YOLO-ED: An efficient lung cancer detection model based on improved YOLOv8
PLOS One · 04.09.2025 · 20 (9) · e0330732
DOI: 10.1371/journal.pone.0330732 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 04.09.2025. Verfasst von Qingqiang Zeng und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering, Macau University of Science and Technology, Macau, China. Hauptthemen laut MEDLINE: Lung Neoplasms, Tomography, X-Ray Computed, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fund of Guangdong-Hong Kong-Macao Joint Laboratory for Intelligent Micro-Nano Optoelectronic Technology.
Abstract (Originalsprache)
In recent years, You Only Look Once (YOLO) models have gradually been applied to medical image object detection tasks due to their good scalability and excellent generalization performance, bringing new perspectives and approaches to this field. However, existing models overlook the impact of numerous consecutive convolutions and the sampling blur caused by bilinear interpolation, resulting in excessive computational costs and insufficient precision in object detection. To address these problems, we propose a YOLOv8-based model using Efficient modulation and dynamic upsampling (YOLO-ED) to detect lung cancer in CT images. Specifically, we incorporate two innovative modules, the Efficient Modulation module and the DySample module, into the YOLOv8 model. The Efficient Modulation module employs a weighted fusion strategy to extract features from input CT images, effectively reducing model parameters and computational overhead. Furthermore, the DySample module is designed to replace the conventional upsampling component in YOLO, thereby mitigating information loss when expanding feature maps. The dynamic bilinear interpolation introduced by this module increases random bias, which helps minimize errors in feature extraction. To validate the effectiveness of YOLO-ED, we compared it with baselines on the LUNG-PET-CT-DX lung cancer diagnosis dataset and the LUNA16 lung nodule dataset. The results show that YOLO-ED significantly improves precision and reduces computational cost on these two datasets, demonstrating its superiority in the detection of medical images.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Computer Science and Engineering, Macau University of Science and Technology, Macau, China.
- Central Laboratory, the Third People's Hospital of ZhuHai, ZhuHai, China.
ORCID-Profile: Qingqiang Zeng, Jianqing Li, Yuanyuan Pan
Förderung
- Fund of Guangdong-Hong Kong-Macao Joint Laboratory for Intelligent Micro-Nano Optoelectronic Technology
Zitieren
APA
Zeng, Q., Hu, T., Chen, Z., Zheng, J., Li, J., & Pan, Y. (2025). YOLO-ED: An efficient lung cancer detection model based on improved YOLOv8. PLOS One, 20(9), e0330732. https://doi.org/10.1371/journal.pone.0330732
Vancouver
Zeng Q, Hu T, Chen Z, Zheng J, Li J, Pan Y. YOLO-ED: An efficient lung cancer detection model based on improved YOLOv8. PLOS One. 2025;20(9):e0330732. doi:10.1371/journal.pone.0330732
BibTeX
@article{Zeng2025,
author = {Zeng, Qingqiang and Hu, Tao and Chen, Zijie and Zheng, Jiexin and Li, Jianqing and Pan, Yuanyuan},
title = {YOLO-ED: An efficient lung cancer detection model based on improved YOLOv8},
journal = {PLOS One},
year = {2025},
volume = {20},
number = {9},
pages = {e0330732},
doi = {10.1371/journal.pone.0330732}
}
EUVIMED