Investigating rectal toxicity associated dosimetric features with deformable accumulated rectal surface dose maps for cervical cancer radiotherapy

Abstract

BackgroundBetter knowledge of the dose-toxicity relationship is essential for safe dose escalation to improve local control in cervical cancer radiotherapy. The conventional dose-toxicity model is based on the dose volume histogram, which is the parameter lacking spatial dose information. To overcome this limit, we explore a comprehensive rectal dose-toxicity model based on both dose volume histogram and dose map features for accurate radiation toxicity prediction.MethodsForty-two cervical cancer patients treated with combined external beam radiotherapy (EBRT) and brachytherapy (BT) were retrospectively studied, including 12 with Grade ≥ 2 rectum toxicity and 30 patients with Grade 0–1 toxicity (non-toxicity patients). The cumulative equivalent 2-Gy rectal surface dose was deformably summed using the deformation vector fields obtained through a recent developed local topology preserved non-rigid point matching algorithm. The cumulative three-dimensional (3D) dose was flattened and mapped to a two-dimensional (2D) plane to obtain the rectum surface dose map (RSDM). The dose volume parameters (DVPs) were calculated from the 3D rectum surface, while the texture features and the dose geometric parameters (DGPs) were extracted from the 2D RSDM. Representative features further computed from DVPs, textures and DGPs by principle component analysis (PCA) and statistical analysis were respectively fed into a support vector machine equipped with a sequential feature selection procedure. The predictive powers of the representative features were compared with the GEC-ESTRO dosimetric parameters D0.1/1/2cm3.ResultsSatisfactory predictive accuracy of sensitivity 74.75 and 84.75%, specificity 72.67 and 79.87%, and area under the receiver operating characteristic curve (AUC) 0.82 and 0.91 were respectively achieved by the PCA features and statistical significant features, which were superior to the D0.1/1/2cm3 (AUC 0.71). The relative area in dose levels of 64Gy, 67Gy, 68Gy, 87Gy, 88Gy and 89Gy, perimeters in dose levels of 89Gy, as well as two texture features were ranked as the important factors that were closely correlated with rectal toxicity.ConclusionsOur extensive experimental results have demonstrated the feasibility of the proposed scheme. A future large patient cohort study is still needed for model validation.Electronic supplementary materialThe online version of this article (10.1186/s13014-018-1068-0) contains supplementary material, which is available to authorized users.

Assessing localized dosimetric effects due to unplanned gas cavities during pelvic MR‐guided radiotherapy using Monte Carlo simulations

“…In light of this, further work should be done to understand the spatial rectal dose-volume toxicity relationship, for the safe implementation of pelvic MRgRT. 31,33,34 Our results suggest that localized volumes of the rectal wall, in the path of a single beam, could exceed acceptable dose-volume criteria for a single fraction when unplanned air cavities occur. However, with no fully validated model defining the link between rectal dose and late toxicity, the clinical implications of hotspots in the rectal wall exceeding current rectal dose constraints during MRgRT cannot be defined here.…”

“…Therefore, DVH parameters may not be the most appropriate means to assess the implications of dosimetric changes caused by unplanned gas during MRgRT in the clinic. In light of this, further work should be done to understand the spatial rectal dose‐volume toxicity relationship, for the safe implementation of pelvic MRgRT …”

“…29 The rectal dose-volume toxicity relationship is not fully understood. Although delivering [30][31][32][33][34][35][36][37][38][39][40] Gy to the rectum is generally accepted to be safe during EBRT, doses in the region of 100 Gy are commonly seen in the rectum during prostate brachytherapy, indicating that we do not fully understand the doses that the rectal wall can tolerate on small volumes. 27,30 Furthermore, there is nothing to suggest that volumes smaller than 1 cc, that would not be revealed by DVH parameters, do not influence the risk of rectal toxicity.…”

Rectum Protection by Rectal Gel Injection in Cervical Cancer Brachytherapy: A Dosimetric Study via Deformable Surface Dose Accumulation and Machine-Learning-Based Discriminative Modeling

“…The 3D-RD was flattened and mapped onto a twodimensional plane to obtain the 2D-RSDM via a mapping procedure detailed in a previous study (25). The RSDMs had a fixed image resolution (1mm × 1mm) but patient-specific image sizes (Figure 2) depending on the rectum circumference on each CT slice and the inferior-superior rectum length.…”

Machine Learning-Based Models for Prediction of Toxicity Outcomes in Radiotherapy

“…One study by Chen et al (14) investigated the relationship between rectal toxicity (CTCAE grade ≥2) and dosimetric features. In detail, the feature calculation was performed on both the 3D rectum surface and the 2D deformed accumulated rectal surface dose map.…”