van Rooij Ward, Verbakel Wilko F, Slotman Berend J, Dahele Max
Department of Radiation Oncology, Amsterdam UMC, Vrije Universiteit Amsterdam, Cancer Center Amsterdam, Amsterdam, The Netherlands.
Adv Radiat Oncol. 2021 Jan 29;6(2):100658. doi: 10.1016/j.adro.2021.100658. eCollection 2021 Mar-Apr.
Contouring organs at risk remains a largely manual task, which is time consuming and prone to variation. Deep learning-based delineation (DLD) shows promise both in terms of quality and speed, but it does not yet perform perfectly. Because of that, manual checking of DLD is still recommended. There are currently no commercial tools to focus attention on the areas of greatest uncertainty within a DLD contour. Therefore, we explore the use of spatial probability maps (SPMs) to help efficiency and reproducibility of DLD checking and correction, using the salivary glands as the paradigm.
A 3-dimensional fully convolutional network was trained with 315/264 parotid/submandibular glands. Subsequently, SPMs were created using Monte Carlo dropout (MCD). The method was boosted by placing a Gaussian distribution (GD) over the model's parameters during sampling (MCD + GD). MCD and MCD + GD were quantitatively compared and the SPMs were visually inspected.
The addition of the GD appears to increase the method's ability to detect uncertainty. In general, this technique demonstrated uncertainty in areas that (1) have lower contrast, (2) are less consistently contoured by clinicians, and (3) deviate from the anatomic norm.
We believe the integration of uncertainty information into contours made using DLD is an important step in highlighting where a contour may be less reliable. We have shown how SPMs are one way to achieve this and how they may be integrated into the online adaptive radiation therapy workflow.
对危及器官进行轮廓勾画在很大程度上仍是一项人工任务，既耗时又容易出现差异。基于深度学习的轮廓描绘（DLD）在质量和速度方面都显示出了前景，但尚未达到完美状态。因此，仍建议对DLD进行人工检查。目前尚无商业工具可将注意力集中在DLD轮廓内最具不确定性的区域。因此，我们以唾液腺为范例，探索使用空间概率图（SPM）来提高DLD检查和校正的效率及可重复性。
使用315个腮腺/264个下颌下腺训练了一个三维全卷积网络。随后，使用蒙特卡洛随机失活（MCD）创建SPM。在采样期间通过在模型参数上放置高斯分布（GD）来增强该方法（MCD + GD）。对MCD和MCD + GD进行了定量比较，并对SPM进行了视觉检查。
添加GD似乎提高了该方法检测不确定性的能力。总体而言，该技术在以下区域显示出不确定性：（1）对比度较低，（2）临床医生轮廓勾画不一致，（3）偏离解剖学标准。
我们认为将不确定性信息整合到使用DLD生成的轮廓中是突出轮廓可能不太可靠之处的重要一步。我们展示了SPM是实现这一目标的一种方法，以及它们如何可以整合到在线自适应放射治疗工作流程中。
