Artificial intelligence for ultrasound microflow imaging in breast cancer diagnosis
Ultraschall in der Medizin - European Journal of Ultrasound · 01.08.2024 · 45 (04) · 412-417
DOI: 10.1055/a-2230-2455 ↗Kurz gefasst
Fachartikel in der Zeitschrift Ultraschall in der Medizin - European Journal of Ultrasound, erschienen am 01.08.2024. Verfasst von Na Lae Eun und 5 weiteren Autor:innen. Beteiligte Einrichtung: Radiology, Gangnam Severance Hospital, Seoul, Korea (the Republic of). Hauptthemen laut MEDLINE: Breast Neoplasms, Artificial Intelligence, Algorithms, Ultrasonography, Mammary. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 30 Literaturangaben.
Abstract (Originalsprache)
Purpose
To develop and evaluate artificial intelligence (AI) algorithms for ultrasound (US) microflow imaging (MFI) in breast cancer diagnosis. Materials and Methods We retrospectively collected a dataset consisting of 516 breast lesions (364 benign and 152 malignant) in 471 women who underwent B-mode US and MFI. The internal dataset was split into training (n = 410) and test datasets (n = 106) for developing AI algorithms from deep convolutional neural networks from MFI. AI algorithms were trained to provide malignancy risk (0–100%). The developed AI algorithms were further validated with an independent external dataset of 264 lesions (229 benign and 35 malignant). The diagnostic performance of B-mode US, AI algorithms, or their combinations was evaluated by calculating the area under the receiver operating characteristic curve (AUROC).
Results
The AUROC of the developed three AI algorithms (0.955–0.966) was higher than that of B-mode US (0.842, P < 0.0001). The AUROC of the AI algorithms on the external validation dataset (0.892–0.920) was similar to that of the test dataset. Among the AI algorithms, no significant difference was found in all performance metrics combined with or without B-mode US. Combined B-mode US and AI algorithms had a higher AUROC (0.963–0.972) than that of B-mode US (P < 0.0001). Combining B-mode US and AI algorithms significantly decreased the false-positive rate of BI-RADS category 4A lesions from 87% to 13% (P < 0.0001).
Conclusion
AI-based MFI diagnosed breast cancers with better performance than B-mode US, eliminating 74% of false-positive diagnoses in BI-RADS category 4A lesions.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Radiology, Gangnam Severance Hospital, Seoul, Korea (the Republic of).
- Computational Science and Engineering, Yonsei University, Seoul, Korea (the Republic of).
- Radiology, Bundang CHA Medical Center, Seongnam, Korea (the Republic of).
- Department of Radiology, Yonsei University College of Medicine, Seoul, Korea, Republic of.
ORCID-Profile: Ah Young Park
Zitieren
APA
Eun, N. L., Lee, E., Park, A. Y., Son, E. J., Kim, J. A., & Youk, J. H. (2024). Artificial intelligence for ultrasound microflow imaging in breast cancer diagnosis. Ultraschall in der Medizin - European Journal of Ultrasound, 45(04), 412-417. https://doi.org/10.1055/a-2230-2455
Vancouver
Eun NL, Lee E, Park AY, Son EJ, Kim JA, Youk JH. Artificial intelligence for ultrasound microflow imaging in breast cancer diagnosis. Ultraschall in der Medizin - European Journal of Ultrasound. 2024;45(04):412-417. doi:10.1055/a-2230-2455
BibTeX
@article{Eun2024,
author = {Eun, Na Lae and Lee, Eunjung and Park, Ah Young and Son, Eun Ju and Kim, Jeong-Ah and Youk, Ji Hyun},
title = {Artificial intelligence for ultrasound microflow imaging in breast cancer diagnosis},
journal = {Ultraschall in der Medizin - European Journal of Ultrasound},
year = {2024},
volume = {45},
number = {04},
pages = {412--417},
doi = {10.1055/a-2230-2455}
}
EUVIMED