EUVIMEDEUVIMED entdecken
Crossref

Research on automatic detection and segmentation of prostate zones based on YOLO-D

Xiaodong Wang iD, Rui Feng iD, Chen Xu, Chuanbing Wang iD, Wei Wang iD, Chang Gao iD, Ye Tan

Technology and Health Care · 2025

DOI: 10.1177/09287329251392399 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Technology and Health Care, 2025. Verfasst von Xiaodong Wang und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Information Engineering, Kangda College of Nanjing Medical University, Lianyungang, China. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Prostate, Prostatic Neoplasms, Image Processing, Computer-Assisted. Die Arbeit nennt 29 Literaturangaben. Gefördert von: the National College Students Innovation and Entrepreneurship Training Program, the Clinical Major Project of Changzhou Medical Center of Nanjing Medical University, the Science and Technology Development Fund of Nanjing Medical University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Accurate identification and localization of prostate zones in magnetic resonance (MR) images are essential for clinical diagnosis and treatment planning. However, convolutional object detection models like YOLO often struggle to capture the complex geometric features of the prostate.

Objective

To enhance the detection and segmentation performance of prostate MR images by addressing limitations in spatial feature extraction and static focusing mechanisms present in conventional YOLO models.

Methods

We propose YOLO-D, an enhanced YOLOv8-based model integrating a Deformable Convolution (DConv) module to better capture fine-grained image details and improve geometric adaptability. Additionally, the Wise-IoU loss function is employed to introduce a dynamic and non-monotonic focusing mechanism, effectively reducing inter-class interference and enhancing localization accuracy.

Results

YOLO-D was evaluated on the publicly available ProstateX dataset using precision, recall, average precision (AP), and F1 score as evaluation metrics. For detection, it achieved 93.4% precision, 91.2% recall, 94.7% AP, and an F1 score of 0.922. For segmentation, YOLO-D achieved 90.7% precision, 88.6% recall, 91.1% AP, and an F1 score of 0.897—consistently outperforming the baseline YOLOv8.

Conclusions

By incorporating DConv and Wise-IoU, YOLO-D offers a robust and efficient solution for automatic prostate zone analysis, with promising potential in real-time clinical imaging applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingProstateProstatic NeoplasmsImage Processing, Computer-AssistedImage Interpretation, Computer-AssistedHumansMaleAlgorithms

Stichwörter der Autor:innen

YOLOv8instance segmentationobject detectionprostate zoneswise-IoU

Autor:innen und Institutionen

  • Department of Medical Information Engineering, Kangda College of Nanjing Medical University, Lianyungang, China.
  • The Engineering Research Center of Intelligent Theranostics Technology and Instruments, Ministry of Education, School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing, China.
  • Department of Clinical Medicine, Kangda College of Nanjing Medical University, Lianyungang, China.
  • Department of Radiology, The First Affiliated Hospital With Nanjing Medical University, Nanjing, China.

ORCID-Profile: Xiaodong Wang, Rui Feng, Chuanbing Wang, Wei Wang, Chang Gao

Förderung

  • the National College Students Innovation and Entrepreneurship Training Program
  • the Clinical Major Project of Changzhou Medical Center of Nanjing Medical University
  • the Science and Technology Development Fund of Nanjing Medical University
  • the Post-Doctor Research Funding of Changzhou Medical Center
  • the Talent Project of Kangda College of Nanjing Medical University
  • the Key R&D of Lianyungang City (Social Development) Project

Zitieren

APA

Wang, X., Feng, R., Xu, C., Wang, C., Wang, W., Gao, C., & Tan, Y. (2025). Research on automatic detection and segmentation of prostate zones based on YOLO-D. Technology and Health Care. https://doi.org/10.1177/09287329251392399

Vancouver

Wang X, Feng R, Xu C, Wang C, Wang W, Gao C, et al. Research on automatic detection and segmentation of prostate zones based on YOLO-D. Technology and Health Care. 2025. doi:10.1177/09287329251392399

BibTeX
@article{Wang2025,
  author = {Wang, Xiaodong and Feng, Rui and Xu, Chen and Wang, Chuanbing and Wang, Wei and Gao, Chang and Tan, Ye},
  title = {Research on automatic detection and segmentation of prostate zones based on YOLO-D},
  journal = {Technology and Health Care},
  year = {2025},
  doi = {10.1177/09287329251392399}
}
Kostenlos starten →