Mövik Louise, Bäck Anna, Gunnarsson Kerstin, Gustafsson Christian Jamtheim, Hallqvist Andreas, Pettersson Niclas
Medical Radiation Sciences, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden.
Therapeutic Radiation Physics, Department of Medical Physics and Biomedical Engineering, Sahlgrenska University Hospital, Gothenburg, Sweden.
J Appl Clin Med Phys. 2025 Jul;26(7):e70152. doi: 10.1002/acm2.70152.
Preparing retrospective dose data for risk modeling using large study cohorts can be time consuming as it often requires patient-wise manual interventions. This is especially the case when considering organs at risk (OARs) not systematically delineated historically. Therefore, we aimed to develop and test a semi-automated workflow for cohort-wise preparation of radiotherapy data from the oncology information system (OIS), including OAR autosegmentation, for risk modeling purposes.
A semi-automated workflow, including cohort-wise data extraction from a clinical OIS, cleanup, autosegmentation, quality controls (QCs), and data injection into a research OIS was iteratively developed using 106 patient cases. We evaluated two deep learning (DL)-based methods and compared with four atlas-based methods for autosegmentation of the proximal bronchial tree (PBT), the heart, and the esophagus that were possible to integrate into the workflow. One method was an in-house DL-based model using OARs manually contoured by experts for 100 cases. Geometric and dosimetric agreements with manually contoured OARs were evaluated for 20 independent cases. The final workflow was tested on 50 independent cases.
The DL-based methods were better than the atlas-based at segmenting the PBT (mean Dice similarity coefficient (DSC) 0.81-0.83 versus 0.59-0.80) and the esophagus (mean DSC 0.76-0.77 versus 0.39-0.46). The methods performed similarly for the heart (mean DSC 0.90-0.95 (DL-based) and 0.84-0.90 (atlas-based)). Our in-house autosegmentation model had the highest mean DSC for all OARs. The final version of the workflow successfully prepared data for 80% of the test cases without case-specific manual interventions.
The semi-automated workflow enabled efficient cohort-wise preparation of OIS data for risk modeling purposes. Our in-house DL-based segmentation model outperformed the other methods.
利用大型研究队列准备用于风险建模的回顾性剂量数据可能很耗时，因为这通常需要逐患者进行人工干预。在考虑历史上未系统勾画的危及器官（OAR）时尤其如此。因此，我们旨在开发并测试一种半自动工作流程，用于从肿瘤学信息系统（OIS）中按队列准备放疗数据，包括OAR自动分割，以用于风险建模。
使用106例患者病例迭代开发了一种半自动工作流程，包括从临床OIS中按队列提取数据、清理、自动分割、质量控制（QC）以及将数据注入研究OIS。我们评估了两种基于深度学习（DL）的方法，并与四种基于图谱的方法进行比较，以对近端支气管树（PBT）、心脏和食管进行自动分割，这些器官可以整合到工作流程中。一种方法是基于内部DL的模型，使用专家手动勾画轮廓得到的100例病例的OAR数据。对20例独立病例评估了与手动勾画轮廓的OAR的几何和剂量学一致性。最终工作流程在50例独立病例上进行了测试。
在分割PBT（平均骰子相似系数（DSC）0.81 - 0.83对0.59 - 0.80）和食管（平均DSC 0.76 - 0.77对0.39 - 0.46）方面，基于DL的方法优于基于图谱的方法。在分割心脏方面，两种方法表现相似（平均DSC 0.90 - 0.95（基于DL）和0.84 - 0.90（基于图谱））。我们的内部自动分割模型对所有OAR的平均DSC最高。工作流程的最终版本在无需针对特定病例进行人工干预的情况下，成功为80%的测试病例准备了数据。
半自动工作流程能够高效地按队列准备用于风险建模的OIS数据。我们基于内部DL的分割模型优于其他方法。
