Robust multi-domain digital pathology image segmentation via joint balancing representation learning.
Saved in:
| Title: | Robust multi-domain digital pathology image segmentation via joint balancing representation learning. |
|---|---|
| Authors: | Xu, Qiaoyi1 (AUTHOR) p114345@siswa.ukm.edu.my, Adam, Afzan1,2 (AUTHOR) afzan@ukm.edu.my, Abdullah, Azizi1 (AUTHOR) azizia@ukm.edu.my, Chen, Tao3 (AUTHOR) t66chen@uwaterloo.ca, Zhang, Xinglin4 (AUTHOR) xinglinzhang@imagecore.com.cn, Shephard, Adam2 (AUTHOR) Adam.Shephard@warwick.ac.uk, Pei Sze, Patsy Ng5 (AUTHOR) peisze.ng@premierintegratedlabs.com.my, Masir, Noraidah6 (AUTHOR) noraidah.masir@premierintegratedlabs.com.my, Li, Lei1,7 (AUTHOR) lenny.lilei.cs@gmail.com, Rahayu, Reena8 (AUTHOR) reenarahayu@ppukm.ukm.edu.my |
| Source: | Expert Systems with Applications. Jul2026, Vol. 320, pN.PAG-N.PAG. 1p. |
| Subjects: | Image segmentation, Machine learning, Breast tumors, Generalization, Tissue analysis, Digital diagnostic imaging |
| Abstract: | • Domain contribution imbalance is identified as a key challenge in multi-domain learning. • A joint balancing representation learning framework is proposed to address this issue. • Boundary generalization is explicitly modeled via cross-domain consistency. • Robust segmentation is achieved across heterogeneous pathology domains. [Display omitted] Multi-domain learning (MDL) seeks to mitigate performance degradation caused by domain-specific feature shifts between training and testing environments. In breast cancer digital pathology, such shifts result from variations in staining protocols, imaging devices, and tissue preparation. Existing MDL methods focus on aligning feature discrepancies across domains, often neglecting inter-domain feature balance caused by data distribution disparities. Addressing this balance is essential for effective cross-domain learning in breast cancer pathology, particularly in clinically diverse settings. Additionally, leveraging multi-source training data to enhance model adaptability across pathological domains remains challenging. We introduce a Joint Training Strategy (JTS) and a novel breast cancer digital pathology dataset with expert annotations to capture pathological heterogeneity across multiple domains. We propose Differential Ratio Integration with Twin-domain Training (DRIFT) for multi-source digital pathology image segmentation, addressing domain adaptation through: (1) PRISM-DD, a dynamic data distribution mechanism that balances domain contributions to optimize segmentation, and (2) AMBiCoL, a multi-level loss function integrating adaptive boundary masks with bidirectional consistency modeling to enhance generalization. Experiments on two breast cancer digital pathology datasets demonstrate that DRIFT outperforms state-of-the-art methods, supporting its potential for robust, scalable multi-domain segmentation in computational pathology. Code is available at https://github.com/Joycecc123/DRIFT. [ABSTRACT FROM AUTHOR] |
| Copyright of Expert Systems with Applications is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
Be the first to leave a comment!
