Interpretable Deep Learning Models for Analysis of Longitudinal 3D Mammography Screenings

用于分析纵向 3D 乳房 X 光检查的可解释深度学习模型

• 批准号: 10667745
• 负责人: Nicha C Dvornek
• 金额: $ 22.61万
• 依托单位: YALE UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-04-01 至 2026-03-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10667745
• 关键词: 3-Dimensional; Adopted; Anxiety; Appearance; Architecture; Attention; Biological Markers; Breast; Breast Cancer Detection; Breast Cancer Risk Factor; Cancer Detection; Clinical; Complex; Decision Making; Dependence; Development; Digital Breast Tomosynthesis; Elements; Eligibility Determination; Exclusion; Family; Future; Goals; Harm Reduction; Image; Learning; Malignant Neoplasms; Mammographic screening; Mammography; Medical; Methodology; Methods; Modeling; Monitor; Patients; Performance; Preventive; Preventive treatment; Procedures; Reading; Recording of previous events; Risk Estimate; Role; Screening for cancer; Technology; Time; Tissues; Woman; Work; Workload; cancer risk; cancer therapy; computer aided detection; deep learning; deep learning model; demographics; detection platform; experience; improved; longitudinal analysis; malignant breast neoplasm; mortality; neural network; novel; predictive modeling; radiologist; routine screening; screening; spatiotemporal; tool; tumor

Project Summary Mammography screening for breast cancer has clear, substantial benefits, including significantly reduced breast cancer mortality and improved treatment options for early detected cancers. However, regular mammography screenings subject women to several potential harms, including high false positive rates, with over 60% of women experiencing a false positive finding after 10 years of annual screening; high false negative rates, with more can- cers missed in dense breasts which obscure tumor appearance; and high recall rates, causing undue anxiety and unnecessary, potentially invasive workup for women with a false positive screen. New 3D mammography technology called digital breast tomosynthesis (DBT) has shown increased cancer detection and decreased re- call rates, but radiologists require longer interpretation time and may lack experience. The clinical workflow could potentially be enhanced with computer aided detection systems. However, current methods only focus on a single mammogram exam, ignoring crucial decision-making information that a radiologist would consider, such as prior mammograms, patient demographics, and personal history. Conversely, established breast cancer risk models rely only on patient demographics and personal/family history, excluding mammographic history. Toward the overarching goal of reducing the harms and increasing the benefits of mammography screening, we propose to increase accuracy of breast cancer detection and predict future cancer development from serial 3D mammogram screenings using a novel deep learning model that jointly incorporates spatial, temporal, and non-imaging clinical information. Our method adopts attention-based neural networks, i.e., Transformers, which learn complex depen- dencies between different elements in a sequence and automatically attend to the most relevant information. In addition to the potential for improved performance, the attention mechanism provides built-in model interpretation to better understand the inputs that are important for the model’s predictions, instilling user confidence in the model and facilitating extraction of mammographic biomarkers for breast cancer detection and development. Our specific aims are to: 1) develop a powerful deep learning model for simultaneously leveraging spatial, temporal, and non-imaging clinical information from DBT exams; 2) create a new tool to detect breast cancer from lon- gitudinal DBT screenings; and 3) develop a new model for predicting development of breast cancer based on longitudinal DBT studies and extract 3D mammographic biomarkers associated with cancer development. Be- yond the direct benefit of improved breast cancer detection and risk estimation, this work could reduce radiologist reading time and workload, inform new individualized screening protocols, further our understanding of the role of breast architecture in cancer risk, and guide development and monitoring of preventive treatments. Finally, the developed deep learning methodology will have wide applicability to spatiotemporal analysis in other medical conditions and imaging domains.

项目概要 乳房 X 线摄影筛查乳腺癌具有明显、实质性的好处，包括显着减少乳房 癌症死亡率和早期发现癌症的治疗选择有所改善，但是，定期进行乳房X线检查。 筛查使女性面临多种潜在危害，其中包括高假阳性率（超过 60% 的女性） 经过 10 年的年度筛查后出现假阳性结果； 致密乳房中的细胞缺失，导致肿瘤外观模糊；召回率高，导致过度焦虑 对筛查结果呈假阳性的女性进行不必要的、潜在的侵入性检查。 称为数字乳腺断层合成 (DBT) 的技术已显示出增加了癌症检出率并减少了复发率。 呼叫率，但放射科医生需要更长的解释时间并且可能缺乏临床工作流程。 可以通过计算机辅助检测系统进行增强，但是，当前的方法仅集中于单一的。 乳房X光检查，忽略了放射科医生会考虑的关键决策信息，例如之前 乳房X光检查、患者人口统计数据和离线个人病史，建立了乳腺癌风险模型。 仅依赖于患者人口统计数据和个人/家族史，不包括乳房X光检查史。 减少乳房 X 光检查筛查的危害并增加其益处的总体目标，我们建议 提高乳腺癌检测的准确性并通过连续 3D 乳房 X 光检查预测未来癌症的发展 使用新颖的深度学习模型进行筛查，该模型联合结合了空间、时间和非成像临床 我们的方法采用基于注意力的神经网络，即 Transformers，它学习复杂的依赖关系。 序列中不同元素之间的密度，并自动关注最相关的信息。 除了提高性能的潜力之外，注意力机制还提供内置的模型解释 为了更好地理解对模型预测很重要的输入，灌输用户对模型的信心 模型并促进乳房X线照相生物标志物的提取，用于乳腺癌检测和发展。 具体目标是：1）开发一个强大的深度学习模型，同时利用空间、时间、 以及来自 DBT 检查的非影像临床信息；2) 创建一种新工具来长期检测乳腺癌 垂体 DBT 筛查；以及 3) 开发一种基于乳腺癌发展预测的新模型 纵向 DBT 研究并提取与癌症发展相关的 3D 乳房 X 线摄影生物标志物。 除了改进乳腺癌检测和风险评估的直接好处之外，这项工作还可以减少放射科医生的工作量 阅读时间和工作量，为新的个性化筛选方案提供信息，进一步我们对角色的理解 乳房结构与癌症风险的关系，并指导预防性治疗的开发和监测。 开发的深度学习方法将广泛适用于其他医学的时空分析 条件和成像域。