Predicting adenocarcinoma recurrence using computational texture models of nodule components in lung CT
Predicting adenocarcinoma recurrence using computational texture models of nodule components in lung CT
复制标题
DOI：
10.1118/1.4916088
复制
发表时间：
2015-04-01
期刊：
影响因子：
3.8
通讯作者：
Rubin, Daniel L.
中科院分区：
文献类型：
--
作者：
Depeursinge, Adrien;Yanagawa, Masahiro;Rubin, Daniel L.
目的：探讨术前计算机断层扫描 (CT) 强度以及磨玻璃样混浊 (GGO) 和实性结节成分的纹理信息对于预测腺癌复发的重要性。方法：在本研究中，选择了 101 例手术切除的 I 期腺癌患者。在随访期间，17 名患者出现疾病复发，其中 6 名患者因癌症相关死亡。放射科医生在术前 CT 扫描中勾画出 GGO 和实体瘤成分。 GGO 和实体区域的计算纹理模型是使用线性支持向量机 (SVM) 学习的可操纵 Riesz 小波的线性组合来构建的。与其他传统纹理属性不同，所提出的纹理模型旨在编码特定于 GGO 和实体组织的局部图像尺度和方向。局部引导模型的响应被用作纹理属性，并与未对齐的 Riesz 小波的响应进行比较。将纹理属性与 CT 强度相结合，根据无病生存 (DFS) 时间预测肿瘤复发和患者风险。比较了两个预测模型家族：LASSO 和 SVM，以及它们的生存对应模型：Cox-LASSO 和生存 SVM。结果：表现最佳的患者危险预测模型与 0.81 +/- 0.02 的一致性指数 (C 指数) 相关，并且基于引导模型和 CT 强度与生存 SVM 的组合。相同的特征组和 LASSO 模型在预测肿瘤复发方面产生了最高的受试者工作特征曲线 (AUC) 下面积 (AUC)，为 0.8 +/- 0.01，尽管与单独使用强度特征相比没有发现统计学上的显着差异。对于所有模型，当图像属性仅基于实体成分时，与使用整个肿瘤相比，性能显着更高 (p < 3.08 x 10(-5))。结论：这项研究提出了如何解释 CT 检查的成像信息的新视角，表明大多数与腺癌侵袭性相关的信息与肿瘤实体成分的强度和形态特性有关。发现腺癌复发的预测特异性较低，但敏感性非常高。我们的结果可用于临床实践，仅使用术前 CT 扫描即可以非常高的置信度识别预计不会复发的患者。它还提供了手术切除给定持续时间 t 后复发风险的准确估计（即 C 指数 = 0.81 +/- 0.02）。 (C) 2015 年美国医学物理学家协会。
Purpose: To investigate the importance of presurgical computed tomography (CT) intensity and texture information from ground-glass opacities (GGO) and solid nodule components for the prediction of adenocarcinoma recurrence.Methods: For this study, 101 patients with surgically resected stage I adenocarcinoma were selected. During the follow-up period, 17 patients had disease recurrence with six associated cancer-related deaths. GGO and solid tumor components were delineated on presurgical CT scans by a radiologist. Computational texture models of GGO and solid regions were built using linear combinations of steerable Riesz wavelets learned with linear support vector machines (SVMs). Unlike other traditional texture attributes, the proposed texture models are designed to encode local image scales and directions that are specific to GGO and solid tissue. The responses of the locally steered models were used as texture attributes and compared to the responses of unaligned Riesz wavelets. The texture attributes were combined with CT intensities to predict tumor recurrence and patient hazard according to disease-free survival (DFS) time. Two families of predictive models were compared: LASSO and SVMs, and their survival counterparts: Cox-LASSO and survival SVMs.Results: The best-performing predictive model of patient hazard was associated with a concordance index (C-index) of 0.81 +/- 0.02 and was based on the combination of the steered models and CT intensities with survival SVMs. The same feature group and the LASSO model yielded the highest area under the receiver operating characteristic curve (AUC) of 0.8 +/- 0.01 for predicting tumor recurrence, although no statistically significant difference was found when compared to using intensity features solely. For all models, the performance was found to be significantly higher when image attributes were based on the solid components solely versus using the entire tumors (p < 3.08 x 10(-5)).Conclusions: This study constitutes a novel perspective on how to interpret imaging information from CT examinations by suggesting that most of the information related to adenocarcinoma aggressiveness is related to the intensity and morphological properties of solid components of the tumor. The prediction of adenocarcinoma relapse was found to have low specificity but very high sensitivity. Our results could be useful in clinical practice to identify patients for which no recurrence is expected with a very high confidence using a presurgical CT scan only. It also provided an accurate estimation of the risk of recurrence after a given duration t from surgical resection (i.e., C-index = 0.81 +/- 0.02). (C) 2015 American Association of Physicists in Medicine.