{
  "abstract": "Objective\n\nAccurate identification of acute ischemic infarcts on diffusion-weighted magnetic resonance imaging (DWI) is a critical prerequisite for reliable lesion quantification and effective clinical decision support in the management of cerebrovascular events.Methods\n\nThis study presents EPRA U-Net (Efficient Pyramid Residual Attention U-Net), a task-specific integrated architecture for efficient and accurate infarct segmentation of DWI images. In the proposed architecture, an EfficientNet-based encoder was used as a hierarchical feature extractor with a minimized parameterization. In addition, a Residual-Recurrent (R2) block (recurrent unrolling step t = 2, following the original formulation) and Atrous Spatial Pyramid Pooling (ASPP) were integrated to enhance the performance of spatial dependency modeling. Additionally, a dual attention mechanism was incorporated to highlight lesion-related activations while concurrently enabling the suppression of extraneous background responses. To prioritize lesion detection consistent with clinical imperative, a Tversky loss function (α = 0.4, β = 0.6) was adopted, thereby emphasizing the sensitivity of detection over its specificity during the optimization process.Results\n\nExperimental evaluations were conducted utilizing an in-house dataset comprising 167 patients with 4,895 DWI slices; subsequently, the performance of the proposed EPRA U-Net was assessed in comparison with state-of-the-art models, specifically UNet++, DeepLabV3+, and TransUNet. The experimental results suggest that EPRA U-Net attained superior performance, evidenced by a pixel-aggregated Dice of 0.8984, a per-sample Dice of 0.9469, an IoU of 0.8155, a Recall of 0.8887, a Lesion F1 of 0.9378, and an HD95 of 11.62 px (median: 2.00 px). Furthermore, a clear reduction in the rate of missed lesions, specifically by 16%, 25%, and 29%, was observed when compared with UNet++, DeepLabV3+, and TransUNet, respectively. Additionally, a comprehensive ablation study was systematically conducted.Conclusion\n\nThese findings suggest that the proposed architecture affords a more robust and accurate infarct segmentation, consequently facilitating a more reliable estimation of treatment eligibility.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Computer Engineering, Yozgat Bozok University, Yozgat, Turkey. hasan.ulutas@yobu.edu.tr.",
    "Department of Computer Engineering, Izmir Bakircay University, Izmir, Turkey.",
    "Queen Mary's Digital Environment Research Institute (DERI), London, UK.",
    "Department of Radiology, Faculty of Medicine, Yozgat Bozok University, Yozgat, Turkey.",
    "Department of Computer Engineering, Yozgat Bozok University, Yozgat, Turkey.",
    "Department of Digital Forensics Engineering, Technology Faculty, Firat University, Elazig, Turkey.",
    "Department of Electrical Engineering, Qatar University, Doha, Qatar."
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 7,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Hasan Ulutas",
      "orcid": "0000-0003-3922-934X"
    },
    {
      "affs": [
        1,
        2
      ],
      "name": "Muhammet Emin Sahin"
    },
    {
      "affs": [
        3
      ],
      "name": "Mustafa Fatih Erkoc"
    },
    {
      "affs": [
        4
      ],
      "name": "Esra Yuce"
    },
    {
      "affs": [
        5
      ],
      "name": "Turker Tuncer"
    },
    {
      "affs": [
        5
      ],
      "name": "Sengul Dogan"
    },
    {
      "affs": [
        6
      ],
      "name": "Serkan Kiranyaz"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/5e0zr5m9b9jd8.bib",
  "cited_by": 0,
  "doi": "10.1186/s12880-026-02569-9",
  "fulltext_url": "https://europepmc.org/articles/PMC13688968",
  "id": "5e0zr5m9b9jd8",
  "issns": [
    "1471-2342"
  ],
  "landing_url": "https://europepmc.org/article/MED/42919228",
  "language": "eng",
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "lcc",
      "R855-855.5"
    ],
    [
      "openalex",
      "1707|Medical Image Segmentation Techniques"
    ]
  ],
  "openalex": "W7170743674",
  "pdf_url": "https://europepmc.org/articles/PMC13688968?pdf=render",
  "pmcid": "PMC13688968",
  "pmid": "42919228",
  "published": "2026-07-01",
  "publisher": "BMC",
  "ris": "https://research.draconitic.com/paper/5e0zr5m9b9jd8.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:21:02Z",
      "native_id": "MED:42919228",
      "source": "europepmc",
      "url": "https://europepmc.org/article/MED/42919228"
    },
    {
      "first_seen": "2026-10-30T13:46:33Z",
      "native_id": "6cf26ddf3dc24a9c80244f01b56a431f",
      "source": "doaj",
      "url": "https://doi.org/10.1186/s12880-026-02569-9"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "journal-openalex:2741|Radiomics and Machine Learning in Medical Imaging",
      "subfield": "imaging"
    }
  ],
  "title": "EPRA U-Net: an efficient pyramid residual attention framework for accurate infarct segmentation in diffusion-weighted MRI.",
  "title_text": "EPRA U-Net: an efficient pyramid residual attention framework for accurate infarct segmentation in diffusion-weighted MRI.",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T13:46:33Z",
  "url": "https://research.draconitic.com/paper/5e0zr5m9b9jd8",
  "venue": "BMC medical imaging",
  "versions": []
}