基于DINOv2的左室射血分数估计、整体纵向应变功能障碍分类及早期心脏毒性预测统一框架
A Unified DINOv2-Based Framework for LVEF Estimation, GLS Dysfunction Classification, and Early Cardiotoxicity Prediction
- GE HealthCare（GE医疗）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究提出基于DINOv2的统一框架，结合LoRA与时序聚合等技术，实现LVEF估计、GLS功能障碍分类及早期心脏毒性预测，在多任务中取得良好性能，还引入专用模型优化LVEF估计。
AI中文摘要：
左室射血分数（LVEF）估计（任务1）、基于整体纵向应变（GLS）的功能障碍分类（任务2）及早期心脏毒性预测（任务3）为肿瘤心脏病学评估提供互补信息。LVEF作为临床标准反映宏观心室容积变化，而GLS捕捉细微心肌变形，可在LVEF明显下降前提示亚临床心脏毒性；此外，从治疗前基线超声心动图预测心脏毒性可实现早期预防性干预。为解决这三项任务，我们采用基于DINOv2的框架，配备任务特定适配模块与预测头。该框架基于冻结的基础编码器，融入参数高效的低秩适配（LoRA）与时间聚合以学习任务专用表征，确保稳健泛化。关键在于，推理阶段无需心脏周期检测与时相划分，既不需要心脏周期分割，也不需要明确的舒张末期/收缩末期（ED/ES）标注。此外，我们引入ED/ES引导的2D/3D混合多视图回归模型专门优化任务1。在包含237例患者的1203个训练视频、59例独立患者的300个验证视频的患者级拆分数据上，该基于DINOv2的框架在任务1的平均绝对误差（MAE）为5.03%，任务2的AUC-ROC为76.48%，任务3的AUC-ROC为70.26%；针对任务1的专用ED/ES引导模型进一步提升性能，MAE达4.64%。该框架证明了基础模型表征在多种肿瘤心脏病学任务中的有效性，以及生理引导建模对精准LVEF估计的额外益处。
英文摘要：
Left ventricular ejection fraction (LVEF) estimation (Task 1), global longitu-dinal strain (GLS)-based dysfunction classification (Task 2), and early cardi-otoxicity prediction (Task 3) provide complementary information for cardio-oncology assessment. LVEF reflects macroscopic ventricular volume chang-es as the clinical standard, whereas GLS captures subtle myocardial defor-mation, indicating subclinical cardiotoxicity before overt LVEF decline. Fur-thermore, predicting cardiotoxicity from baseline echocardiography prior to treatment enables preventive interventions at an early stage. To address these three tasks, we employ a DINOv2-based framework with task-specific adap-tation and prediction heads. Built upon a frozen foundation encoder, the framework incorporates parameter-efficient Low-Rank Adaptation (LoRA) and temporal aggregation to learn task-specialized representations, ensuring robust generalization. Crucially, during inference, it operates in a fully cycle-detection-free and phase-free manner, requiring neither cardiac cycle seg-mentation nor explicit End-Diastolic/End-Systolic (ED/ES) annotations. Ad-ditionally, we introduce an ED/ES-guided 2D/3D hybrid multi-view regres-sion model specifically to optimize Task 1. On a patient-level split containing 1,203 training videos from 237 patients and 300 validation videos from 59 independent patients, the DINOv2-based framework achieved a mean abso-lute error (MAE) of 5.03% for Task 1, an AUC-ROC of 76.48% for Task 2, and an AUC-ROC of 70.26% for Task 3. For Task 1, the specialized ED/ES-guided model further improves performance, achieving an MAE of 4.64%. This framework demonstrates the effectiveness of foundation model repre-sentations across diverse cardio-oncology tasks and the additional benefit of physiology-guided modeling for accurate LVEF estimation.
