量化肺癌细分中的不确定性,使用应用到混合域数据集的基础模型来量化
Aneesh Rangnekar1, Nishant Nadkarni1, Jue Jiang1
1Department of Medical Physics, Memorial Sloan Kettering Cancer Center, NY, USA.
概括
医学成像的基础模型在肺瘤细分方面显示出前景. 新的指标显示,SMIT提供了更可靠的性能,特别是在分布之外的数据集上,有助于临床部署.
科学领域:
- 医疗成像中的人工智能
- 用于医学图像分析的深度学习
- 自主监督学习用于细分学习.
背景情况:
- 医学图像基础模型可以在最小的微调下对器官和瘤进行细分.
- 目前对分布式 (ID) 数据集的评估并不能保证对分布式 (OOD) 数据进行可靠的概括.
- 在临床环境中评估性能偏移是具有挑战性的,因为来自不同成像协议的OOD数据.
研究的目的:
- 引入计算速度快的指标,用于评估医学图像细分中的基础模型.
- 评估多个自我监督学习 (SSL) 基础模型对肺瘤细分的性能.
- 在不同的数据集中比较模型概括,包括OOD场景.
主要方法:
- 评估了Swin UNETR,SimMIM,iBOT和SMIT基础模型,在CT扫描上为肺瘤细分进行了微调.
- 使用相同架构,预训练和微调数据集的比较模型,仅对SimMIM,iBOT和SMIT进行SSL借口任务的变化.
- 对分布中的肺癌数据集 (LRAD,5Rater) 和分布之外的肺栓塞数据集进行了绩效评估.
主要成果:
- 所有模型在肺癌数据集上都取得了类似的准确性;SMIT显示了最高的F1分数和最低的.
- 在OOD数据集上,SMIT表现优越,瘤错误检测较少 (SimMIM的中位体积占用量为5.67cc,而SimMIM的9.97cc).
- 和体积占用指标为混合域数据集的模型性能提供了更好的洞察力.
结论:
- 基础模型在ID肺癌细分任务中表现相似.
- 史密斯展现了增强的稳定性和可靠性,特别是在OOD数据上,这表明其SSL借口任务的有效性.
- 诸如和体积占用等额外的指标对于在各种临床成像场景中全面评估模型至关重要.
相关概念视频
00:54Uncertainty: Confidence Intervals
10.1K
The confidence interval is the range of values around the mean that contains the true mean. It is expressed as a probability percentage. The interpretation of a 95% confidence interval, for instance, is that the statistician is 95% confident that the true mean falls within the interval. The upper and lower limits of this range are known as confidence limits. The confidence limits for the true mean are estimated from the sample's mean, the standard deviation, and the statistical factor...
10.1K
00:59Uncertainty: Overview
1.5K
In analytical chemistry, we often perform repetitive measurements to detect and minimize inaccuracies caused by both determinate and indeterminate errors. Despite the cares we take, the presence of random errors means that repeated measurements almost never have exactly the same magnitude. The collective difference between these measurements - observed values - and the estimated or expected value is called uncertainty. Uncertainty is conventionally written after the estimated or expected value.
1.5K