EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CAML-PSPNet: A Medical Image Segmentation Network Based on Coordinate Attention and a Mixed Loss Function

Yuxia Li iD, Peng Li, Hailing Wang, Xiaomei Gong, Zhijun Fang

Sensors · 12.02.2025 · 25 (4) · 1117

DOI: 10.3390/s25041117 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 12.02.2025. Verfasst von Yuxia Li und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shanghai Science and Technology Innovation Action Plan, National Natural Science Foundation of China, Clinical Research fundation of Shanghai Pulmonary Hospital.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The problems of missed segmentation with fuzzy boundaries of segmented regions and small regions are common in segmentation tasks, and greatly decrease the accuracy of clinicians’ diagnosis. For this, a new network based on PSPNet, using a coordinate attention mechanism and a mixed loss function for segmentation (CAML-PSPNet), is proposed. Firstly, the coordinate attention module splits the input feature map into horizontal and vertical directions to locate the edge position of the segmentation target. Then, a Mixed Loss function (MLF) is introduced in the model training stage to solve the problem of the low accuracy of small-target tumor segmentation. Finally, the lightweight MobilenetV2 is utilized in backbone feature extraction, which largely reduces the model’s parameter count and enhances computation speed. Three datasets—PrivateLT, Kvasir-SEG and ISIC 2017—are selected for the experimental part, and the experimental results demonstrate significant enhancements in both visual effects and evaluation metrics for the segmentation achieved by CAML-PSPNet. Compared with Deeplabv3, HrNet, U-Net and PSPNet networks, the average intersection rates of CAML-PSPNet are increased by 2.84%, 3.1%, 5.4% and 3.08% on lung cancer data, 7.54%, 3.1%, 5.91% and 8.78% on Kvasir-SEG data, and 1.97%, 0.71%, 3.83% and 0.78% on ISIC 2017 data, respectively. When compared to other methods, CAML-PSPNet has the greatest similarity with the gold standard in boundary segmentation, and effectively enhances the segmentation accuracy for small targets.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Processing, Computer-AssistedHumansAlgorithmsNeural Networks, ComputerLung Neoplasms

Stichwörter der Autor:innen

PSPNetattention mechanismimage segmentationlung tumormixed loss

Autor:innen und Institutionen

  • School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China.
  • Department of Radiation Oncology, Shanghai Pulmonary Hospital, Tongji University School of Medicine, Shanghai 200433, China.

ORCID-Profile: Yuxia Li

Förderung

  • Shanghai Science and Technology Innovation Action Plan
  • National Natural Science Foundation of China
  • Clinical Research fundation of Shanghai Pulmonary Hospital
  • Clinical Research Foundation of Shanghai Pulmonary Hospital

Zitieren

APA

Li, Y., Li, P., Wang, H., Gong, X., & Fang, Z. (2025). CAML-PSPNet: A Medical Image Segmentation Network Based on Coordinate Attention and a Mixed Loss Function. Sensors, 25(4), 1117. https://doi.org/10.3390/s25041117

Vancouver

Li Y, Li P, Wang H, Gong X, Fang Z. CAML-PSPNet: A Medical Image Segmentation Network Based on Coordinate Attention and a Mixed Loss Function. Sensors. 2025;25(4):1117. doi:10.3390/s25041117

BibTeX
@article{Li2025,
  author = {Li, Yuxia and Li, Peng and Wang, Hailing and Gong, Xiaomei and Fang, Zhijun},
  title = {CAML-PSPNet: A Medical Image Segmentation Network Based on Coordinate Attention and a Mixed Loss Function},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {4},
  pages = {1117},
  doi = {10.3390/s25041117}
}
Kostenlos starten →