Domain Incremental Learning for Pandemic-Resilient Chest X-Ray Analysis
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911692527501312 |
|---|---|
| author | Kim, Danu |
| author_facet | Kim, Danu |
| contents | Deep learning models achieved high accuracy in pneumonia detection from chest X-rays. However, their generalization across clinical domains remains limited due to variations in imaging devices, acquisition protocols, and institutional conditions. This study introduces a replay-based domain-incremental continual learning designed to enable continual adaptation to cross-domain variations without catastrophic forgetting. The proposed method incorporates a class-aware balanced replay to maintain balanced class representation within a constrained memory and a class-aware loss to dynamically reweight class imbalance during training. Experiments conducted on a domain-shifted PneumoniaMNIST dataset consisting of five simulated domains demonstrate that the proposed method achieves an average accuracy of 88.66%, outperforming Experience Replay, Fine-Tuning, and Joint Training baselines. These findings highlight the efficacy of the proposed approach in achieving robust and consistent pneumonia detection across clinical environment variations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_17729 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Domain Incremental Learning for Pandemic-Resilient Chest X-Ray Analysis Kim, Danu Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Deep learning models achieved high accuracy in pneumonia detection from chest X-rays. However, their generalization across clinical domains remains limited due to variations in imaging devices, acquisition protocols, and institutional conditions. This study introduces a replay-based domain-incremental continual learning designed to enable continual adaptation to cross-domain variations without catastrophic forgetting. The proposed method incorporates a class-aware balanced replay to maintain balanced class representation within a constrained memory and a class-aware loss to dynamically reweight class imbalance during training. Experiments conducted on a domain-shifted PneumoniaMNIST dataset consisting of five simulated domains demonstrate that the proposed method achieves an average accuracy of 88.66%, outperforming Experience Replay, Fine-Tuning, and Joint Training baselines. These findings highlight the efficacy of the proposed approach in achieving robust and consistent pneumonia detection across clinical environment variations. |
| title | Domain Incremental Learning for Pandemic-Resilient Chest X-Ray Analysis |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2605.17729 |