Prior-Anchored Debiasing for Long-Tailed Multi-Organ Pathology Report Generation

2026-07-01

AI Summary

This work addresses the visual and textual biases arising from the long-tailed distribution of organ categories in multi-organ pathological report generation. To mitigate these biases, the authors propose PriOrGen, a novel framework featuring a dual-path debiasing mechanism. Specifically, an information bottleneck module anchored by visual prototypes preserves diagnostically critical visual features, while a learnable organ-specific meta-report anchor bank injects adaptive textual priors. This joint debiasing strategy operates cohesively across both visual and textual modalities. Experimental results demonstrate that PriOrGen significantly outperforms existing methods on multi-organ pathology datasets, achieving state-of-the-art performance in report generation quality for both head and tail organ categories.

Abstract

Automated pathology report generation from Whole Slide Images (WSIs) has attracted increasing attention in digital pathology. However, existing methods are predominantly developed under single-organ settings, overlooking the multi-organ scenarios encountered in clinical practice, where organ types typically follow a long-tailed distribution. To address this gap, we identify two critical biases: (1) visual representation bias, where the encoder favors head-class patterns over tail-class discriminative features, and (2) textual decoding bias, where the decoder overfits to head-class narrative patterns, yielding diagnostically unreliable outputs for tail-class organs. To mitigate these two biases, we propose a novel Prior-anchored multi-Organ pathology report Generation framework (PriOrGen). Specifically, a Visual-Prototype Anchored Bottleneck module leverages the information bottleneck principle with learnable anchor representations to selectively retain diagnostically relevant visual information while filtering out head-biased redundancy. Secondly, a Meta-Report Anchored Bank module constructs an organ-specific meta-report anchored bank and retrieves organ-faithful textual priors to steer the decoder away from head-class narrative patterns. Extensive experiments on a multi- organ pathology dataset demonstrate that our method effectively mitigates long-tail biases and achieves superior report generation performance across both head and tail organ categories compared to state-of-the-art methods.

Problem

• long-tailed distribution
• multi-organ pathology
• visual representation bias
• textual decoding bias
• pathology report generation

Innovation

• long-tailed learning
• multi-organ pathology report generation
• visual-textual debiasing
• information bottleneck
• prior-anchored generation