EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Attention-Enhanced Lightweight Architecture with Hybrid Loss for Colposcopic Image Segmentation

Priyadarshini Chatterjee iD, Shadab Siddiqui, Razia Sulthana Abdul Kareem, Srikant Rao

Cancers · 25.02.2025 · 17 (5) · 781

DOI: 10.3390/cancers17050781 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cancers, online erschienen am 25.02.2025. Verfasst von Priyadarshini Chatterjee und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Hyderabad 500075, Telangana, India. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cervical cancer screening through computer-aided diagnosis often faces challenges like inaccurate segmentation and incomplete boundary detection in colposcopic images. This study proposes a lightweight segmentation model to improve accuracy and computational efficiency. The architecture integrates dual encoder backbones (ResNet50 and MobileNetV2) for high-level and efficient feature extraction. While a lightweight atrous spatial pyramid pooling (ASPP) module records multi-scale contextual information, a novel attention module improves feature details by concentrating on relevant locations. The decoder employs advanced upsampling and feature fusion for refined segmentation boundaries. The experimental results show exceptional performance: training accuracy of 97.56%, validation accuracy of 96.04%, 97.00% specificity, 96.78% sensitivity, 98.71% Dice coefficient, and 97.56% IoU, outperforming the existing methods. In collaboration with the MNJ Institute of Oncology Regional Center, Hyderabad, this work demonstrates potential for real-world clinical applications, delivering precise and reliable colposcopic image segmentation. This research advances efficient, accurate tools for cervical cancer diagnosis, improving diagnostic workflows and patient outcomes.

Schlagwörter

Stichwörter der Autor:innen

cervical cancercontextual informationimage segmentationloss functionmulti-scale feature extractionrefinement module

Autor:innen und Institutionen

  • Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Hyderabad 500075, Telangana, India.
  • Old Royal Naval College, University of Greenwich, Park Row, London SE10 9LS, UK.
  • MNJ Institue of Oncology and Regional Cancer Center, Hyderabad 500004, Telangana, India.

ORCID-Profile: Priyadarshini Chatterjee

Zitieren

APA

Chatterjee, P., Siddiqui, S., Kareem, R. S. A., & Rao, S. (2025). Attention-Enhanced Lightweight Architecture with Hybrid Loss for Colposcopic Image Segmentation. Cancers, 17(5), 781. https://doi.org/10.3390/cancers17050781

Vancouver

Chatterjee P, Siddiqui S, Kareem RSA, Rao S. Attention-Enhanced Lightweight Architecture with Hybrid Loss for Colposcopic Image Segmentation. Cancers. 2025;17(5):781. doi:10.3390/cancers17050781

BibTeX
@article{Chatterjee2025,
  author = {Chatterjee, Priyadarshini and Siddiqui, Shadab and Kareem, Razia Sulthana Abdul and Rao, Srikant},
  title = {Attention-Enhanced Lightweight Architecture with Hybrid Loss for Colposcopic Image Segmentation},
  journal = {Cancers},
  year = {2025},
  volume = {17},
  number = {5},
  pages = {781},
  doi = {10.3390/cancers17050781}
}
Kostenlos starten →