用于生成本土语言前列腺病理报告的端到端训练视觉-语言模型

中文摘要 AI 辅助

前列腺癌是全球最常被诊断的恶性肿瘤之一，对每个活检核心进行结构化报告会给病理学家带来负担。现有工具将此问题框架化为分类任务，让病理学家自行整理连贯的报告，而许多基于切片级的视觉-语言模型依赖以英语为中心的编码器，难以迁移到其他临床语言。我们提出一种切片级框架，用于生成前列腺活检报告，该框架在构建上具有语言独立性：分词器和模型均从头开始训练，此处以德语为例进行演示。为应对配对数据稀缺问题，一条自动化流水线使用本地部署的大语言模型将复合报告拆分为核心特定的图像-文本对，从2402个历史病例中生成了17344对，无需手动标注。在针对临床属性而非语言相似性进行评估时，该模型在恶性肿瘤检测上达到96.2%的F1值，在Gleason分级上达到65.2%，与FDA批准的分类器具有竞争力。分级在三个外部队列上通过潜在空间增强得到进一步验证，因此各机构可基于自身档案训练本土语言的报告生成模型。

英文摘要

Prostate cancer is among the most frequently diagnosed malignancies worldwide, and structured reporting of each biopsy core burdens pathologists. Existing tools frame this as classification, leaving pathologists to assemble coherent reports, while many slide-level vision-language models rely on English-centric encoders that transfer poorly to other clinical languages. We present a slide-level framework generating prostate biopsy reports that is language-independent by construction: tokenizer and model are trained from scratch, demonstrated here in German. To address paired-data scarcity, an automated pipeline uses a locally deployed large language model to split composite reports into core-specific image-text pairs, yielding 17,344 pairs from 2,402 historical cases without manual annotation. Evaluated for clinical attributes rather than linguistic similarity, the model achieves 96.2% F1 for malignancy detection and 65.2% for Gleason grading, competitive with an FDA-cleared classifier. Grading is further validated on three external cohorts with latent-space augmentation. Institutions can thus train native-language reporting models on their own archives.

发表机构

• Technical University of Munich（慕尼黑工业大学）
• Munich Data Science Institute（慕尼黑数据科学研究所）
• Munich Center for Machine Learning（慕尼黑机器学习中心）
• University Hospital Heidelberg（海德堡大学医院）
• Heidelberg University（海德堡大学）
• Interdisciplinary Center for Scientific Computing (IWR)（跨学科科学计算中心（IWR））

机构由 AI 辅助整理，请以论文原文为准。