EUVIMEDEUVIMED entdecken
Crossref

MSCPT: Few-Shot Whole Slide Image Classification With Multi-Scale and Context-Focused Prompt Tuning

Minghao Han, Linhao Qu, Dingkang Yang, Xukun Zhang, Xiaoying Wang, Lihua Zhang

IEEE Transactions on Medical Imaging · 2025-09 · 44 (9) · 3756-3769

DOI: 10.1109/tmi.2025.3564976 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2025-09. Verfasst von Minghao Han und 5 weiteren Autor:innen. Hauptthemen laut MEDLINE: Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multiple instance learning (MIL) has become a standard paradigm for the weakly supervised classification of whole slide images (WSIs). However, this paradigm relies on using a large number of labeled WSIs for training. The lack of training data and the presence of rare diseases pose significant challenges for these methods. Prompt tuning combined with pre-trained Vision-Language models (VLMs) is an effective solution to the Few-shot Weakly Supervised WSI Classification (FSWC) task. Nevertheless, applying prompt tuning methods designed for natural images to WSIs presents three significant challenges: 1) These methods fail to fully leverage the prior knowledge from the VLM's text modality; 2) They overlook the essential multi-scale and contextual information in WSIs, leading to suboptimal results; and 3) They lack exploration of instance aggregation methods. To address these problems, we propose a Multi-Scale and Context-focused Prompt Tuning (MSCPT) method for FSWC task. Specifically, MSCPT employs the frozen large language model to generate pathological visual language prior knowledge at multiple scales, guiding hierarchical prompt tuning. Additionally, we design a graph prompt tuning module to learn essential contextual information within WSI, and finally, a non-parametric cross-guided instance aggregation module has been introduced to derive the WSI-level features. Extensive experiments, visualizations, and interpretability analyses were conducted on five datasets and three downstream tasks using three VLMs, demonstrating the strong performance of our MSCPT. All codes have been made publicly accessible at https://github.com/Hanminghao/MSCPT.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Interpretation, Computer-AssistedHumansAlgorithmsMachine Learning

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Han, M., Qu, L., Yang, D., Zhang, X., Wang, X., & Zhang, L. (2025). MSCPT: Few-Shot Whole Slide Image Classification With Multi-Scale and Context-Focused Prompt Tuning. IEEE Transactions on Medical Imaging, 44(9), 3756-3769. https://doi.org/10.1109/tmi.2025.3564976

Vancouver

Han M, Qu L, Yang D, Zhang X, Wang X, Zhang L. MSCPT: Few-Shot Whole Slide Image Classification With Multi-Scale and Context-Focused Prompt Tuning. IEEE Transactions on Medical Imaging. 2025;44(9):3756-3769. doi:10.1109/tmi.2025.3564976

BibTeX
@article{Han2025,
  author = {Han, Minghao and Qu, Linhao and Yang, Dingkang and Zhang, Xukun and Wang, Xiaoying and Zhang, Lihua},
  title = {MSCPT: Few-Shot Whole Slide Image Classification With Multi-Scale and Context-Focused Prompt Tuning},
  journal = {IEEE Transactions on Medical Imaging},
  year = {2025},
  volume = {44},
  number = {9},
  pages = {3756--3769},
  doi = {10.1109/tmi.2025.3564976}
}
Kostenlos starten →