用贝叶斯深度学习估计地理缩细分的不确定性
Theodore Spaide1,2,3, Anand E Rajesh1,2, Nayoon Gim1,2,4
1Department of Ophthalmology, University of Washington, Seattle, Washington.
Ophthalmology science
|October 9, 2024
概括
贝叶斯深度学习模型改善了地理缩 (GA) 分段的准确性,并提供了不确定性估计. 这些方法提高了模型的可靠性,并帮助临床决策在与年龄有关的黄斑变性.
科学领域:
- 眼科医生 眼科 眼科
- 人工智能的人工智能
- 医疗成像医学成像
背景情况:
- 地理缩 (GA) 是与年龄相关的黄斑变性 (AMD) 视力丧失的主要原因.
- 精确的GA病变细分对于监测疾病进展和评估治疗疗效至关重要.
- 深度学习模型显示了自动GA细分的前景,但量化预测不确定性仍然是一个挑战.
研究的目的:
- 应用和评估贝叶斯深度学习技术来量化地理缩 (GA) 的语义细分中的不确定性.
- 为了比较贝叶斯方法 (蒙特卡洛脱落,整体) 与GA细分的传统深度学习模型的性能.
主要方法:
- 从SWAGGER队列中对光学连贯性断层扫描 (SD-OCT) 图像进行了回顾性分析.
- 开发了两个近似的贝叶斯深度学习模型:蒙特卡洛脱和整体方法.
- 使用子得分对模型性能进行比较,并使用Shannon Entropy计算像素智能的不确定性.
主要成果:
- 与传统模型 (0.82) 相比,贝叶斯深度学习模型显示了显著更高的Dice分数 (MC脱落:0.90,ensemble:0.88).
- 这两种贝叶斯方法都产生了更多的具有高的像素数量,这表明不确定性估计较高.
- 这些模型为GA细分提供了基于像素的不确定性估计.
结论:
- 在GA细分中量化预测不确定性提高了临床应用的模型可靠性.
- 贝叶斯深度学习技术提高了细分性能,并提供了有价值的不确定性指标,有助于临床医生的决策.
- 这些先进的方法为分析OCT成像中的GA提供了更强大的方法.
相关概念视频
01:04Random Error
Random or indeterminate errors originate from various uncontrollable variables, such as variations in environmental conditions, instrument imperfections, or the inherent variability of the phenomena being measured. Usually, these errors cannot be predicted, estimated, or characterized because their direction and magnitude often vary in magnitude and direction even during consecutive measurements. As a result, they are difficult to eliminate. However, the aggregate effect of these errors can be...
00:59Uncertainty: Overview
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.
00:54Uncertainty: Confidence Intervals
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 't,' or...
01:19Survival Tree
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a survival tree begins...
Building a Survival Tree
Constructing a survival tree begins...
01:29Application of Linearization and Approximation
A drone flying through complex terrain often relies on more than one sensing method to estimate small changes in altitude. Along with direct measurements, air pressure provides a useful indirect indicator of vertical movement. Atmospheric pressure decreases as altitude increases, and this relationship is commonly described using an exponential model. Although accurate, converting pressure measurements into altitude values requires calculations that are too complex to perform repeatedly during...
01:23Linear Approximations
For a differentiable function of two variables, linear approximation estimates values near a known point by replacing the curved surface with its tangent plane. Consider the function\begin{equation*}f(x,y)=x^2+3y^2\end{equation*}near the point (2, 1). The exact value at this point is f(2, 1) = 22 + 3(1)2 = 4 + 3 = 7.The linear approximation of f(x, y)) near (a, b) is\begin{equation*}L(x,y)=f(a,b)+f_x(a,b)(x-a)+f_y(a,b)(y-b)\end{equation*}First, compute the partial derivatives: fx(x, y) = 2x and...