发表机构
Politehnica University Timişoara; University Hospital Müenster（蒂米什瓦拉理工大学; 明斯特大学医院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
QuantumBoostNet作为经典-量子混合架构，通过双头部设计及分阶段训练，在心脏超声视图识别任务中优于现有模型，且在图像分类基准中表现更优、抗噪性更强，为专业医学成像的混合模型发展提供支撑。
AI 中文摘要
准确识别心脏超声（超声心动图）中的正确视图或角度是心脏病学成像的关键组成部分，该步骤对于精准的解剖学解读、可靠的测量以及减少临床错误至关重要。尽管计算机视觉已取得显著进展，但大多数最先进的模型在标准基准测试中表现良好，却因数据中存在的高水平噪声，在专业医学成像任务中往往产生次优结果。本文提出了量子BoostNet（QuantumBoostNet）这一经典-量子混合架构，以应对这些挑战。该模型将经典骨干网络与两个头部模块相集成：一个为经典头部，另一个为量子头部，其中量子头部实现为参数化的10量子比特量子电路。训练分为两个阶段，头部之间的自适应转换由监控损失动态的混合参数控制。大量实验表明，尽管可模拟的量子比特数量有限，QuantumBoostNet在心脏超声视图识别任务中始终优于最先进的经典模型和经典-量子混合模型，相比最优竞争者实现了相对提升。QuantumBoostNet在已建立的图像分类基准测试中也展现出更优性能，且对噪声具有鲁棒性。这些发现支持针对专业医学成像应用的经典-量子混合模型的持续开发。
英文摘要
Accurate identification of the correct view or angle in cardiac ultrasound (echocardiogram) is critical for cardiologic imaging, precise anatomical interpretation, and reducing clinical errors. Most state-of-the-art classical models perform well on standard benchmarks but give suboptimal results in specialized medical imaging due to high noise levels. To address these challenges, this work proposes the hybrid classical-quantum architecture QuantumBoostNet, which combines a classical backbone with two heads: one classical and one quantum, a parametrized 10-qubit quantum circuit. The main contribution of this work is training in two stages, with an adaptive transition between heads controlled by a mixing parameter that monitors loss dynamics. Extensive experiments show that QuantumBoostNet outperforms the implemented baselines under matched training conditions. Statistically significant gains appear on FashionMNIST ($p_t=9.91\!\times\!10^{-6}$) and MNIST ($p_t=1.29\!\times\!10^{-5}$), with a less significant improvement on the echocardiography task ($p_t=0.0711$). The model also shows robustness to noise. These findings support continued development of hybrid classical-quantum models for specialized medical imaging applications.
CommentsAdditional classical baseline model; classical ablation; QPU inference
