Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Duncan Stothers, Ben Stothers, Emily Schaeffer, Kishore Mulpuri

TL;DR

An ultrasound-first, radiation-preserving policy for developmental dysplasia of the hip (DDH) that requests a radiograph only when needed is studied, with a simple, reproducible pipeline that turns limited labels into interpretable measurements and tunable selective imaging curves suitable for clinical handoff and future external validation.

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 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), uncertainty inflation factors, 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.

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

TL;DR

An ultrasound-first, radiation-preserving policy for developmental dysplasia of the hip (DDH) that requests a radiograph only when needed is studied, with a simple, reproducible pipeline that turns limited labels into interpretable measurements and tunable selective imaging curves suitable for clinical handoff and future external validation.

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 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), uncertainty inflation factors, 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.

Paper Structure

This paper contains 44 sections, 14 equations, 4 figures, 1 table.

Table of Contents

  1. Background
  2. Clinical context and age-aware measurements.
  3. Ultrasound-only automation (what exists).
  4. Radiograph-only automation (what exists).
  5. Cross-modal US-XR learning (what remains sparse).
  6. Why the intersection matters: clinical and statistical rationale.
  7. From ultrasound to radiographic surrogates (US$\rightarrow$XR prediction).
  8. Decision-theoretic selective imaging and risk control.
  9. Positioning of this work.
  10. Methods
  11. Data, pairing, and splits
  12. Self-supervised pretraining (SimSiam) and frozen encoders
  13. Measurement heads on frozen encoders
  14. Ultrasound head.
  15. Radiograph heads.
  16. ...and 29 more sections

Figures (4)

  • Figure 1: US-only rate across $(\delta_\alpha,\delta_{\mathrm{cov}})$ for the three policy families.
  • Figure 2: Miss rate among US-only decisions across the same grid.
  • Figure 3: Empirical one-sided coverage for femoral head coverage as $\delta_{\mathrm{cov}}$ varies.
  • Figure 4: Decision-curve envelopes over radiation cost $\lambda$ for two miss penalties $\mu$.