in Medical Imaging
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_ | 1866915288244551680 |
|---|---|
| author | Luo, Haozhe Zhou, Ziyu Shu, Zixin de Mortanges, Aurélie Pahud Berke, Robert Reyes, Mauricio |
| author_facet | Luo, Haozhe Zhou, Ziyu Shu, Zixin de Mortanges, Aurélie Pahud Berke, Robert Reyes, Mauricio |
| contents | Deep neural networks excel in medical imaging but remain prone to biases, leading to fairness gaps across demographic groups. We provide the first systematic exploration of Human-AI alignment and fairness in this domain. Our results show that incorporating human insights consistently reduces fairness gaps and enhances out-of-domain generalization, though excessive alignment can introduce performance trade-offs, emphasizing the need for calibrated strategies. These findings highlight Human-AI alignment as a promising approach for developing fair, robust, and generalizable medical AI systems, striking a balance between expert guidance and automated efficiency. Our code is available at https://github.com/Roypic/Aligner. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_10231 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | On the Interplay of Human-AI Alignment,Fairness, and Performance Trade-offs in Medical Imaging Luo, Haozhe Zhou, Ziyu Shu, Zixin de Mortanges, Aurélie Pahud Berke, Robert Reyes, Mauricio Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Deep neural networks excel in medical imaging but remain prone to biases, leading to fairness gaps across demographic groups. We provide the first systematic exploration of Human-AI alignment and fairness in this domain. Our results show that incorporating human insights consistently reduces fairness gaps and enhances out-of-domain generalization, though excessive alignment can introduce performance trade-offs, emphasizing the need for calibrated strategies. These findings highlight Human-AI alignment as a promising approach for developing fair, robust, and generalizable medical AI systems, striking a balance between expert guidance and automated efficiency. Our code is available at https://github.com/Roypic/Aligner. |
| title | On the Interplay of Human-AI Alignment,Fairness, and Performance Trade-offs in Medical Imaging |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2505.10231 |