Dose coverage calculation using a statistical shape model—applied to cervical cancer radiotherapy

Abstract

A comprehensive methodology for treatment simulation and evaluation of dose coverage probabilities is presented where a population based statistical shape model (SSM) provide samples of fraction specific patient geometry deformations. The learning data consists of vector fields from deformable image registration of repeated imaging giving intra-patient deformations which are mapped to an average patient serving as a common frame of reference. The SSM is created by extracting the most dominating eigenmodes through principal component analysis of the deformations from all patients. The sampling of a deformation is thus reduced to sampling weights for enough of the most dominating eigenmodes that describe the deformations. For the cervical cancer patient datasets in this work, we found seven eigenmodes to be sufficient to capture 90% of the variance in the deformations of the, and only three eigenmodes for stability in the simulated dose coverage probabilities. The normality assumption of the eigenmode weights was tested and found relevant for the 20 most dominating eigenmodes except for the first. Individualization of the SSM is demonstrated to be improved using two deformation samples from a new patient. The probabilistic evaluation provided additional information about the trade-offs compared to the conventional single dataset treatment planning.

Statistical Shape Model to Generate a Planning Library for Cervical Adaptive Radiotherapy

“…Landmark positioning appears, however, difficult on pelvic anatomy, and a numerical phantom could have been used as reported when considering prostate cancer [39]. The ICE were larger than the ones reported in the literature using symmetric registration methods [12,20] due to the fact that our method computes the DVF in only one direction (i.e., forward). Still, the proposed method provides the smallest reported ICE of the non-symmetrical registration method [20] (cf.…”

“…This registration step is challenging due to the large intra-patient and all the more inter-patient variations. To our knowledge, only one study analyzed both intra and inter-patient deformations of the cervixuterus anatomy in the context of EBRT [12]. Based on CT images, the proposed approach used deformable registration and principal component analysis (PCA) to quantify the delivered dose uncertainties.…”

“…Recent studies used the ability of the model to generate random or systematic deformations prior to the treatment according to the training set observation. For example, random treatment planning scenarios have been generated to assess the dose coverage probability in cervical cancer [12]. The patientspecific per-treatment bladder deformations have been predicted in a prostate cancer population [14].…”

Probabilistic optimization of dose coverage in radiotherapy

“…The shape and position of the patient anatomy was described by a statistical shape model (SSM) where the parameters are sampled from the probability density function of a random vector y [12]. The SSM was derived through principal component analysis (PCA) of deformable image registration results of images acquired at different fractions during the radiotherapy.…”

“…The algorithm satisfies a target PD constraint while minimizing the expectation value of the organ at risk (OAR) objective functions. To test the feasibility of this methodology, we applied it to radiotherapy planning of cervical cancer patients for which systematic geometrical uncertainties were modelled by a deformation model [12]. The resulting probabilistic treatment plans were evaluated versus margin based plans satisfying the same target PD.…”