量子支持向量机在医学影像分类中显著优于经典方法，尤其在少数类预测上。
Quantum Kernel Advantage over Classical Collapse in Medical Foundation Model Embeddings
- 用冻结的医疗模型嵌入特征，通过量子核方法实现分类。
- 11量子比特时，量子模型少数类F1达0.343，经典模型仅0.050。
- 无需调参即展现优势，适合医疗数据稀缺场景使用。
我们在无噪声模拟下，针对MIMIC-CXR胸部X光片的二分类保险任务，验证了量子支持向量机（QSVM）在三种医疗基础模型（MedSigLIP-448、RAD-DINO、ViT-patch32）嵌入上的量子核优势。提出两级公平对比框架，双方均使用相同的PCA-q特征。第一级（未调参的QSVM vs. 未调参线性SVM，C=1），QSVM在全部18种配置中胜出少数类F1（17个p<0.001，1个p<0.01）；经典线性核在所有量子比特数下均退化为多数类预测（90%-100%种子），而QSVM保持非平凡召回率。当量子比特数q=11（MedSigLIP-448平台期中心），平均F1达0.343，经典为0.050（提升+0.293，p<0.001），且无需超参数调优。第二级（未调参QSVM vs. C调优的RBF SVM），QSVM在7种配置中全胜（平均增益+0.068，最大+0.112）。特征谱分析显示，量子核有效秩在q=11时达69.80，远超线性核，而经典崩溃特性与惩罚系数无关。全量子比特扫描揭示不同模型存在架构依赖的集中现象。代码见：https://github.com/sebasmos/qml-medimage
原文摘要 · Abstract (English)
We provide evidence of quantum kernel advantage under noiseless simulation in binary insurance classification on MIMIC-CXR chest radiographs using quantum support vector machines (QSVM) with frozen embeddings from three medical foundation models (MedSigLIP-448, RAD-DINO, ViT-patch32). We propose a two-tier fair comparison framework in which both classifiers receive identical PCA-q features. At Tier 1 (untuned QSVM vs. untuned linear SVM, C = 1 both sides), QSVM wins minority-class F1 in all 18 tested configurations (17 at p < 0.001, 1 at p < 0.01). The classical linear kernel collapses to majority-class prediction on 90-100% of seeds at every qubit count, while QSVM maintains non-trivial recall. At q = 11 (MedSigLIP-448 plateau center), QSVM achieves mean F1 = 0.343 vs. classical F1 = 0.050 (F1 gain = +0.293, p < 0.001) without hyperparameter tuning. Under Tier 2 (untuned QSVM vs. C-tuned RBF SVM), QSVM wins all seven tested configurations (mean gain +0.068, max +0.112). Eigenspectrum analysis reveals quantum kernel effective rank reaches 69.80 at q = 11, far exceeding linear kernel rank, while classical collapse remains C-invariant. A full qubit sweep reveals architecture-dependent concentration onset across models. Code: https://github.com/sebasmos/qml-medimage
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。