{
  "abstract": "Automated neonatal brain pathology detection from magnetic resonance imaging (MRI) faces a dual challenge: preterm birth produces a characteristic but confounding pattern of delayed myelination that can obscure concurrent structural abnormalities, while conditions such as hypoxic-ischaemic encephalopathy (HIE) and hydrocephalus demand timely identification in their own right. Existing frameworks typically address these clinical questions in isolation or collapse them into a single flat classifier, discarding the natural clinical decision hierarchy. This study presents a hierarchical two-stage deep learning pipeline that emulates clinical reasoning from paired T1-weighted and T2-weighted neonatal brain MRI. An initial Stage-1 deploys a brain-age gap classifier, built on a 3-D ResNet-18 regressor followed by a gap-thresholded binary decision intended to screen for myelination delay. Then the same subjects advance to a Stage-2, where a second 3-D ResNet-18, trained for structural pathology, performs three-class classification: normal, HIE, and hydrocephalus. Experiments demonstrate that a regression from MRI scan to age with an R2 of 0.941 at Stage-1, the proposed hierarchical pipeline achieves a Stage-2 area under the curve (AUC) of 0.919 ± 0.024.",
  "abstract_shown": true,
  "affiliations": [
    "African Institute for Mathematical Sciences, Accra, Ghana",
    "Department of Computer Science, AGH University of Kraków, Kraków, Poland"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Christian Ahwoi Ampiah"
    },
    {
      "affs": [
        0
      ],
      "name": "Tina Malalanirainy"
    },
    {
      "affs": [
        1
      ],
      "name": "Alessandro Crimi"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0bhg1jftr248q.bib",
  "cited_by": 0,
  "doi": "10.3389/fnimg.2026.1981436",
  "fulltext_url": "https://www.frontiersin.org/articles/10.3389/fnimg.2026.1981436/full",
  "id": "0bhg1jftr248q",
  "issns": [
    "2813-1193"
  ],
  "landing_url": "https://doi.org/10.3389/fnimg.2026.1981436",
  "language": "en",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "lcc",
      "RC346-429"
    ],
    [
      "openalex",
      "2735|Fetal and Pediatric Neurological Disorders"
    ]
  ],
  "openalex": "W7224954953",
  "pdf_url": "https://www.frontiersin.org/journals/neuroimaging/articles/10.3389/fnimg.2026.1981436/pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-30",
  "publisher": "Frontiers Media S.A.",
  "ris": "https://research.draconitic.com/paper/0bhg1jftr248q.ris",
  "sources": [
    {
      "first_seen": "2026-10-31T14:22:45Z",
      "native_id": "0cf2609e37b04ca0a0d83542b1675b4b",
      "source": "doaj",
      "url": "https://doi.org/10.3389/fnimg.2026.1981436"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2735|Fetal and Pediatric Neurological Disorders",
      "subfield": "reproductive-child"
    }
  ],
  "title": "Hierarchical detection of neonatal brain pathologies using a two-stage deep learning framework from magnetic resonance imaging",
  "title_text": "Hierarchical detection of neonatal brain pathologies using a two-stage deep learning framework from magnetic resonance imaging",
  "type": "peer-reviewed",
  "updated_at": "2026-11-01T14:20:44Z",
  "url": "https://research.draconitic.com/paper/0bhg1jftr248q",
  "venue": "Frontiers in Neuroimaging",
  "versions": []
}