Department of Electrical and Computer Engineering, Polytechnic Institute of New York University, Brooklyn, New York 11201, USA.
Med Phys. 2010 Oct;37(10):5341-50. doi: 10.1118/1.3483264.
NYU 05-181 protocol compared the CT simulation in both supine and prone positions for 400 patients with breast cancer (200 left-breast and 200 right-breast) to identify which setup is better at sparing heart and lung involvement in the treatment process. The results demonstrated that all right-breast patients benefited from the prone treatment position, while for left-breast patients, 85% were better treated prone and 15% were better treated supine. Using the clinical data collected from this protocol, the authors aimed at developing an automated tool capable of identifying which of the left-breast cancer patients are better treated supine without obtaining a second CT scan in the supine position.
Prone CT scans from 198 of the 200 left-breast cancer patients enrolled in NYU 05-181 protocol were deidentified and exported to a dedicated research planning workstation. Three-dimensional geometric features of the organs at risk and tumor bed were extracted. A two-stage classifier was used to classify patients into the prone class or the supine class. In the first stage, the authors use simple thresholding to divide the patients into two groups based on their in-field heart volume. For patients with in-field heart volume < or = 0.1 cc, the prone position was chosen as the preferred treatment position. Patients with in-field heart volume > 0.1 cc will be further classified in the second stage by a weighted support vector machine (SVM). The weight parameters of the SVM were adjusted to maximize the specificity [true-supine/(true-supine+false-prone)] at the cost of lowering but still maintaining reasonable sensitivity [true-prone/(true-prone+false-supine)]. The authors used K-fold cross validations to test the performance of the SVM classifier. A feature selection algorithm was also used to identify features that give the best classification performance.
After the first stage, 49 of the 198 left-breast cancer patients were found to have > 0.1 cc of in-field heart volume. The three geometric features of heart orientation, distance between heart and tumor, and in-field lung were selected by the feature selection algorithm in the second stage of the two-stage classifier to give the best predefined weighted accuracy. The overall sensitivity and specificity of the proposed method were found to be 90.4% and 99.3%, respectively. Using two-stage classification, the authors reduced the proportion of prone-treated patients that need a second supine CT scan down to 16.3/170 or 9.6%, as compared to 21/170 or 12.4% when the authors use only the first stage (thresholding) for classification.
The authors' study showed that a feature-based classifier is feasible for predicting the preferred treatment position, based on features extracted from prone CT scans. The two-stage classifier achieved very high specificity at an acceptable expense of sensitivity.
NYU 05-181 方案比较了 400 例乳腺癌患者（左乳 200 例，右乳 200 例）的仰卧位和俯卧位 CT 模拟，以确定哪种体位在治疗过程中更能避免心脏和肺部受累。结果表明，所有右乳患者均受益于俯卧位治疗，而对于左乳患者，85%的患者俯卧位治疗效果更好，15%的患者仰卧位治疗效果更好。作者利用该方案收集的临床数据，旨在开发一种自动化工具，能够在不进行仰卧位第二次 CT 扫描的情况下识别哪些左乳腺癌患者更适合仰卧位治疗。
将 NYU 05-181 方案中 200 例左乳腺癌患者中的 198 例俯卧位 CT 扫描图像进行去标识化处理，并导出到专用研究规划工作站。提取危及器官和肿瘤床的三维几何特征。使用两阶段分类器将患者分为俯卧位组或仰卧位组。在第一阶段，作者使用简单的阈值将患者分为两组，根据其场内心脏体积。场内心脏体积≤0.1cc 的患者选择俯卧位作为首选治疗体位。场内心脏体积>0.1cc 的患者将在第二阶段通过加权支持向量机（SVM）进一步分类。调整 SVM 的权重参数，以在降低但仍保持合理灵敏度[真俯卧位/（真俯卧位+假仰卧位）]的情况下最大化特异性[真仰卧位/（真仰卧位+假俯卧位）]。作者使用 K 折交叉验证来测试 SVM 分类器的性能。还使用特征选择算法来识别给出最佳分类性能的特征。
第一阶段后，发现 198 例左乳腺癌患者中有 49 例的场内心脏体积>0.1cc。在第二阶段的两阶段分类器中，心脏方向、心脏与肿瘤之间的距离和场内肺的三个几何特征通过特征选择算法被选中，以获得最佳的预定义加权准确性。所提出方法的总体敏感性和特异性分别为 90.4%和 99.3%。使用两阶段分类，与仅使用第一阶段（阈值）进行分类时的 21/170 或 12.4%相比，需要进行第二次仰卧位 CT 扫描的俯卧位治疗患者比例降低到 16.3/170 或 9.6%。
作者的研究表明，基于从俯卧位 CT 扫描中提取的特征，基于特征的分类器可用于预测首选治疗体位。两阶段分类器在可接受的灵敏度代价下实现了非常高的特异性。
