AI summaryⓘ
The authors address a problem in automated breast ultrasound diagnosis where existing AI models often miss rare but important signs of cancer because they focus too much on common benign features. They propose a new method called Latent-CURE that guides the AI to reason step-by-step by first identifying specific clinical features before making a diagnosis. This approach helps the model avoid shortcuts and better recognize critical malignant signs, especially when cancer cases are very rare. Their method also uses a special training technique to keep the focus on these important cancer indicators. Overall, the authors show their method provides clearer clinical reasoning and more accurate results in difficult, imbalanced datasets.
Multimodal Large ModelsBreast UltrasoundBI-RADSChain-of-Thought ReasoningLatent SpaceShortcut LearningEpidemiological ImbalanceDual-Asymmetric OptimizationMalignant DescriptorsBenign Patterns
Authors
Weiyi Zhao, Xiaoyu Tan, Lu Gan, Liang Liu, Xihe Qiu
Abstract
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.