EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing Microcalcification Detection in Mammography with YOLO-v8 Performance and Clinical Implications

Wei-Chung Shia iD, Tien-Hsiung Ku

Diagnostics · 20.12.2024 · 14 (24) · 2875

DOI: 10.3390/diagnostics14242875 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 20.12.2024. Verfasst von Wei-Chung Shia und 1 weiteren Autor:innen. Beteiligte Einrichtung: Molecular Medicine Laboratory, Department of Research, Changhua Christian Hospital, Changhua 500, Taiwan. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Changhua Christian Hospital, Department of Research, Changhua Christian Hospital, Taiwan.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Microcalcifications in the breast are often an early warning sign of breast cancer, and their accurate detection is crucial for the early discovery and management of the disease. In recent years, deep learning technology, particularly models based on object detection, has significantly improved the ability to detect microcalcifications. This study aims to use the advanced YOLO-v8 object detection algorithm to identify breast microcalcifications and explore its advantages in terms of performance and clinical application.

Methods

This study collected mammograms from 7615 female participants, with a dataset including 10,323 breast images containing microcalcifications. We used the YOLO-v8 model for microcalcification detection and trained and validated the model using five-fold cross-validation. The model’s performance was evaluated through metrics such as accuracy, recall, F1 score, mAP50, and mAP50-95. Additionally, this study explored the potential applications of this technology in clinical practice.

Results

The YOLO-v8 model achieved an mAP50 of 0.921, an mAP50-95 of 0.709, an F1 score of 0.82, a detection accuracy of 0.842, and a recall rate of 0.796 in breast microcalcification detection. Compared to previous similar deep learning object detection techniques like Mask R-CNN, YOLO-v8 has shown improvements in both speed and accuracy.

Conclusions

YOLO-v8 outperforms traditional detection methods in detecting breast microcalcifications. Its multi-scale detection capability significantly enhances both speed and accuracy, making it more clinically practical for large-scale screenings. Future research should further explore the model’s potential in benign and malignant classification to promote its application in clinical settings, assisting radiologists in diagnosing breast cancer more efficiently.

Schlagwörter

Stichwörter der Autor:innen

deep learningmammographymicrocalcificationobject detection

Autor:innen und Institutionen

  • Molecular Medicine Laboratory, Department of Research, Changhua Christian Hospital, Changhua 500, Taiwan.
  • School of Big Data and Artificial Intelligence, Fujian Polytechnic Normal University, Fuqing 350300, China.
  • Artificial Intelligence Development Center, Changhua Christian Hospital, Changhua 50050, Taiwan.
  • Department of Applied Chemistry, Providence University, Taichung 43301, Taiwan.

ORCID-Profile: Wei-Chung Shia

Förderung

  • Changhua Christian Hospital
  • Department of Research, Changhua Christian Hospital, Taiwan

Zitieren

APA

Shia, W. C., & Ku, T. H. (2024). Enhancing Microcalcification Detection in Mammography with YOLO-v8 Performance and Clinical Implications. Diagnostics, 14(24), 2875. https://doi.org/10.3390/diagnostics14242875

Vancouver

Shia WC, Ku TH. Enhancing Microcalcification Detection in Mammography with YOLO-v8 Performance and Clinical Implications. Diagnostics. 2024;14(24):2875. doi:10.3390/diagnostics14242875

BibTeX
@article{Shia2024,
  author = {Shia, Wei-Chung and Ku, Tien-Hsiung},
  title = {Enhancing Microcalcification Detection in Mammography with YOLO-v8 Performance and Clinical Implications},
  journal = {Diagnostics},
  year = {2024},
  volume = {14},
  number = {24},
  pages = {2875},
  doi = {10.3390/diagnostics14242875}
}
Kostenlos starten →