TY - GEN
T1 - HASD
T2 - 28th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2025
AU - Liu, Jingsong
AU - Li, Han
AU - Yang, Chen
AU - Deutges, Michael
AU - Sadafi, Ario
AU - You, Xin
AU - Breininger, Katharina
AU - Navab, Nassir
AU - Schüffler, Peter J.
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.
PY - 2026
Y1 - 2026
N2 - Domain shift is a critical problem for artificial intelligence (AI) in pathology as it is heavily influenced by center-specific conditions. Current pathology domain adaptation methods focus on image patches rather than whole-slide images (WSI), thus failing to capture global WSI features required in typical clinical scenarios. In this work, we address the challenges of slide-level domain shift by proposing a Hierarchical Adaptation framework for Slide-level Domain-shift (HASD). HASD achieves multi-scale feature consistency and computationally efficient slide-level domain adaptation through two key components: (1) a hierarchical adaptation framework that integrates a Domain-level Alignment Solver for feature alignment, a Slide-level Geometric Invariance Regularization to preserve the morphological structure, and a Patch-level Attention Consistency Regularization to maintain local critical diagnostic cues; and (2) a prototype selection mechanism that reduces computational overhead. We validate our method on two slide-level tasks across five datasets, achieving a 4.1% AUROC improvement in a Breast Cancer HER2 Grading cohort and a 3.9% C-index gain in a UCEC survival prediction cohort. Our method provides a practical and reliable slide-level domain adaption solution for pathology institutions, minimizing both computational and annotation costs. Code is available at https://github.com/TumVink/HASD.
AB - Domain shift is a critical problem for artificial intelligence (AI) in pathology as it is heavily influenced by center-specific conditions. Current pathology domain adaptation methods focus on image patches rather than whole-slide images (WSI), thus failing to capture global WSI features required in typical clinical scenarios. In this work, we address the challenges of slide-level domain shift by proposing a Hierarchical Adaptation framework for Slide-level Domain-shift (HASD). HASD achieves multi-scale feature consistency and computationally efficient slide-level domain adaptation through two key components: (1) a hierarchical adaptation framework that integrates a Domain-level Alignment Solver for feature alignment, a Slide-level Geometric Invariance Regularization to preserve the morphological structure, and a Patch-level Attention Consistency Regularization to maintain local critical diagnostic cues; and (2) a prototype selection mechanism that reduces computational overhead. We validate our method on two slide-level tasks across five datasets, achieving a 4.1% AUROC improvement in a Breast Cancer HER2 Grading cohort and a 3.9% C-index gain in a UCEC survival prediction cohort. Our method provides a practical and reliable slide-level domain adaption solution for pathology institutions, minimizing both computational and annotation costs. Code is available at https://github.com/TumVink/HASD.
KW - Domain shift
KW - Pathology slide-level tasks
UR - https://www.scopus.com/pages/publications/105017845919
U2 - 10.1007/978-3-032-04978-0_32
DO - 10.1007/978-3-032-04978-0_32
M3 - Conference contribution
AN - SCOPUS:105017845919
SN - 9783032049773
T3 - Lecture Notes in Computer Science
SP - 332
EP - 342
BT - Medical Image Computing and Computer Assisted Intervention, MICCAI 2025 - 28th International Conference, Proceedings
A2 - Gee, James C.
A2 - Hong, Jaesung
A2 - Sudre, Carole H.
A2 - Golland, Polina
A2 - Alexander, Daniel C.
A2 - Iglesias, Juan Eugenio
A2 - Venkataraman, Archana
A2 - Kim, Jong Hyo
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 23 September 2025 through 27 September 2025
ER -
