Artificial Intelligence-Assisted Opportunistic Screening for Breast Cancer Using Non-Contrast Chest CT: A Comparative Study With Mammography and/or Breast MRI
试验速览
- 阶段
- 不适用
- 状态
- 尚未招募
- 入组人数
- 5,000
- 试验地点
- 1
- 主要终点
- Screening performance of non-contrast chest CT for detection of breast cancer, with comparison to mammography and/or breast MRI
研究概览
简要总结
The goal of this observational study is to evaluate the feasibility and effectiveness of using non-contrast chest computed tomography scans for opportunistic breast cancer screening, and to further compare its diagnostic performance with conventional imaging modalities, including mammography and/or breast magnetic resonance imaging.
详细描述
Breast cancer is one of the most common malignancies in women, and early detection is essential for improving clinical outcomes. While dedicated breast imaging modalities, including mammography and breast MRI, are widely used for screening. Many women undergo non-contrast chest CT scans for other clinical indications, providing a potential opportunity for breast evaluation. This observational study aims to investigate the clinical value of non-contrast chest CT scans as an opportunistic screening tool for breast cancer. Breast tissue visible on routine CT scans will be assessed using artificial intelligence-based methods to identify suspicious lesions. The primary objective is to evaluate the diagnostic performance of non-contrast chest CT in detecting breast cancer, including sensitivity, specificity, and accuracy, and to further compare its diagnostic performance with mammography and breast MRI. The findings are expected to determine whether non-contrast chest CT can serve as an opportunistic tool for early breast cancer detection without additional imaging burden, and to clarify its relative clinical value compared with established breast imaging techniques.
研究设计
- 研究类型
- Observational
- 观察模型
- Cohort
- 时间视角
- Prospective
入排标准
- 年龄范围
- 18 Years 至 —（Adult, Older Adult）
- 性别
- Female
- 接受健康志愿者
- 是
入选标准
- •Female patients who have undergone non-contrast chest CT examination;
- •Participants included in the comparative analysis must have undergone at least one comparator imaging modality (mammography and/or breast MRI);
- •If a breast lesion is detected, it must be confirmed by pathology or clinical follow-up at least 12 months;
- •No prior systemic or local therapy before imaging examinations;
- •Imaging data are complete and of sufficient quality for analysis.
排除标准
- •History of other malignancies with potential impact on breast imaging interpretation;
- •Participants with suspected malignant breast lesions but no confirmation;
- •Prior radiotherapy, chemotherapy, or immunotherapy before imaging examinations;
- •Imaging data that are incomplete, of poor quality, or contain significant artifacts preventing reliable analysis;
- •Time interval between non-contrast chest CT and comparator imaging modalities exceeding three months, or with clinical events occurring between examinations that may alter lesion status.
结局指标
主要结局
Screening performance of non-contrast chest CT for detection of breast cancer, with comparison to mammography and/or breast MRI
时间窗: Up to 12 months
The primary outcome is the screening performance of AI-assisted analysis for the detection of breast cancer on non-contrast chest CT. The detection process is conducted in a stepwise approach, involving lesion identification followed by classification into benign or malignant categories for breast cancer detection. Performance metrics include sensitivity, specificity, positive predictive value, negative predictive value, accuracy, and area under the receiver operating characteristic curve. Participants included in the comparative analysis must have undergone at least one comparator imaging modality (mammography and/or breast MRI) within three months of the chest CT examination, with no intervening clinical events. Performance metrics will be further compared with those obtained from mammography and/or breast MRI within the same participants to evaluate the relative screening performance.
次要结局
- Performance of non-contrast chest CT for histological classification of breast cancer, with comparison to mammography and/or breast MRI(Up to 12 months)
研究者
Yajia Gu, MD
Professor, Department of Radiology, Fudan University Shanghai Cancer Center
Fudan University