Virginia Commonwealth University, Department of Radiation Oncology, Richmond, VA, United States of America; Virginia Commonwealth University, Department of Computer Science, Richmond, VA, United States of America; National Radiation Oncology Program, Department of Veteran Affairs, Richmond, VA, United States of America.
Virginia Commonwealth University, Department of Radiation Oncology, Richmond, VA, United States of America; National Radiation Oncology Program, Department of Veteran Affairs, Richmond, VA, United States of America.
J Biomed Inform. 2020 Sep;109:103527. doi: 10.1016/j.jbi.2020.103527. Epub 2020 Aug 8.
To present a Machine Learning pipeline for automatically relabeling anatomical structure sets in the Digital Imaging and Communications in Medicine (DICOM) format to a standard nomenclature that will enable data abstraction for research and quality improvement.
DICOM structure sets from approximately 1200 lung and prostate cancer patients across 40 treatment centers were used to build predictive models to automate the relabeling of clinically specified structure labels to standardized labels as defined by the American Association of Physics in Medicine's (AAPM) Task Group 263 (TG-263). Volumetric bitmaps were created based on the delineated volumes and were combined with associated bony anatomy data to build feature vectors. Feature reduction was performed with singular value decomposition and the resulting vectors were used for predicting the label of each structure using five different classifier algorithms on the Apache Spark platform with 5-fold cross-validation. Undersampling methods were used to deal with underlying class imbalance that hindered the performance of classifiers. Experiments were performed on both a curated version of the data, which included only annotated structures, and the non-curated data that included all structures from the original treatment plans.
Random Forest provided the highest accuracies with F scores of 98.77 for lung and 95.06 for prostate on the curated data sets. Scores were lower with 95.67 for lung and 90.22 for prostate on the non-curated data sets, highlighting some of the challenges of classifying real clinical data. Including bony anatomy data and pooling information from all structures for the same patient both increased accuracies. In some cases, undersampling with k-Means clustering for class balancing improved classifier accuracy but in all experiments it significantly reduced run time compared to random undersampling.
This work shows that structure sets can be relabeled using our approach with accuracies over 95% for many structure types when presented with curated data. Although accuracies dropped when using the full non-curated data sets, some structure types were still correctly labeled over 90% of the time. With similar results obtained on an external test data set, we can infer that the proposed models are likely to work on other clinical data sets.
提出一种机器学习管道，用于将数字成像和通信在医学（DICOM）格式中的解剖结构集自动重新标记为标准命名法，从而为研究和质量改进实现数据抽象。
使用来自 40 个治疗中心的大约 1200 名肺癌和前列腺癌患者的 DICOM 结构集来构建预测模型，以自动将临床指定的结构标签重新标记为美国医学物理学家协会（AAPM）第 263 任务组（TG-263）定义的标准化标签。基于勾画的体积创建体绘制位图，并将其与相关的骨性解剖数据结合起来构建特征向量。使用奇异值分解进行特征降维，并在 Apache Spark 平台上使用五种不同的分类器算法对降维后的特征向量进行 5 折交叉验证，以预测每个结构的标签。使用欠采样方法处理底层的类不平衡问题，这会影响分类器的性能。实验在经过精心整理的数据（仅包含已注释的结构）和非精心整理的数据（包含原始治疗计划中的所有结构）上进行。
随机森林在经过整理的数据上的肺和前列腺的 F 分数分别为 98.77 和 95.06，提供了最高的准确性。在非整理数据上的分数分别为 95.67 和 90.22，这突出了对真实临床数据进行分类的一些挑战。包含骨性解剖数据并汇集同一患者的所有结构信息都提高了准确性。在某些情况下，使用 k-Means 聚类进行类平衡的欠采样提高了分类器的准确性，但在所有实验中，与随机欠采样相比，它显著减少了运行时间。
这项工作表明，当提供经过整理的数据时，使用我们的方法可以将结构集重新标记为超过 95%的准确率，对于许多结构类型。虽然在使用完整的非整理数据集时准确性有所下降，但某些结构类型仍然有超过 90%的时间被正确标记。在外部测试数据集上获得类似的结果后，我们可以推断出所提出的模型可能适用于其他临床数据集。
