Prior-Anchored Debiasing for Long-Tailed Multi-Organ Pathology Report Generation
2026-07-01 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors worked on improving automated pathology report writing from medical images across many different organs, which is hard because some organs appear much more than others. They found that current methods tend to focus too much on common organs, both visually and in the wording of reports, which hurts accuracy for rare organs. To fix this, they designed a new system that filters visual information to keep important details for less common organs and guides the text generation using organ-specific report examples. Their tests showed this approach helps produce better reports for both common and rare organs.
Whole Slide Imagespathology report generationlong-tailed distributionvisual representation biastextual decoding biasinformation bottleneckencoder-decoder modelmulti-organ pathologyautomated medical reportingmeta-report
Authors
Feng Yang, Jie Liu, Yubo Pang, Peilin Chen, Xinheng Lyu, Shiqi Wang, Howard Leung, Ping Chen
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.