解决深度学习模型校准使用证据神经网络和不确定性意识培训
Tareen Dawood1, Emily Chan1, Reza Razavi1
1School of Biomedical Engineering & Imaging Sciences, King's College London, UK.
Proceedings. IEEE International Symposium on Biomedical Imaging
|September 10, 2024
概括
医学成像中的深度学习 (DL) 模型可能过于自信. 结合证据神经网络 (ENN) 和不确定性意识培训,可以改善复杂任务的模型校准,增强临床医生的信任.
科学领域:
- 人工智能的人工智能
- 医疗成像医学成像
- 机器学习 机器学习
背景情况:
- 深度学习 (DL) 模型在医学图像分类中实现了高精度.
- 然而,DL模型的输出,通常使用SoftMax,可能是校准不良 (过度自信).
- 有证据的神经网络 (ENN) 和不确定性意识培训是提出的解决方案.
研究的目的:
- 调查来自不确定性意识培训和ENN的校准改进,单独和组合.
- 在一个简单的MNIST任务和一个复杂的医学成像任务上评估这些方法.
主要方法:
- 在MNIST数字分类上进行了实验.
- 阶段对比心脏磁共振图像用于复杂的文物检测任务.
- 该研究比较了ENN和不确定性意识培训的单个和组合应用.
主要成果:
- 模型校准可能会随着任务复杂度的增加而降低,需要更高容量的模型.
- 结合ENN和不确定性意识培训,在复杂的文物检测任务中改善了低容量和高容量模型的校准.
结论:
- 在复杂的医学成像应用中,ENNs和不确定性意识培训的结合显示出改善DL模型校准的前景.
- 改进的校准可以提高临床医生对DL驱动的医学诊断的信心.
相关概念视频
Uncertainty: Overview
529
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.
529
Propagation of Uncertainty from Systematic Error
490
The atomic mass of an element varies due to the relative ratio of its isotopes. A sample's relative proportion of oxygen isotopes influences its average atomic mass. For instance, if we were to measure the atomic mass of oxygen from a sample, the mass would be a weighted average of the isotopic masses of oxygen in that sample. Since a single sample is not likely to perfectly reflect the true atomic mass of oxygen for all the molecules of oxygen on Earth, the mass we obtain from this...
490
Propagation of Uncertainty from Random Error
656
An experiment often consists of more than a single step. In this case, measurements at each step give rise to uncertainty. Because the measurements occur in successive steps, the uncertainty in one step necessarily contributes to that in the subsequent step. As we perform statistical analysis on these types of experiments, we must learn to account for the propagation of uncertainty from one step to the next. The propagation of uncertainty depends on the type of arithmetic operation performed on...
656
Uncertainty: Confidence Intervals
3.1K
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...
3.1K
Uncertainty in Measurement: Accuracy and Precision
73.5K
Scientists typically make repeated measurements of a quantity to ensure the quality of their findings and to evaluate both the precision and the accuracy of their results. Measurements are said to be precise if they yield very similar results when repeated in the same manner. A measurement is considered accurate if it yields a result that is very close to the true or the accepted value. Precise values agree with each other; accurate values agree with a true value.
73.5K
Calibration Curves: Linear Least Squares
1.3K
A calibration curve is a plot of the instrument's response against a series of known concentrations of a substance. This curve is used to set the instrument response levels, using the substance and its concentrations as standards. Alternatively, or additionally, an equation is fitted to the calibration curve plot and subsequently used to calculate the unknown concentrations of other samples reliably.
For data that follow a straight line, the standard method for fitting is the linear...
For data that follow a straight line, the standard method for fitting is the linear...
1.3K


