What type of study is this?

This is a Quantitative Study study.

September 20, 20250 citations

Curriculum Hierarchical Knowledge Distillation for Bias-Free Survival Prediction

CLChaozhuo LiBeijing University of Posts and Telecommunications ZTZhihao TangBeijing University of Posts and Telecommunications MZMingji ZhangFujian Medical University

Key Points

The proposed PathoKD method enhances prediction accuracy across various patient groups, minimizing bias.
Integrating hierarchical knowledge distillation with a curriculum learning framework effectively reduces performance gaps.
Extensive evaluations show PathoKD outperforms traditional models using popular datasets.
This approach addresses variability in whole slide images, critical for survival prediction accuracy.

Abstract

Survival prediction is a pivotal task for estimating mortality risk within a given timeframe based on whole slide images (WSIs). Conventional models typically assume that WSIs across patients are independent and identically distributed, an assumption that may not hold due to inherent variability in WSI preparation and the uncertain condition of infected tissues. These uncontrollable external factors introduce significant variability in the numbers and resolutions of WSIs across patients, leading to bias and compromised performance, particularly for tail patients with limited data. In this paper, we propose a novel approach, PathoKD, based on knowledge distillation. Recognizing the hierarchical nature of disease progression and the data scarcity issues associated with vanilla knowledge distillation methods, PathoKD integrates a novel curriculum learning framework with hierarchical knowledge distillation. This integration effectively mitigates the performance gap between head and tail patients, thereby enhancing prediction accuracy across patient groups. Our proposal is extensively evaluated over popular datasets and experimental results demonstrate its superiority.

AI에게 질문

Bookmark

View Full Paper