用金字塔特征提取和检索验证，自动生成高精度病理报告
Automated Histopathology Report Generation via Pyramidal Feature Extraction and the UNI Foundation Model
- 分层处理超大病理图像，通过多尺度选块降低计算负担
- 结合基础模型与Transformer解码器，生成符合医学术语的报告
- 新增检索验证环节，提升报告可靠性，适合临床辅助诊断场景
从全幻灯片图像（WSIs）生成诊断文本极具挑战，因其输入规模可达十亿像素，且需精确的领域专用语言。我们提出一种分层视觉语言框架，将冻结的病理基础模型与Transformer解码器结合用于报告生成。为使WSI处理可行，采用多分辨率金字塔补丁选择（下采样因子2^3至2^6），并利用拉普拉斯方差与HSV标准去除背景和伪影。补丁特征由UNI视觉变换器提取，并投影至6层Transformer解码器，通过交叉注意力生成诊断文本。为更好表达生物医学术语，输出使用BioGPT进行分词。最后加入基于检索的验证步骤：使用Sentence BERT嵌入对比生成报告与参考语料库；若匹配度高，则用检索到的真实报告替换生成结果，以提升可靠性。
原文摘要 · Abstract (English)
Generating diagnostic text from histopathology whole slide images (WSIs) is challenging due to the gigapixel scale of the input and the requirement for precise, domain specific language. We propose a hierarchical vision language framework that combines a frozen pathology foundation model with a Transformer decoder for report generation. To make WSI processing tractable, we perform multi resolution pyramidal patch selection (downsampling factors 2^3 to 2^6) and remove background and artifacts using Laplacian variance and HSV based criteria. Patch features are extracted with the UNI Vision Transformer and projected to a 6 layer Transformer decoder that generates diagnostic text via cross attention. To better represent biomedical terminology, we tokenize the output using BioGPT. Finally, we add a retrieval based verification step that compares generated reports with a reference corpus using Sentence BERT embeddings; if a high similarity match is found, the generated report is replaced with the retrieved ground truth reference to improve reliability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。