Improvement of RT-DETR model for ground glass pulmonary nodule detection
PLOS ONE · 11.03.2025 · 20 (3) · e0317114
DOI: 10.1371/journal.pone.0317114 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 11.03.2025. Verfasst von Siyuan Tang und 9 weiteren Autor:innen. Beteiligte Einrichtung: College of computer science and technology, Inner Mongolia Normal University, Hohhot, Inner Mongolia, China. Hauptthemen laut MEDLINE: Solitary Pulmonary Nodule, Lung Neoplasms, Multiple Pulmonary Nodules. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Inner Mongolia Natural Science Foundation, Inner Mongolia Health Commission Project, Baotou Municipal Health Science and Technology Project.
Abstract (Originalsprache)
Currently, pulmonary nodules detection work mostly focus on recognition and diagnosis of solid nodules. However, ground glass nodules have higher probability of malignancy, posing greater identification challenges and thus greater value for detection. To achieve rapid and accurate detection of ground glass nodules. This article proposed an algorithm based on RT-DETR model with the following enhancement: 1) optimize the backbone network with FCGE blocks to increase the detection accuracy of small-sized and blurred edge nodules; 2) replace the AIFI module with HiLo-AIFI module to reduce redundant computation and improve the detection accuracy of pure ground glass pulmonary nodules and mixed ground glass pulmonary nodules; 3) replace the DGAK module with CCFF module to address the issue of capturing complex features and recognition of irregularly shaped ground glass nodules. To obtain a more lightweight model, modules are designed for smaller number of parameters and higher computational efficiency. Model are tested on mixed dataset composed of LIDC-IDRI data and clinical data from cooperating hospitals. Compared to the baseline model, it shows an average precision improvement (mAP50/mAP50:95) of 2.1% and 1.7%, with a reduction parameters by 5.2 million. On a specialized dataset containing both pure and mixed ground glass nodules, our model outperformed the baseline model in all evaluation metrics. In general, the model proposed in this paper achieves improvement on lightweightness and detection accuracy. However, the model exhibits poor noise resistance and robustness, suggesting optimization in future work.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- College of computer science and technology, Inner Mongolia Normal University, Hohhot, Inner Mongolia, China.
- Baotou Medical College, Inner Mongolia University of Science and Technology, Baotou, Inner Mongolia, China.
- School of Digital and Intelligence Industry, Inner Mongolia University of Science and Technology, Baotou, Inner Mongolia, China.
- Second Affiliated Hospital of Baotou Medical College, Inner Mongolia University of Science and Technology, Baotou, Inner Mongolia, China.
ORCID-Profile: Siriguleng Wang
Förderung
- Inner Mongolia Natural Science Foundation
- Inner Mongolia Health Commission Project
- Baotou Municipal Health Science and Technology Project
- Inner Mongolia College Students' Innovation and Entrepreneurship Training Program Projects
- Scientific Research for the Public Hospitals of Inner Mongolia Academy of Medical Sciences
- National College Students Innovation and Entrepreneurship Training Program
- Science and Technology Major Project of Inner Mongolia
- Baotou Municipal Health Science and Technology
Zitieren
APA
Tang, S., Bao, Q., Ji, Q., Wang, T., Wang, N., Yang, M., Gu, Y., Zhao, J., Qu, Y., & Wang, S. (2025). Improvement of RT-DETR model for ground glass pulmonary nodule detection. PLOS ONE, 20(3), e0317114. https://doi.org/10.1371/journal.pone.0317114
Vancouver
Tang S, Bao Q, Ji Q, Wang T, Wang N, Yang M, et al. Improvement of RT-DETR model for ground glass pulmonary nodule detection. PLOS ONE. 2025;20(3):e0317114. doi:10.1371/journal.pone.0317114
BibTeX
@article{Tang2025,
author = {Tang, Siyuan and Bao, Qiangqiang and Ji, Qingyu and Wang, Tong and Wang, Naiyu and Yang, Min and Gu, Yu and Zhao, Jinliang and Qu, Yuhan and Wang, Siriguleng},
title = {Improvement of RT-DETR model for ground glass pulmonary nodule detection},
journal = {PLOS ONE},
year = {2025},
volume = {20},
number = {3},
pages = {e0317114},
doi = {10.1371/journal.pone.0317114}
}
EUVIMED