Automatic Pelvic Organ Delineation in Prostate Cancer Treatment

前列腺癌治疗中的盆腔器官自动勾画 摘要： 在计划和治疗图像中快速、可靠和准确地描绘盆腔器官是一个长期的挑战， 长期存在的、重要的、技术上具有挑战性的问题。它的解决方案非常需要最先进的 图像引导放射治疗计划和治疗，因为更好的治疗决策依赖于及时的 图像中解剖信息的解释。然而，男性骨盆区域的自动分割 由于1）前列腺和周围器官之间的对比度低，以及2）可能不同， 由组织变形引起的膀胱和直肠的形状/外观。这个项目的目标是创造 一套新颖的机器学习工具，以实现准确，可靠和有效的重要骨盆描绘 器官（例如，前列腺、膀胱和直肠）以不同的方式（例如，计划CT、治疗CT/CBCT， 和MRI）用于前列腺癌的放射治疗。 计划CT。对于自动分割，地标检测通常是快速定位目标的第一步。 靶器官。因此，在目标1中，我们将创建一个新的联合地标检测方法，基于两者 随机森林和自动上下文模型，以迭代地检测所有地标，并进一步协调它们的 用于获得更准确和一致的地标检测结果的检测结果。在大致定位后 第二步是准确分割目标边界 计划CT中的器官。因此，在目标2中，我们将创建一组学习方法，以a）首先 同时预测规划CT中的所有盆腔器官边界，回归森林由 标记的训练数据，以及B）然后通过使它们各自的形状模型变形来联合地分割所有盆腔器官。 特别是，为了解决传统的可变形模型在假设简单高斯分布时的局限性， 分布的器官形状，一种新的层次稀疏形状组成方法将开发， 在可变形分割期间约束形状模型。 治疗CT/CBCT。在连续放射治疗过程中， 输送到患者的累积剂量，治疗图像中的器官也需要被分割。 虽然目标1-2中提出的方法可以简单地应用，正如许多传统方法所做的那样， 将导致a）不一致的标志检测和B）不同治疗中不一致的分割 由于可能的大形状/外观变化。因此，在目标3中，我们将创建一个新的自我- 逐步学习并将患者特定信息纳入两个关节标志的学习机制 检测和可变形的分割步骤。 因此，人口数据将逐渐被患者自身数据所取代，以训练个性化模型。 核磁共振为了在计划CT中引导盆腔器官分割，现在通常采集MRI以用于选择性地分割盆腔器官。 患者为此，在目标4中，我们将开发a）通过使用深度 学习学习MRI特定特征，用于指导界标检测和可变形分割， B）一种新的协作MRI和CT分割算法，用于更准确地 计划CT分割。 我们开发的所有算法都将在临床（治疗计划和 交付）工作流程为130名患者在癌症医院和医院的顾问。 患者护理的好处。这些细分工具的发展将1）大大加快 临床工作流程，2）减少工作量（即，手动交互时间），以及3）更好地 通过对目标区域和关键器官的可靠和准确分割，实现患者结局。虽然这些 工具不能取代医生的专业知识，但它们可以对医生有很大的帮助。

Automatic Pelvic Organ Delineation in Prostate Cancer Treatment Abstract: Fast, reliable and accurate delineation of pelvic organs in the planning and treatment images is a long- standing, important and technically challenging problem. Its solution is highly required for state-of-the-art image-guided radiation therapy planning and treatment, as better treatment decisions rely on timely interpretation of anatomical information in the images. However, automatic segmentation in male pelvic regions is always difficult due to 1) low contrast between prostate and surrounding organs, and 2) possibly disparate shapes/appearances of bladder and rectum caused by tissue deformations. The goal of this project is to create a set of novel machine learning tools to achieve accurate, reliable and efficient delineation of important pelvic organs (e.g., prostate, bladder, and rectum) in different modalities (e.g., planning CT, treatment CT/CBCT, and MRI) for radiotherapy of prostate cancer. Planning CT. For automatic segmentation, landmark detection is often the first step in rapidly locating the target organs. Thus, in Aim 1, we will create a novel joint landmark detection approach, based on both random forests and auto-context model, to iteratively detect all landmarks and further coordinate their detection results for achieving more accurate and consistent landmark detection results. After roughly locating organs with the aid of those detected landmarks, the second step is to accurately segment boundaries of target organs in the planning CT. Accordingly, in Aim 2, we will create a set of learning methods to a) first simultaneously predict all pelvic organ boundaries in the planning CT with the regression forests trained by labeled training data, and b) then segment all pelvic organs jointly by deforming their respective shape models. In particular, to address the limitations of conventional deformable models in assuming simple Gaussian distributions for organ shapes, a novel hierarchical sparse shape composition approach will be developed to constrain shape models during deformable segmentation. Treatment CT/CBCT. During the course of serial radiation treatments, to quantitatively record and monitor the accumulated dose delivered to the patient, organs in the treatment image also need to be segmented. Although methods proposed in Aims 1-2 can be simply applied, as done by many conventional methods, this will lead to a) inconsistent landmark detection and b) inconsistent segmentations across different treatment days because of possible large shape/appearance changes. Accordingly, in Aim 3, we will create a novel self- learning mechanism to gradually learn and incorporate patient-specific information into both joint landmark detection and deformable segmentation steps from the increasingly acquired treatment images of patient. Thus, population data will gradually be replaced by the patient's own data to train personalized models. MRI. To guide pelvic organ segmentation in the planning CT, MRI is now often acquired for selected patients. To this end, in Aim 4, we will develop a) a prostate MRI segmentation method by using deep learning to learn MRI-specific features for guiding landmark detection and deformable segmentation as proposed in Aims 1-2; b) a novel collaborative MRI and CT segmentation algorithm for more accurate segmentation of planning CT. All our developed algorithms will be evaluated for their performance in clinical (treatment planning and delivery) workflow for 130 patients in UNC Cancer Hospital and also hospitals of our consultants. Benefit for Patient Care. Development of these segmentation tools will 1) dramatically accelerate the clinical workflow, 2) reduce workload (i.e., manual interaction time) for physicians, and 3) lead to better patient outcomes with reliable and accurate segmentations of target area and critical organs. Although these tools cannot replace the expertise of physicians, they can be of great assistance to physicians.