arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.29928cs.CVcs.AI
收藏

Latent-CURE:用于乳腺癌诊断的潜在空间推理框架

Latent-CURE for Breast Cancer Diagnosis

Weiyi Zhao, Xiaoyu Tan, Lu Gan, Liang Liu, Xihe Qiu

AI总结:

针对多模态大模型在乳腺癌超声诊断中因数据不平衡而忽略罕见恶性特征的问题,提出基于潜在空间非对称加权思维链的Latent-CURE框架,强制模型先推断BI-RADS形态描述符再诊断,并采用双非对称优化策略保护恶性特征,实现透明且鲁棒的诊断。

摘要:

多模态大模型显著推进了自动化乳腺超声诊断。然而,大多数现有框架采用不透明的端到端范式,优先考虑全局统计相关性而非结构化临床推理。因此,这些模型在极端现实流行病学不平衡中仍易受捷径学习影响,常常绕过罕见但决定性的恶性指标,转而偏向占主导的良性模式。为解决这一脱节,我们提出Latent-CURE,一种基于潜在空间推理的非对称加权思维链方法驱动的新型诊断框架。与传统方法不同,我们的框架构建隐式推理轨迹,迫使模型在最终诊断前依次推断标准化的BI-RADS形态描述符。此外,为应对关键恶性特征的极端稀缺性,我们将该架构与双非对称优化策略相结合。通过动态调整边界和权重,该策略保护高特异性恶性描述符不被常见良性先验所掩盖。全面评估表明,我们的知识注入方法在不平衡医学队列中提供透明的临床证据,同时实现稳健、准确的诊断性能。

英文摘要:

Multimodal Large Models have significantly advanced automated breast ultrasound diagnosis. However, most existing frameworks utilize opaque, end-to-end paradigms prioritizing global statistical correlations over structured clinical reasoning. Consequently, these models remain susceptible to shortcut learning amid extreme real-world epidemiological imbalances, often bypassing rare but decisive malignant indicators for dominant benign patterns. To address this disconnect, we propose Latent-CURE, a novel diagnostic framework driven by asymmetric weighted chain-of-thought methodology grounded in latent space reasoning. Unlike traditional approaches, our framework constructs an implicit reasoning trajectory forcing the model to sequentially infer standardized BI-RADS morphological descriptors before converging on a final diagnosis. Furthermore, to combat the extreme scarcity of critical malignant features, we couple this architecture with a dual-asymmetric optimization strategy. By dynamically adjusting margins and weights, this strategy safeguards high-specificity malignant descriptors from being overshadowed by common benign priors. Comprehensive evaluations demonstrate that our knowledge-injected approach provides transparent clinical evidence while achieving robust, accurate diagnostic performance in imbalanced medical cohorts.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑