Taming Domain Shift in Multi-source CT-Scan Classification via Input-Space Standardization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908468644937728 |
|---|---|
| author | Lee, Chia-Ming Qiu, Bo-Cheng Chen, Ting-Yao Sun, Ming-Han Lin, Fang-Ying Tsai, Jung-Tse Tsai, I-An Lin, Yu-Fan Hsu, Chih-Chung |
| author_facet | Lee, Chia-Ming Qiu, Bo-Cheng Chen, Ting-Yao Sun, Ming-Han Lin, Fang-Ying Tsai, Jung-Tse Tsai, I-An Lin, Yu-Fan Hsu, Chih-Chung |
| contents | Multi-source CT-scan classification suffers from domain shifts that impair cross-source generalization. While preprocessing pipelines combining Spatial-Slice Feature Learning (SSFL++) and Kernel-Density-based Slice Sampling (KDS) have shown empirical success, the mechanisms underlying their domain robustness remain underexplored. This study analyzes how this input-space standardization manages the trade-off between local discriminability and cross-source generalization. The SSFL++ and KDS pipeline performs spatial and temporal standardization to reduce inter-source variance, effectively mapping disparate inputs into a consistent target space. This preemptive alignment mitigates domain shift and simplifies the learning task for network optimization. Experimental validation demonstrates consistent improvements across architectures, proving the benefits stem from the preprocessing itself. The approach's effectiveness was validated by securing first place in a competitive challenge, supporting input-space standardization as a robust and practical solution for multi-institutional medical imaging. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_19858 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Taming Domain Shift in Multi-source CT-Scan Classification via Input-Space Standardization Lee, Chia-Ming Qiu, Bo-Cheng Chen, Ting-Yao Sun, Ming-Han Lin, Fang-Ying Tsai, Jung-Tse Tsai, I-An Lin, Yu-Fan Hsu, Chih-Chung Image and Video Processing Computational Engineering, Finance, and Science Computer Vision and Pattern Recognition Machine Learning Multi-source CT-scan classification suffers from domain shifts that impair cross-source generalization. While preprocessing pipelines combining Spatial-Slice Feature Learning (SSFL++) and Kernel-Density-based Slice Sampling (KDS) have shown empirical success, the mechanisms underlying their domain robustness remain underexplored. This study analyzes how this input-space standardization manages the trade-off between local discriminability and cross-source generalization. The SSFL++ and KDS pipeline performs spatial and temporal standardization to reduce inter-source variance, effectively mapping disparate inputs into a consistent target space. This preemptive alignment mitigates domain shift and simplifies the learning task for network optimization. Experimental validation demonstrates consistent improvements across architectures, proving the benefits stem from the preprocessing itself. The approach's effectiveness was validated by securing first place in a competitive challenge, supporting input-space standardization as a robust and practical solution for multi-institutional medical imaging. |
| title | Taming Domain Shift in Multi-source CT-Scan Classification via Input-Space Standardization |
| topic | Image and Video Processing Computational Engineering, Finance, and Science Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2507.19858 |