Image-based Data Mining to Probe Dosimetric Correlates of Radiation-induced Trismus.
Image-based Data Mining to Probe Dosimetric Correlates of Radiation-induced Trismus.
复制标题
DOI：
10.1016/j.ijrobp.2018.05.054
复制
发表时间：
2018-11-15
期刊：
影响因子：
--
通讯作者：
van Herk M
中科院分区：
文献类型：
--
作者：
Beasley W;Thor M;McWilliam A;Green A;Mackay R;Slevin N;Olsson C;Pettersson N;Finizia C;Estilo C;Riaz N;Lee NY;Deasy JO;van Herk M
使用一种新的基于图像的数据挖掘（IBDM）框架，识别头颈癌放疗（HNRT）后剂量与辐射诱导牙关紧闭相关的成像区域。对86例HNRT患者进行了区域识别分析。牙关紧闭的特点是作为一个连续变量的最大门齿到门齿开口距离（MID）在6个月后RT。患者的解剖结构和剂量分布进行空间归一化到一个共同的参考框架，使用变形图像配准。IBDM用于识别与MID相关的体素簇（基于排列检验，p≤0.05）。结果在35名HNC患者的队列中进行了外部测试。在内部，我们还进行了基于剂量体积直方图（DVH）的分析，通过比较MID和平均剂量（Dmean）的IBDM识别的集群与五个划定的咀嚼结构相比的相关性的大小。用IBDM方法识别出单个簇（p<0.01），与同侧咬肌部分重叠。基于DVH的分析证实，IBDM簇与MID的相关性最强，其次是同侧咬肌和同侧内侧翼肌（斯皮尔曼等级相关系数：Rs=-0.36，-0.35，-0.32; p=0.001，0.001，0.002）。外部验证证实了Dmean与IBDM聚类和MID之间的关联（Rs=-0.45; p=0.007）。IBDM绕过了结构内剂量模式不重要的常见假设。我们的新的IBDM方法连续的结果变量成功地确定了一组体素，是高度相关的牙关紧闭，部分重叠的同侧咬肌。对外部验证队列的测试显示，与牙关紧闭症的相关性更强。这些结果支持在HNRT治疗计划中使用该区域以潜在地减少牙关紧闭。
To identify imaged regions in which dose is associated with radiation-induced trismus after head and neck cancer radiotherapy (HNRT) using a novel image-based data mining (IBDM) framework. A cohort of 86 HNRT patients were analysed for region identification. Trismus was characterised as a continuous variable by the maximum incisor-to-incisor opening distance (MID) at 6 months post-RT. Patient anatomies and dose distributions were spatially normalised to a common frame of reference using deformable image registration. IBDM was used to identify clusters of voxels associated with MID (p≤0.05 based on permutation testing). The result was externally tested on a cohort of 35 HNC patients. Internally, we also performed a dose-volume histogram (DVH)-based analysis by comparing the magnitude of the correlation between MID and the mean dose (Dmean) for the IBDM-identified cluster in comparison with five delineated masticatory structures. A single cluster was identified with the IBDM approach (p<0.01), partially overlapping with the ipsilateral masseter. The DVH-based analysis confirmed that the IBDM cluster had the strongest association with MID, followed by the ipsilateral masseter and the ipsilateral medial pterygoid (Spearman’s rank correlation coefficients: Rs=-0.36, −0.35, −0.32; p=0.001, 0.001, 0.002). External validation confirmed an association between Dmean to the IBDM cluster and MID (Rs=−0.45; p=0.007). IBDM bypasses the common assumption that dose patterns within structures are unimportant. Our novel IBDM approach for continuous outcome variables successfully identified a cluster of voxels that are highly associated with trismus, overlapping partially with the ipsilateral masseter. Tests on an external validation cohort showed an even stronger correlation with trismus. These results support use of the region in HNRT treatment planning to potentially reduce trismus.
登录
查看更多内容
影响因子：
3.5
作者：
Acosta, Oscar;Drean, Gael;de Crevoisier, Renaud
通讯作者：
de Crevoisier, Renaud
DOI：
10.1016/j.ejmp.2016.08.013
发表时间：
2016-12-01
影响因子：
3.4
作者：
Improta, I.;Palorini, F.;Fiorino, C.
通讯作者：
Fiorino, C.
影响因子：
3.5
作者：
Buettner, Florian;Gulliford, Sarah L.;Partridge, Mike
通讯作者：
Partridge, Mike
DOI：
10.3109/0284186x.2015.1037864
发表时间：
2016
期刊：
Acta oncologica (Stockholm, Sweden)
影响因子：
--
作者：
Rao SD;Saleh ZH;Setton J;Tam M;McBride SM;Riaz N;Deasy JO;Lee NY
通讯作者：
Lee NY
DOI：
10.1186/1748-717x-8-293
发表时间：
2013-12-23
期刊：
Radiation oncology (London, England)
影响因子：
--
作者：
Chen C;Witte M;Heemsbergen W;van Herk M
通讯作者：
van Herk M