EUVIMEDEUVIMED entdecken
Crossref

Long-Tailed and Inter-Class Homogeneity Matters in Multi-Class Weakly Supervised Tissue Segmentation of Histopathology Images

Siyang Feng, Xipeng Pan, Huadeng Wang, Zhenbing Liu, Weidong Zhang, Rushi Lan

IEEE Transactions on Image Processing · 2026

DOI: 10.1109/tip.2026.3671622 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Siyang Feng und 5 weiteren Autor:innen. Hauptthemen laut MEDLINE: Histocytochemistry, Image Interpretation, Computer-Assisted, Supervised Machine Learning, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 64 Literaturangaben. Gefördert von: Guangxi Natural Science Foundation, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Using image-level weakly supervised semantic segmentation (WSSS) techniques to segment tissue regions in giga-pixel histopathological whole slide images (WSI) has garnered widespread attention, as it can reduce many annotation workloads for pathologists. Most recent studies are based on class activation mapping (CAM) to generate pseudo masks, which are then used to train segmentation model in a fully supervised manner. However, it is still a challenge to accurately segment non-predominant tissue categories due to the existence of long-tailed and inter-class homogeneity matters. For these matters, we propose three designs to solve them: 1) Diffusion-based Data Generation to synthesis new images of tail class to expand data distribution; 2) Feature Recalibration to reassign the logits in CAM to narrow the feature-level prediction gap between predominant and non-predominant classes; 3) Grade-skip Learning to correct the under-fitting tendency of hard samples during the segmentation phase. Moreover, we also design a powerful pipeline LoHo for histopathology tissue segmentation. Extensive experiments demonstrate that our method not only achieves new state-of-the-art performances but also significantly improves segmentation of tail classes. In addition, our methods are plug-and-play, making it easily integrable into many mainstream WSSS frameworks.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

HistocytochemistryImage Interpretation, Computer-AssistedSupervised Machine LearningImage Processing, Computer-AssistedAlgorithmsHumans

Förderung

  • Guangxi Natural Science Foundation
  • National Natural Science Foundation of China

Zitieren

APA

Feng, S., Pan, X., Wang, H., Liu, Z., Zhang, W., & Lan, R. (2026). Long-Tailed and Inter-Class Homogeneity Matters in Multi-Class Weakly Supervised Tissue Segmentation of Histopathology Images. IEEE Transactions on Image Processing. https://doi.org/10.1109/tip.2026.3671622

Vancouver

Feng S, Pan X, Wang H, Liu Z, Zhang W, Lan R. Long-Tailed and Inter-Class Homogeneity Matters in Multi-Class Weakly Supervised Tissue Segmentation of Histopathology Images. IEEE Transactions on Image Processing. 2026. doi:10.1109/tip.2026.3671622

BibTeX
@article{Feng2026,
  author = {Feng, Siyang and Pan, Xipeng and Wang, Huadeng and Liu, Zhenbing and Zhang, Weidong and Lan, Rushi},
  title = {Long-Tailed and Inter-Class Homogeneity Matters in Multi-Class Weakly Supervised Tissue Segmentation of Histopathology Images},
  journal = {IEEE Transactions on Image Processing},
  year = {2026},
  doi = {10.1109/tip.2026.3671622}
}
Kostenlos starten →