基于深度学习的乳腺癌风险预测模型的灵敏度
Zan Klanecek1, Yao-Kuan Wang2, Tobias Wagner2
1Faculty of Mathematics and Physics, Medical Physics, University of Ljubljana, Ljubljana, Slovenia.
Physics in medicine and biology
|April 7, 2025
概括
用于预测乳腺癌风险 (BCR) 的深度学习模型对乳房影像采集的图像变化敏感. 虽然整体歧视仍然不受影响,但个体风险预测可能会发生重大变化,影响临床实施.
科学领域:
- 放射学和医学成像学 医学成像学
- 医疗保健中的人工智能
- 在瘤学瘤学.
背景情况:
- 越来越多地使用深度学习模型来预测乳腺癌风险 (BCR).
- 这些模型可能对乳房镜采集的变化敏感.
- 了解这种敏感性对于可靠的临床实施至关重要.
研究的目的:
- 为了研究一个最先进的BCR预测模型对现实的乳房图像改变的敏感性.
- 评估这些改变对个别BCR预测和模型整体性能的影响.
主要方法:
- 从斯洛文尼亚和比利时的查计划中使用了5076张乳房影像.
- 应用各种模拟图像改变 (例如,乳房交换,裁剪,旋转,乳房肌肉去除) 来对MIRAI模型进行BCR估计.
- 使用布兰德-阿尔特曼图表和AUC分析评估了预测偏差,一致性极限 (LOA) 和歧视性能 (AUC).
主要成果:
- 乳房交换和乳腺下折变化的影响最小.
- 翻译,旋转,裁剪和注册导致LOA高达±0.1.1.
- 完全去除胸部肌肉导致了大量的预测偏差和更广泛的LOA.
- 没有任何变化影响了整体歧视性能 (AUC).
结论:
- 乳腺样本图像的改变可能会导致预测乳腺癌风险的显著个体变化.
- 尽管总体歧视稳定,但这些变化可能会影响临床决策.
- 需要进一步的研究,以确保深度学习BCR模型在现实临床环境中的稳定性.
相关概念视频
01:15Receiver Operating Characteristic Plot
66
A ROC (Receiver Operating Characteristic) plot is a graphical tool used to assess the performance of a binary classification model by illustrating the trade-off between sensitivity (true positive rate) and specificity (false positive rate). By plotting sensitivity against 1 - specificity across various threshold settings, the ROC curve shows how well the model distinguishes between classes, with a curve closer to the top-left corner indicating a more accurate model. The area under the ROC curve...
66
01:13Sensitivity, Specificity, and Predicted Value
146
In healthcare diagnostics, laboratory tests play a crucial role in identifying and diagnosing a wide range of medical conditions. However, interpreting test results is not always straightforward. An abnormal test result does not always confirm the presence of a disease, just as a normal result does not guarantee its absence. To assess the reliability of these diagnostic tools, healthcare practitioners rely on two key statistical indicators: sensitivity and specificity.
Sensitivity is the...
Sensitivity is the...
146