EUVIMEDEUVIMED entdecken
Crossref

Frequency-Aware Causal Regularization for Multiple Instance Learning in Whole Slide Image Classification

Dawei Fan, Lifang Wei, Mingyue Han, Tao Xu, Xuemei Qiu, Yanping Chen, Changcai Yang, Riqing Chen

IEEE Transactions on Medical Imaging · 2026-08 · 45 (8) · 4287-4302

DOI: 10.1109/tmi.2026.3697015 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2026-08. Verfasst von Dawei Fan und 7 weiteren Autor:innen. Hauptthemen laut MEDLINE: Multiple-Instance Learning Algorithms, Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 55 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Fujian Province, Fujian Health Science and Technology Plan Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Whole slide image (WSI) classification is a critical task in computational pathology and is aimed at providing automated diagnostic support through high-resolution tissue image analysis. In weakly supervised WSI classification scenarios, the main challenge concerns the traditional multiple instance learning (MIL) methods, which rely on instance-level embeddings aggregated by an attention-based pooling mechanism. These methods often depend on data-driven statistical correlations, leading to misalignments between their attention allocation schemes and histopathological diagnostic regions and reducing the resulting prediction reliability. To address this, we propose frequency-aware causal regularized multiple instance learning (FC-MIL), an innovative framework combining that combines frequency-aware attention (FAA) and causal regularization (CR). FAA extracts more granular, fine-grained histological textures by jointly modeling spatial- and frequency- domain features, whereas CR introduces feature-level counterfactual perturbations as an intervention-inspired regularizer in the latent space, encouraging the model to rely less on spurious correlations and more on invariant pathological cues. Experimental results obtained on four WSI datasets show that FC-MIL outperforms the state-of-the-art MIL methods in terms of both accuracy and interpretability. Our source code is available at https://github.com/7FFDW/FCMIL.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Multiple-Instance Learning AlgorithmsImage Interpretation, Computer-AssistedHumansAlgorithms

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Fujian Province
  • Fujian Health Science and Technology Plan Project

Zitieren

APA

Fan, D., Wei, L., Han, M., Xu, T., Qiu, X., Chen, Y., Yang, C., & Chen, R. (2026). Frequency-Aware Causal Regularization for Multiple Instance Learning in Whole Slide Image Classification. IEEE Transactions on Medical Imaging, 45(8), 4287-4302. https://doi.org/10.1109/tmi.2026.3697015

Vancouver

Fan D, Wei L, Han M, Xu T, Qiu X, Chen Y, et al. Frequency-Aware Causal Regularization for Multiple Instance Learning in Whole Slide Image Classification. IEEE Transactions on Medical Imaging. 2026;45(8):4287-4302. doi:10.1109/tmi.2026.3697015

BibTeX
@article{Fan2026,
  author = {Fan, Dawei and Wei, Lifang and Han, Mingyue and Xu, Tao and Qiu, Xuemei and Chen, Yanping and Yang, Changcai and Chen, Riqing},
  title = {Frequency-Aware Causal Regularization for Multiple Instance Learning in Whole Slide Image Classification},
  journal = {IEEE Transactions on Medical Imaging},
  year = {2026},
  volume = {45},
  number = {8},
  pages = {4287--4302},
  doi = {10.1109/tmi.2026.3697015}
}
Kostenlos starten →