CorePath: A Breast-Specialized Pathology Foundation Model for Core Needle Biopsy Diagnosis and Risk-Controlled Report Generation

📄 arXiv: 2608.03079v1 📥 PDF

作者: Ting Yin, Danning Li, Chen Shu, Xiaoxia Yao, Boyu Fu, Yujing Chang, Tianyu Shi, Mengna Feng, Jie Chen, Jing Fu, Xiuli Xiao, Tianlin Li, Mumin Shao, Jiaxin Bi, Wenchuan Zhang, Xiaoyan Wu, Xiao Han, Zhang Zhang, Yuhao Yi, Hong Bu

分类: cs.CV, cs.AI, cs.LG, stat.AP

发布日期: 2026-08-04

备注: The code will be made publicly available upon publication

💡 一句话要点

提出CorePath以解决乳腺核心针活检诊断挑战

🎯 匹配领域: 支柱九：具身大模型 (Embodied Foundation Models)

关键词: 乳腺癌诊断 核心针活检 多模态病理 模型微调 风险控制 报告生成 病理学

📋 核心要点

  1. 现有乳腺核心针活检方法面临组织取样有限和病变异质性等挑战，导致亚型区分困难。
  2. CorePath是一个针对乳腺的多模态病理基础模型，通过微调PRISM模型来提高乳腺癌的诊断准确性。
  3. 实验结果显示，CorePath在多个评估指标上超越了现有模型，显著降低了非乳腺幻觉率，提升了报告生成的可靠性。

📝 摘要（中文）

乳腺核心针活检（CNB）在乳腺癌诊断中至关重要，但由于组织取样有限、病变异质性和形态重叠等因素，导致亚型区分困难。本文开发了CorePath，一个专门针对乳腺的多模态病理基础模型，基于7901对CNB全切片图像和诊断报告进行微调。CorePath在六个CNB队列和两个公共乳腺病理基准上评估，未进行任务特定的再训练，始终优于PRISM，在癌症检测、侵袭性评估和组织学亚型分类方面表现出色。CorePath在报告生成中将整体非乳腺幻觉率从30.1%降低至2.8%，显示出经过乳腺特定适应后的领域保真度提升。CorePath-CRG结合了亚型置信度门控与风险控制，实现了选择性报告发布和亚型级别的回退。

🔬 方法详解

问题定义：本文旨在解决乳腺核心针活检中由于组织取样有限和病变异质性导致的亚型区分困难，现有方法在这些方面表现不佳。

核心思路：CorePath通过微调PRISM模型，专门针对乳腺病理数据进行训练，以提高模型在乳腺癌检测和分类中的准确性和可靠性。

技术框架：CorePath的整体架构包括数据预处理、模型微调、评估和报告生成等主要模块。模型在多个CNB队列和公共基准上进行评估，确保其广泛适用性。

关键创新：最重要的创新在于CorePath的乳腺特定适应性和风险控制机制，显著提高了模型在乳腺病理诊断中的表现，与现有方法相比，提供了更高的准确性和可靠性。

关键设计：在模型设计中，采用了多模态输入和特定的损失函数，以优化亚型分类的性能。同时，CorePath-CRG结合了置信度门控和风险控制策略，确保生成的报告在准确性和可靠性上达到最佳平衡。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

CorePath在多个评估指标上表现优异，五类CNB组织学亚型的加权AUC值达到0.9526-0.9735。在公共基准上，CorePath在侵袭性癌症亚型分类、BRACS病变分层和细粒度分类中均取得了最高的加权AUC值，分别为0.7780、0.8178和0.8252，显示出显著的性能提升。

🎯 应用场景

该研究的潜在应用领域包括乳腺癌的早期诊断和病理报告生成，能够为病理学家提供更为准确的辅助决策工具。未来，CorePath有望在临床实践中推广，提升乳腺癌诊断的效率和准确性，减少误诊率。

📄 摘要（原文）

Breast core needle biopsy (CNB) is central to breast cancer diagnosis yet remains challenging because limited tissue sampling, lesion heterogeneity, and subtle morphologic overlap can obscure subtype distinctions. We developed CorePath, a breast-specialized multimodal pathology foundation model fine-tuned from PRISM using 7901 paired CNB whole-slide images and diagnostic reports from two centers. Evaluated across six CNB cohorts and two public breast pathology benchmarks without task-specific retraining, CorePath consistently outperformed PRISM across cancer detection, invasion assessment, and histological subtyping. It achieved weighted area under the receiver operating characteristic curves (AUCs) of 0.9526-0.9735 for five-class CNB histological subtyping across private centers. On public benchmarks, CorePath outperformed leading pathology foundation models, achieving the highest weighted AUCs of 0.7780 for BCNB invasive carcinoma subtyping, 0.8178 for BRACS lesion stratification, and 0.8252 for BRACS fine-grained classification. In report generation, CorePath reduced the overall non-breast hallucinations from 30.1% to 2.8%, demonstrating improved domain fidelity after breast-specific adaptation. CorePath-CRG further combined conformal subtype-confidence gating with Learn-Then-Test risk control to enable selective report release, subtype-level fallback, and deferral. CorePath-CRG achieved zero non-breast hallucinations among released outputs and showed the strongest overall performance in pathologist-validated LLM-based Evaluation Scores and quantitative report-generation metrics across most centers. These results demonstrate that domain-specialized foundation models with statistical risk control offer a promising approach for accurate breast CNB diagnosis and reliable report generation.