EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Slice-based YOLO-SAM hybrid prompting framework for automatic medical image segmentation

Xiaobo Liu iD, Qiuyan Pei, Xiaoyu Wang, Honghang Luo

PLOS One · 13.11.2026 · 21 (11) · e0360939

DOI: 10.1371/journal.pone.0360939 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 13.11.2026. Verfasst von Xiaobo Liu und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Nuclear Medicine, the First Affiliated Hospital, Fujian Medical University, Fuzhou, Fujian, China. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Prostatic Neoplasms, Image Processing, Computer-Assisted. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate medical image segmentation is essential for computer-aided diagnosis, treatment planning, and quantitative image analysis. This study evaluates a slice-based automatic segmentation framework that couples YOLOv8-based region localization with prompt-driven Segment Anything Model (SAM) segmentation. In contrast to a simple YOLOv8 + SAM cascade using only bounding-box prompts, the proposed framework adds hybrid prompt generation with bounding boxes and positive/negative points, parameter-efficient fine-tuning of the SAM prompt encoder and mask decoder, and lightweight post-processing. The framework is evaluated on two public datasets under explicitly defined local protocols: 2D slice-based prostate MRI segmentation using Prostate158 and skin lesion segmentation using an internal ISIC 2018 split. On Prostate158, the method obtains Dice coefficients of 89.2%, 76.8%, and 65.3% for central gland, peripheral zone, and prostate cancer lesion segmentation, respectively. On the local ISIC 2018 split, it obtains a Dice coefficient of 94.8% and a Jaccard index of 91.5%. These results indicate competitive performance under the implemented experimental protocol, but they should not be interpreted as protocol-independent state-of-the-art claims. The manuscript clarifies the evaluation unit, prompt-source protocol, 2D processing strategy, hyperparameter settings, baseline grouping, and limitations related to statistical uncertainty, detector failure propagation, and clinical translation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingProstatic NeoplasmsImage Processing, Computer-AssistedHumansMaleAlgorithmsProstate

Autor:innen und Institutionen

  • Department of Nuclear Medicine, the First Affiliated Hospital, Fujian Medical University, Fuzhou, Fujian, China.
  • Department of Nuclear Medicine, National Regional Medical Center, Binhai Campus of the First Affiliated Hospital, Fujian Medical University, Fuzhou, Fujian, China.
  • College of Safety and Emergency Management Engineering, Taiyuan University of Technology, Taiyuan, Shanxi, China.
  • Nuclear Emergency and Nuclear Safety Department, China Institute for Radiation Protection, Taiyuan, Shanxi, China.
  • School of Nuclear Technology and Chemistry & Biology, Hubei University of Science and Technology, Xianning, Hubei, China.
  • Department of Economics and Management, Fujian Forestry Vocational and Technical College, Nanping, Fujian, China.

ORCID-Profile: Xiaobo Liu

Zitieren

APA

Liu, X., Pei, Q., Wang, X., & Luo, H. (2026). Slice-based YOLO-SAM hybrid prompting framework for automatic medical image segmentation. PLOS One, 21(11), e0360939. https://doi.org/10.1371/journal.pone.0360939

Vancouver

Liu X, Pei Q, Wang X, Luo H. Slice-based YOLO-SAM hybrid prompting framework for automatic medical image segmentation. PLOS One. 2026;21(11):e0360939. doi:10.1371/journal.pone.0360939

BibTeX
@article{Liu2026,
  author = {Liu, Xiaobo and Pei, Qiuyan and Wang, Xiaoyu and Luo, Honghang},
  title = {Slice-based YOLO-SAM hybrid prompting framework for automatic medical image segmentation},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {11},
  pages = {e0360939},
  doi = {10.1371/journal.pone.0360939}
}
Kostenlos starten →