{
  "abstract": "BackgroundDeep denoisers restore low-dose chest radiographs but emit a single point estimate with no indication of where the output is reliable, so a confident-looking reconstruction can be locally wrong. In paediatric radiography, where the radiation-dose imperative is sharpest, we ask whether a per-pixel uncertainty map can be attached at no meaningful cost to reconstruction quality.\n\nMethodsWe develop PP-VAE-Hformer, a hybrid convolution-transformer denoiser with a variational-autoencoder bottleneck (epistemic uncertainty map) and a heteroscedastic dual head (aleatoric map), and run a 19-arm ablation isolating five composite-loss terms on Poisson-Gaussian-degraded paediatric chest radiographs (Kermany collection; 624-image held-out test set), against eight discriminative baselines retrained on identical data and noise. Calibration is assessed by reliability diagrams and post-hoc{sigma} -scaling; comparisons use Bonferroni-corrected Welch tests with Cohens d as the primary discriminant.\n\nResultsA heteroscedastic negative-log-likelihood (NLL) objective buys a calibrated aleatoric map for 1.2 dB PSNR, which two-stage fine-tuning recovers to a statistically indistinguishable 0.010 dB. For the variational variant the Kullback-Leibler (KL) annealing schedule, not the bottleneck itself, is decisive: cyclic annealing closes a 1.10 dB gap over posterior-collapsing linear warmup. Predicted uncertainty tracks realised error (Pearson r > 0.8) with an optimal recalibration scale within 1% of unity. A matched-severity cross-degradation test shows this calibration is model-circular, however: at equal severity the aleatoric map becomes modestly (8-16%, a lower bound) over-confident once the noise model changes, and the Monte-Carlo epistemic map is a weaker error predictor that does not compensate. We additionally document a previously unreported destructive interaction between structural-similarity and Sobel-edge supervision at literature-default weights.\n\nConclusionsA calibrated per-pixel uncertainty map can be attached to a paediatric low-dose CXR denoiser at effectively no reconstruction cost. Its near-perfect calibration is tied to the trained (\"inverse-crime\") noise model, and the Monte-Carlo epistemic map does not reliably substitute where the aleatoric map fails, so an architecture-independent uncertainty estimate (e.g. deep ensembling), a blinded reader study, and real low-dose data are the immediate next steps.",
  "abstract_shown": true,
  "affiliations": [
    "University of Oxford"
  ],
  "article_type": "PUBLISHAHEADOFPRINT",
  "arxiv": null,
  "author_total": 2,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "S. T. Mengistu"
    },
    {
      "name": "K. Flouris"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/83ahp2z84fxz7.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.14.26363026",
  "fulltext_url": "https://www.medrxiv.org/content/10.64898/2026.09.14.26363026v1.full",
  "id": "83ahp2z84fxz7",
  "issns": [],
  "landing_url": "https://www.medrxiv.org/content/10.64898/2026.09.14.26363026v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "medrxiv",
      "radiology and imaging"
    ],
    [
      "openalex",
      "1707|Image and Signal Denoising Methods"
    ]
  ],
  "openalex": "W7213349920",
  "pdf_url": "https://www.medrxiv.org/content/10.64898/2026.09.14.26363026v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-14",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/83ahp2z84fxz7.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:18:39Z",
      "native_id": "10.64898/2026.09.14.26363026",
      "source": "medrxiv",
      "url": "https://www.medrxiv.org/content/10.64898/2026.09.14.26363026v1"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "medrxiv:radiology and imaging",
      "subfield": "imaging"
    }
  ],
  "title": "Calibrated per-pixel uncertainty for low-dose paediatric chest-radiograph denoising at no fidelity cost",
  "title_text": "Calibrated per-pixel uncertainty for low-dose paediatric chest-radiograph denoising at no fidelity cost",
  "type": "preprint",
  "updated_at": "2026-10-30T12:18:39Z",
  "url": "https://research.draconitic.com/paper/83ahp2z84fxz7",
  "venue": "medRxiv",
  "versions": []
}