{
  "abstract": "Background/Objectives: Pneumothorax, caused by air accumulation in the pleural space, can lead to lung collapse and, if diagnosis is delayed, respiratory or cardiovascular deterioration. Most deep-learning studies on pneumothorax address classification or segmentation alone. This study proposes a holistic automatic radiological reporting system combining U-Net-based segmentation, Segment Anything Model 2 (SAM2)-based boundary refinement, and a Vision-Language Model (VLM)-based reporting module for pneumothorax detection on computed tomography (CT) images. Methods: A MobileNetV2-encoder U-Net was trained on 224×224 CT patches from 171 patients (15,555 patches). A frozen, zero-shot SAM2 module, guided by a box prompt derived from the U-Net mask, was combined with U-Net via an Intersection over Union (IoU)-agreement rule. The refined mask and rule-based geometric features were passed to a frozen VLM (Qwen2-VL-2B-Instruct) to generate structured reports with a combined confidence coefficient. Performance was evaluated with Accuracy, Dice, IoU, and Loss, over all patches and over pneumothorax-positive patches only. Results: U-Net achieved 93.09/92.09/99.71% (Dice/IoU/Accuracy) on validation and 93.68/92.79/99.79% on the test set; these largely reflect correct empty-mask prediction on negative patches. On positive patches only, Dice was 0.6295 (validation) and 0.6215 (test), with patch-level sensitivity of 82.2% (validation) and 79.9% (test) and specificity above 97%. SAM2 refinement achieved 92.44% Dice and 91.29% IoU on a random test subsample (n ≈ 300), close to but not exceeding U-Net alone; an ablation analysis confirmed no consistent Dice/IoU or 95th-percentile Hausdorff distance (HD95) gain from SAM2. BLEU/ROUGE and Likert evaluation frameworks for the VLM reports were defined but not yet scored against reference reports. Conclusions: U-Net-based segmentation reliably identifies pneumothorax-containing patches with moderate boundary accuracy, while frozen SAM2 refinement adds limited value. The rule-based reporting layer is reproducible and shows triage-support potential, whereas the VLM free-text layer carries a documented hallucination risk and requires radiologist verification before clinical use.",
  "abstract_shown": true,
  "affiliations": [
    "Faculty of Technology, Department of Software Engineering Firat University, Elazig 23000, Türkiye;",
    "Faculty of Medicine Hospital, Department of Radiology, Firat University, Elazig 23000, Türkiye;"
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Savaş Tunçer"
    },
    {
      "affs": [
        1
      ],
      "name": "Mustafa Yıldırım"
    },
    {
      "affs": [
        0
      ],
      "name": "Özal Yıldırım"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/4ea26sbcpchd3.bib",
  "cited_by": 0,
  "doi": "10.3390/biomedicines14102312",
  "fulltext_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13701554/?tool=EBI",
  "id": "4ea26sbcpchd3",
  "issns": [
    "2227-9059"
  ],
  "landing_url": "https://europepmc.org/article/PMC/PMC13701554",
  "language": "eng",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "lcc",
      "QH301-705.5"
    ],
    [
      "openalex",
      "2741|COVID-19 diagnosis using AI"
    ]
  ],
  "openalex": "W7221507777",
  "pdf_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13701554/pdf/?tool=EBI",
  "pmcid": "PMC13701554",
  "pmid": null,
  "published": "2026-10-01",
  "publisher": "MDPI AG",
  "ris": "https://research.draconitic.com/paper/4ea26sbcpchd3.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:21:45Z",
      "native_id": "PMC:PMC13701554",
      "source": "europepmc",
      "url": "https://europepmc.org/article/PMC/PMC13701554"
    },
    {
      "first_seen": "2026-10-31T14:21:22Z",
      "native_id": "00d35d503b854851a728087622c2314f",
      "source": "doaj",
      "url": "https://doi.org/10.3390/biomedicines14102312"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2741|COVID-19 diagnosis using AI",
      "subfield": "imaging"
    }
  ],
  "title": "A SAM2 and VLM-Based Automatic Radiological Reporting System for Pneumothorax Detection",
  "title_text": "A SAM2 and VLM-Based Automatic Radiological Reporting System for Pneumothorax Detection",
  "type": "peer-reviewed",
  "updated_at": "2026-10-31T14:21:22Z",
  "url": "https://research.draconitic.com/paper/4ea26sbcpchd3",
  "venue": "Biomedicines",
  "versions": []
}