EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing breast ultrasound segmentation through fine-tuning and optimization techniques: Sharp attention UNet

Donya Khaledyan iD, Thomas J Marini, Timothy M Baran, Avice O'Connell, Kevin Parker

PLOS ONE · 13.12.2023 · 18 (12) · e0289195

DOI: 10.1371/journal.pone.0289195 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 13.12.2023. Verfasst von Donya Khaledyan und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Electronics Engineering, University of Rochester, Rochester, NY, United States of America. Hauptthemen laut MEDLINE: Benchmarking, Diagnosis, Computer-Assisted. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 82 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIA NIH HHS, NIBIB NIH HHS, National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Segmentation of breast ultrasound images is a crucial and challenging task in computer-aided diagnosis systems. Accurately segmenting masses in benign and malignant cases and identifying regions with no mass is a primary objective in breast ultrasound image segmentation. Deep learning (DL) has emerged as a powerful tool in medical image segmentation, revolutionizing how medical professionals analyze and interpret complex imaging data. The UNet architecture is a highly regarded and widely used DL model in medical image segmentation. Its distinctive architectural design and exceptional performance have made it popular among researchers. With the increase in data and model complexity, optimization and fine-tuning models play a vital and more challenging role than before. This paper presents a comparative study evaluating the effect of image preprocessing and different optimization techniques and the importance of fine-tuning different UNet segmentation models for breast ultrasound images. Optimization and fine-tuning techniques have been applied to enhance the performance of UNet, Sharp UNet, and Attention UNet. Building upon this progress, we designed a novel approach by combining Sharp UNet and Attention UNet, known as Sharp Attention UNet. Our analysis yielded the following quantitative evaluation metrics for the Sharp Attention UNet: the Dice coefficient, specificity, sensitivity, and F1 score values obtained were 0.93, 0.99, 0.94, and 0.94, respectively. In addition, McNemar’s statistical test was applied to assess significant differences between the approaches. Across a number of measures, our proposed model outperformed all other models, resulting in improved breast lesion segmentation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

BenchmarkingDiagnosis, Computer-AssistedFemaleHumansResearch PersonnelUltrasonography, MammaryImage Processing, Computer-Assisted

Autor:innen und Institutionen

  • Department of Electrical and Electronics Engineering, University of Rochester, Rochester, NY, United States of America.
  • Department of Imaging Sciences, University of Rochester Medical Center, Rochester, NY, United States of America.

ORCID-Profile: Donya Khaledyan

Förderung

  • NIA NIH HHS
  • NIBIB NIH HHS
  • National Institutes of Health

Zitieren

APA

Khaledyan, D., Marini, T. J., M Baran, T., O'Connell, A., & Parker, K. (2023). Enhancing breast ultrasound segmentation through fine-tuning and optimization techniques: Sharp attention UNet. PLOS ONE, 18(12), e0289195. https://doi.org/10.1371/journal.pone.0289195

Vancouver

Khaledyan D, Marini TJ, M Baran T, O'Connell A, Parker K. Enhancing breast ultrasound segmentation through fine-tuning and optimization techniques: Sharp attention UNet. PLOS ONE. 2023;18(12):e0289195. doi:10.1371/journal.pone.0289195

BibTeX
@article{Khaledyan2023,
  author = {Khaledyan, Donya and Marini, Thomas J and M Baran, Timothy and O'Connell, Avice and Parker, Kevin},
  title = {Enhancing breast ultrasound segmentation through fine-tuning and optimization techniques: Sharp attention UNet},
  journal = {PLOS ONE},
  year = {2023},
  volume = {18},
  number = {12},
  pages = {e0289195},
  doi = {10.1371/journal.pone.0289195}
}
Kostenlos starten →