用超声主导减少儿童髋关节发育不良的辐射暴露，仅在必要时才拍片。
Radiation-Preserving Selective Imaging for Pediatric Hip Dysplasia: A Cross-Modal Ultrasound-Xray Policy with Limited Labels
- 先用大量无标签数据预训练超声和X光模型，再针对关键测量点微调小模型。
- 超声预测角度误差约9.7度，X光预测误差7.6至8.9度，整体覆盖率可调。
- 支持临床灵活决策，适合需要降低辐射暴露的儿科影像场景。
我们研究了一种以超声为主的辐射节约策略，用于发育性髋关节发育不良（DDH）筛查，仅在必要时才请求X光检查。首先，在大规模未标注数据集（37,186例超声、19,546张X光片）上使用SimSiam对模态专用编码器（ResNet-18）进行预训练；其次，冻结主干网络，为髋关节相关解剖标志和测量值适配小型、高保真的预测头；第三，基于保留校准集构建单侧置信区间拒决规则，实现交换性下的有限样本边际覆盖率保证。超声头预测Graf α、β角及股骨头覆盖度；X光头预测髋臼指数（AI）、中心边缘角（CE）及IHDI分级。在独立标注测试集上，超声测量误差较小（如α角平均绝对误差≈9.7°，覆盖率误差≈14.0%），而放射学指标达到AI与CE的平均绝对误差分别为≈7.6°和≈8.9°。通过决策曲线分析探索不同拒绝规则组合（α角仅限；α或覆盖度；α且覆盖度）、置信水平与实用权衡，保守设置下覆盖率高但超声独用率接近零；宽松设置（如α或覆盖度，较大δ值）可实现非零超声独用率，代价是预期覆盖率下降。最终形成一个简单、可复现的流程，将有限标签转化为可解释测量结果和可调的按需成像曲线，适用于临床交接与未来外部验证。
原文摘要 · Abstract (English)
We study an ultrasound-first, radiation-preserving policy for developmental dysplasia of the hip (DDH) that requests a radiograph only when needed. We (i) pretrain modality-specific encoders (ResNet-18) with SimSiam on a large unlabelled registry (37186 ultrasound; 19546 radiographs), (ii) freeze the backbones and fit small, measurement-faithful heads on DDH-relevant landmarks and measurements, (iii) calibrate a one-sided conformal deferral rule on ultrasound predictions that provides finite sample marginal coverage guarantees under exchangeability, using a held-out calibration set. Ultrasound heads predict Graf alpha, beta, and femoral head coverage; X-ray heads predict acetabular index (AI), center-edge (CE) angle and IHDI grade. On our held out labeled evaluation set, ultrasound measurement error is modest (e.g., alpha MAE ~= 9.7 degrees, coverage MAE ~= 14.0%), while radiographic probes achieve AI and CE MAEs of ~= 7.6 degrees and ~= 8.9 degrees, respectively. The calibrated US-only policy is explored across rule families (alpha-only; alpha OR coverage; alpha AND coverage), conformal miscoverage levels, and per-utility trade-offs using decision-curve analysis. Conservative settings yield high coverage with near-zero US-only rates; permissive settings (e.g., alpha OR coverage at larger deltas) achieve non-zero US-only throughput with expected coverage tradeoffs. The result is a simple, reproducible pipeline that turns limited labels into interpretable measurements and tunable selective imaging curves suitable for clinical handoff and future external validation.
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。