EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Inception U-Net for Enhanced Breast Ultrasound Image Segmentation Using Transfer Learning

Yeonhyo Choi, Myoung Nam Kim iD, Sungdae Na iD

Bioengineering · 04.02.2026 · 13 (2) · 181

DOI: 10.3390/bioengineering13020181 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioengineering, online erschienen am 04.02.2026. Verfasst von Yeonhyo Choi und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical & Biological Engineering, Graduate School, Kyungpook National University, Daegu 41404, Republic of Korea. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIP), Korean government.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Breast cancer diagnosis increasingly relies on ultrasound imaging, but challenges related to operator dependency and image quality limitations necessitate automated segmentation approaches. Traditional U-Net architectures, while widely used for medical image segmentation, suffer from shallow encoder structures that limit feature extraction capabilities.

Methods

This study proposes an enhanced segmentation model that replaces the conventional U-Net encoder with an Inception architecture and employs transfer learning using ImageNet pre-trained weights. The model was trained and evaluated on a dataset of 900 breast ultrasound images from Kyungpook National University Hospital. Performance evaluation utilized multiple metrics including Intersection over Union (IoU), Dice coefficient, precision, and recall scores.

Results

The proposed Inception U-Net achieved superior performance with an IoU score of 0.7774, Dice score of 0.8491, precision score of 0.7081, and recall score of 0.7174, demonstrating approximately 5% improvement over baseline U-Net architecture across all evaluation metrics.

Conclusions

The integration of Inception modules within the U-Net architecture effectively addresses feature extraction limitations in breast ultrasound segmentation. Transfer learning from ImageNet datasets proves beneficial even across domain differences, establishing a foundation for broader medical imaging applications.

Schlagwörter

Stichwörter der Autor:innen

U-Netbreast ultrasounddeep learningimage segmentationinceptionmedical imagingtransfer learning

Autor:innen und Institutionen

  • Department of Medical & Biological Engineering, Graduate School, Kyungpook National University, Daegu 41404, Republic of Korea.
  • Department of Biomedical Engineering, School of Medicine, Kyungpook National University, Daegu 41404, Republic of Korea.
  • Department of Biomedical Engineering, Kyungpook National University Hospital, Daegu 41944, Republic of Korea.

ORCID-Profile: Myoung Nam Kim, Sungdae Na

Förderung

  • This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIP)
  • Korean government

Zitieren

APA

Choi, Y., Kim, M. N., & Na, S. (2026). Inception U-Net for Enhanced Breast Ultrasound Image Segmentation Using Transfer Learning. Bioengineering, 13(2), 181. https://doi.org/10.3390/bioengineering13020181

Vancouver

Choi Y, Kim MN, Na S. Inception U-Net for Enhanced Breast Ultrasound Image Segmentation Using Transfer Learning. Bioengineering. 2026;13(2):181. doi:10.3390/bioengineering13020181

BibTeX
@article{Choi2026,
  author = {Choi, Yeonhyo and Kim, Myoung Nam and Na, Sungdae},
  title = {Inception U-Net for Enhanced Breast Ultrasound Image Segmentation Using Transfer Learning},
  journal = {Bioengineering},
  year = {2026},
  volume = {13},
  number = {2},
  pages = {181},
  doi = {10.3390/bioengineering13020181}
}
Kostenlos starten →