English(EN) External Validation of Deep Learning Models for BI-RADS Breast Density Prediction from Ultrasound Images

AI模型在超声检查中显示出强大的乳腺密度预测能力，泛化性良好

作者 PulseAugur 编辑部 · [2 个来源] · 2026-05-06 16:19

研究人员对三种深度学习模型——DenseNet121、ViT-B/32和ResNet50——进行了外部验证，用于从超声图像预测乳腺密度。这些模型表现出强大的性能，尤其是在极度致密的乳腺中，尽管异质性致密的乳腺仍然是一个挑战。当整合到风险预测模型中时，AI衍生的密度与乳房X线摄影报告的密度显示出可比的结果，表明其在不同人群中的泛化能力。 AI

影响验证了深度学习模型在医学成像任务中的泛化能力，但也指出了密度评估方面需要进一步优化的领域。

排序理由这是一篇研究论文，详细介绍了深度学习模型在特定医学成像任务中的外部验证。

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.CV TIER_1 English(EN) · Yuxuan Chen, Arianna Bunnell, Yanqi Xu, Haoyan Yang, Thomas K. Wolfgruber, John A. Shepherd, Yiqiu Shen · 2026-05-07 04:00

External Validation of Deep Learning Models for BI-RADS Breast Density Prediction from Ultrasound Images

arXiv:2605.05082v1 Announce Type: cross Abstract: We externally validated three deep learning models (DenseNet121, ViT-B/32, and ResNet50) for predicting mammographic breast density from breast ultrasound exams on an independent cohort. The external validation set comprised 2,000…
arXiv cs.CV TIER_1 English(EN) · Yiqiu Shen · 2026-05-06 16:19

External Validation of Deep Learning Models for BI-RADS Breast Density Prediction from Ultrasound Images

We externally validated three deep learning models (DenseNet121, ViT-B/32, and ResNet50) for predicting mammographic breast density from breast ultrasound exams on an independent cohort. The external validation set comprised 2,000 ultrasound exams, including 500 cancer cases defi…

报道来源 [2]

External Validation of Deep Learning Models for BI-RADS Breast Density Prediction from Ultrasound Images

External Validation of Deep Learning Models for BI-RADS Breast Density Prediction from Ultrasound Images

相关实体

相关话题