Application of Machine Learning Based on Ultrasonic RF Time Series and 2D Image Features in the Diagnosis of BI ‐ RADS 4A Lesions of Breast
Journal of Ultrasound in Medicine · 2026
DOI: 10.1002/jum.70097 ↗Kurz gefasst
Evaluationsstudie in der Zeitschrift Journal of Ultrasound in Medicine, 2026. Verfasst von Ruifang Guo und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Ultrasound, Beijing Friendship Hospital, Capital Medical University, Beijing, China. Hauptthemen laut MEDLINE: Machine Learning, Image Interpretation, Computer-Assisted, Breast, Breast Neoplasms. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 17 Literaturangaben.
Abstract (Originalsprache)
Objectives
This study aimed to develop and validate machine‐learning (ML) models that integrate ultrasonic radiofrequency (RF) time‐series signals with gray‐scale image features for the preoperative differentiation of breast lesions classified as category 4A of the Breast Imaging Reporting and Data System.
Methods
A dataset comprising RF signals, 2D ultrasound features, and pathological diagnoses from 130 BI‐RADS 4A lesions (128 patients) was analyzed. Five ML models (logistic regression [LR], support vector machine [SVM], k‐nearest neighbor [k‐NN], and gradient boosting [GB]) were evaluated.
Results
Among 31 features (28 RF‐derived and 5 2D image features), 6 key features were selected through feature selection. The LR model achieved the highest area under the curve (0.81, 95% confidence interval: 0.66–1.00), though no statistically significant differences were observed among models (DeLong test, p > .05). Artificial intelligence‐assisted diagnosis improved accuracy across physician seniority levels ( p < .05): junior (≤3 years: 52.28% versus baseline 27.28%), intermediate (4–10 years: 79.54% versus 45.46%), and senior (≥10 years: 81.91% versus 63.63%).
Conclusion
The integration of RF time series and 2D features via LR demonstrates potential to reduce unnecessary biopsies by enhancing diagnostic precision, particularly for less experienced clinicians.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Ultrasound, Beijing Friendship Hospital, Capital Medical University, Beijing, China.
ORCID-Profile: Xiangdong Hu
Zitieren
APA
Guo, R., Wang, Z., Cao, X., Sun, P., Qian, L., & Hu, X. (2026). Application of Machine Learning Based on Ultrasonic RF Time Series and 2D Image Features in the Diagnosis of BI ‐ RADS 4A Lesions of Breast. Journal of Ultrasound in Medicine. https://doi.org/10.1002/jum.70097
Vancouver
Guo R, Wang Z, Cao X, Sun P, Qian L, Hu X. Application of Machine Learning Based on Ultrasonic RF Time Series and 2D Image Features in the Diagnosis of BI ‐ RADS 4A Lesions of Breast. Journal of Ultrasound in Medicine. 2026. doi:10.1002/jum.70097
BibTeX
@article{Guo2026,
author = {Guo, Ruifang and Wang, Zhixiang and Cao, Xuebin and Sun, Pengfei and Qian, Linxue and Hu, Xiangdong},
title = {Application of Machine Learning Based on Ultrasonic RF Time Series and 2D Image Features in the Diagnosis of BI ‐ RADS 4A Lesions of Breast},
journal = {Journal of Ultrasound in Medicine},
year = {2026},
doi = {10.1002/jum.70097}
}
EUVIMED