Radiation-Preserving Selective Imaging for Pediatric Hip Dysplasia: A Cross-Modal Ultrasound-Xray Policy with Limited Labels

TL;DR

This paper proposes a radiation-preserving, ultrasound-first policy for pediatric hip dysplasia that uses a calibrated, selective imaging approach with limited labels, balancing diagnostic accuracy and reduced radiograph use.

Contribution

It introduces a novel pipeline combining self-supervised learning, measurement-specific heads, and conformal calibration for selective imaging in DDH diagnosis.

Findings

Ultrasound measurement errors are modest and comparable to radiographs.

The calibrated policy achieves high coverage with minimal ultrasound use.

Flexible rule settings allow trade-offs between coverage and imaging throughput.

Abstract

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.