The rise of ai language pathologists: Exploring two-level prompt learning for few-shot weakly-supervised whole slide image classification

L Qu, K Fu, M Wang, Z Song - Advances in Neural …, 2023‏ - proceedings.neurips.cc
This paper introduces the novel concept of few-shot weakly supervised learning for
pathology Whole Slide Image (WSI) classification, denoted as FSWC. A solution is proposed …

Boosting whole slide image classification from the perspectives of distribution, correlation and magnification

L Qu, Z Yang, M Duan, Y Ma, S Wang… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
Bag-based multiple instance learning (MIL) methods have become the mainstream for
Whole Slide Image (WSI) classification. However, there are still three important issues that …

Boosting multiple instance learning models for whole slide image classification: A model-agnostic framework based on counterfactual inference

W Lin, Z Zhuang, L Yu, L Wang - … of the AAAI Conference on Artificial …, 2024‏ - ojs.aaai.org
Multiple instance learning is an effective paradigm for whole slide image (WSI) classification,
where labels are only provided at the bag level. However, instance-level prediction is also …

MSCPT: Few-shot Whole Slide Image Classification with Multi-scale and Context-focused Prompt Tuning

M Han, L Qu, D Yang, X Zhang, X Wang… - ar** an instance-level classifier via weakly-supervised self-training for whole slide image classification
Y Ma, M Yuan, A Shen, X Luo, B An, X Chen… - Computer Methods and …, 2025‏ - Elsevier
Abstract Background and Objective Pathology image classification is crucial in clinical
cancer diagnosis and computer-aided diagnosis. Whole Slide Image (WSI) classification is …

Object-based feedback attention in convolutional neural networks improves tumour detection in digital pathology

A Broad, A Wright, C McGenity, D Treanor… - Scientific Reports, 2024‏ - nature.com
Human visual attention allows prior knowledge or expectations to influence visual
processing, allocating limited computational resources to only that part of the image that are …