arXiv 2411.008912024-11-07eess.IVcs.AIcs.CV

深度学习在临床乳腺超声图像中预测乳腺钼靶密度

Deep Learning Predicts Mammographic Breast Density in Clinical Breast Ultrasound Images

University of Hawai’i at Mānoa（夏威夷大学马诺阿分校）；University of Hawai’i Cancer Center（夏威夷大学癌症中心）；The Queen’s Medical Center（皇后医疗中心）；Hawaiʻi Pacific Health（夏威夷太平洋健康）；Hawaiʻi Diagnostic Radiology Services（夏威夷诊断放射服务中心）

Arianna Bunnell, Dustin Valdez, Thomas K. Wolfgruber, Brandon Quon, Kailee Hung, Brenda Y. Hernandez, Todd B. Seto, Jeffrey Killeen, Marshall Miyoshi, Peter Sad… 展开作者

Arianna Bunnell, Dustin Valdez, Thomas K. Wolfgruber, Brandon Quon, Kailee Hung, Brenda Y. Hernandez, Todd B. Seto, Jeffrey Killeen, Marshall Miyoshi, Peter Sadowski, John A. Shepherd

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本研究利用深度学习从临床乳腺超声图像预测BI-RADS乳腺钼靶密度，在测试集上达到0.854 AUROC，并证明AI衍生的超声密度可预测5年乳腺癌风险，性能与临床密度相当。

摘要：

背景：乳腺密度，源自乳腺钼靶图像，并由美国放射学会的乳腺影像报告和数据系统（BI-RADS）定义，是乳腺癌最强的风险因素之一。乳腺超声（BUS）是另一种乳腺癌筛查方式，在资源匮乏的农村地区尤其有助于早期检测。本研究旨在探索一种人工智能（AI）模型，从临床手持式BUS图像中预测BI-RADS乳腺钼靶密度类别。方法：所有数据均来自夏威夷和太平洋岛屿乳腺摄影登记处。我们比较了基于BUS图像的深度学习方法，以及仅基于图像统计的机器学习模型。随后，将AI衍生的BUS密度作为乳腺癌风险因素，与临床BI-RADS乳腺密度进行比较，并调整年龄因素。BUS数据按个体分为70/20/10%组，分别用于训练、验证和测试。结果：本研究共纳入来自14,066名女性的405,120张临床BUS图像，其中9,846名女性用于训练（302,574张图像），2,813名用于验证（11,223张图像），1,406名用于测试（4,042张图像）。在保留的测试集上，最强的AI模型从BUS图像预测BI-RADS乳腺钼靶密度，AUROC达到0.854，优于所有基于图像统计的浅层机器学习方法。在癌症风险预测中，经年龄调整的AI BUS乳腺密度预测5年乳腺癌风险的AUROC为0.633，而经年龄调整的临床乳腺密度的AUROC为0.637。结论：使用深度学习模型可以从BUS图像中高精度地估计BI-RADS乳腺钼靶密度。此外，我们证明AI衍生的BUS乳腺密度在我们的人群中可预测5年乳腺癌风险。

英文摘要：

Background: Breast density, as derived from mammographic images and defined by the American College of Radiology's Breast Imaging Reporting and Data System (BI-RADS), is one of the strongest risk factors for breast cancer. Breast ultrasound (BUS) is an alternative breast cancer screening modality, particularly useful for early detection in low-resource, rural contexts. The purpose of this study was to explore an artificial intelligence (AI) model to predict BI-RADS mammographic breast density category from clinical, handheld BUS imaging. Methods: All data are sourced from the Hawaii and Pacific Islands Mammography Registry. We compared deep learning methods from BUS imaging, as well as machine learning models from image statistics alone. The use of AI-derived BUS density as a risk factor for breast cancer was then compared to clinical BI-RADS breast density while adjusting for age. The BUS data were split by individual into 70/20/10% groups for training, validation, and testing. Results: 405,120 clinical BUS images from 14.066 women were selected for inclusion in this study, resulting in 9.846 women for training (302,574 images), 2,813 for validation (11,223 images), and 1,406 for testing (4,042 images). On the held-out testing set, the strongest AI model achieves AUROC 0.854 predicting BI-RADS mammographic breast density from BUS imaging and outperforms all shallow machine learning methods based on image statistics. In cancer risk prediction, age-adjusted AI BUS breast density predicted 5-year breast cancer risk with 0.633 AUROC, as compared to 0.637 AUROC from age-adjusted clinical breast density. Conclusions: BI-RADS mammographic breast density can be estimated from BUS imaging with high accuracy using a deep learning model. Furthermore, we demonstrate that AI-derived BUS breast density is predictive of 5-year breast cancer risk in our population.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。