Kendall Edward, Hajishafiezahramini Parham, Hamilton Matthew, Doyle Gregory, Wadden Nancy, Meruvia-Pastor Oscar
Faculty of Medicine, Memorial University of Newfoundland, St. John's, NL, Canada.
Department of Computer Science, Faculty of Science, Memorial University of Newfoundland, St. John's, NL, Canada.
Sci Data. 2025 Aug 25;12(1):1479. doi: 10.1038/s41597-025-05866-0.
Breast cancer presents the second largest cancer risk in the world to women. Early detection of cancer has been shown to be effective in reducing mortality. Population screening programs schedule regular mammography imaging for participants, promoting early detection. Currently, such screening programs require manual reading. False-positive errors in the reading process unnecessarily leads to costly follow-up and patient anxiety. Automated methods promise to provide more efficient, consistent and effective reading. To facilitate their development, a number of datasets have been created. Such datasets can aid in learning-based development but many are not publicly available and do not draw directly from population screening programs. With the aim of specifically targeting population screening programs, we introduce NL-Breast-Screening, a dataset from a Canadian provincial screening program. The dataset consists of 5997 mammography exams, each of which has four standard views and is biopsy-confirmed. Cases where radiologists' reading was a false-positive are identified. NL-Breast-Screening is made publicly available as a new resource to promote advances in automation for population screening programs.
乳腺癌是全球女性面临的第二大癌症风险。癌症的早期检测已被证明对降低死亡率有效。人群筛查项目为参与者安排定期的乳房X光成像检查，以促进早期检测。目前，此类筛查项目需要人工阅读。阅读过程中的假阳性错误会不必要地导致昂贵的后续检查和患者焦虑。自动化方法有望提供更高效、一致和有效的阅读。为了促进它们的发展，已经创建了一些数据集。此类数据集有助于基于学习的开发，但许多数据集不公开，也不是直接从人群筛查项目中获取的。为了专门针对人群筛查项目，我们引入了NL-Breast-Screening，这是一个来自加拿大省级筛查项目的数据集。该数据集由5997次乳房X光检查组成，每次检查有四个标准视图且均经活检确认。已识别出放射科医生阅读结果为假阳性的病例。NL-Breast-Screening作为一种新资源公开提供，以促进人群筛查项目自动化方面的进展。
