Interindividual registration and dose mapping for voxelwise population analysis of rectal toxicity in prostate cancer radiotherapy.

PURPOSE: Recent studies revealed a trend toward voxelwise population analysis in order to understand the local dose/toxicity relationships in prostate cancer radiotherapy. Such approaches require, however, an accurate interindividual mapping of the anatomies and 3D dose distributions toward a common coordinate system. This step is challenging due to the high interindividual variability. In this paper, the authors propose a method designed for interindividual nonrigid registration of the rectum and dose mapping for population analysis. METHODS: The method is based on the computation of a normalized structural description of the rectum using a Laplacian-based model. This description takes advantage of the tubular structure of the rectum and its centerline to be embedded in a nonrigid registration-based scheme. The performances of the method were evaluated on 30 individuals treated for prostate cancer in a leave-one-out cross validation. RESULTS: Performance was measured using classical metrics (Dice score and Hausdorff distance), along with new metrics devised to better assess dose mapping in relation with structural deformation (dose-organ overlap). Considering these scores, the proposed method outperforms intensity-based and distance maps-based registration methods. CONCLUSIONS: The proposed method allows for accurately mapping interindividual 3D dose distributions toward a single anatomical template, opening the way for further voxelwise statistical analysis.

Identification of a rectal subregion highly predictive of rectal bleeding in prostate cancer IMRT.

BACKGROUND AND PURPOSE: To identify rectal subregions at risks (SRR) highly predictive of 3-year rectal bleeding (RB) in prostate cancer IMRT. MATERIALS AND METHODS: Overall, 173 prostate cancer patients treated with IMRT/IGRT were prospectively analyzed, divided into "training" (n=118) and "validation" cohorts (n=53). Dose-volume histograms (DVHs) were calculated in three types of rectal subregions: "geometric", intuitively defined (hemi-rectum,…); "personalized", obtained by non-rigid registration followed by voxel-wise statistical analysis (SRRp); "generic", mapped from SRRps, located within 8×8 rectal subsections (SRRg). DVHs from patients with and without RB were compared and used for toxicity prediction. RESULTS: Training cohort SRRps were primarily within the inferior anterior hemi-rectum and upper anal canal, with 3.8Gy mean dose increase for Grade⩾1 RB patients. The SRRg, representing 15% of the absolute rectal volume, was located in 10 inferior-anterior rectal subsections. V18-V70 for SRRps and V58-V65 for SRRg were significantly higher for RB patients than non-RB. Maximum areas under the curve (AUCs) for SRRp and SRRg RB prediction were 71% and 64%, respectively. The validation cohort confirmed the predictive value of SRRg for Grade⩾1 RB. The total cohort confirmed the predictive value of SRRg for Grade⩾2 RB. Geometrical subregions were not RB predictors. CONCLUSION: The inferior-anterior hemi anorectum was highly predictive of RB.

On feature extraction and classification in prostate cancer radiotherapy using tensor decompositions.

External beam radiotherapy is commonly prescribed for prostate cancer. Although new radiation techniques allow high doses to be delivered to the target, the surrounding healthy organs (rectum and bladder) may suffer from irradiation, which might produce undesirable side-effects. Hence, the understanding of the complex toxicity dose-volume effect relationships is crucial to adapt the treatment, thereby decreasing the risk of toxicity. In this paper, we introduce a novel method to classify patients at risk of presenting rectal bleeding based on a Deterministic Multi-way Analysis (DMA) of three-dimensional planned dose distributions across a population. After a non-rigid spatial alignment of the anatomies applied to the dose distributions, the proposed method seeks for two bases of vectors representing bleeding and non bleeding patients by using the Canonical Polyadic (CP) decomposition of two fourth order arrays of the planned doses. A patient is then classified according to its distance to the subspaces spanned by both bases. A total of 99 patients treated for prostate cancer were used to analyze and test the performance of the proposed approach, named CP-DMA, in a leave-one-out cross validation scheme. Results were compared with supervised (linear discriminant analysis, support vector machine, K-means, K-nearest neighbor) and unsupervised (recent principal component analysis-based algorithm, and multidimensional classification method) approaches based on the registered dose distribution. Moreover, CP-DMA was also compared with the Normal Tissue Complication Probability (NTCP) model. The CP-DMA method allowed rectal bleeding patients to be classified with good specificity and sensitivity values, outperforming the classical approaches.

A Novel Classification Method for Prediction of Rectal Bleeding in Prostate Cancer Radiotherapy Based on a Semi-Nonnegative ICA of 3D Planned Dose Distributions.

The understanding of dose/side-effects relationships in prostate cancer radiotherapy is crucial to define appropriate individual's constraints for the therapy planning. Most of the existing methods to predict side-effects do not fully exploit the rich spatial information conveyed by the three-dimensional planned dose distributions. We propose a new classification method for three-dimensional individuals' doses, based on a new semi-nonnegative ICA algorithm to identify patients at risk of presenting rectal bleeding from a population treated for prostate cancer. The method first determines two bases of vectors from the population data: the two bases span vector subspaces, which characterize patients with and without rectal bleeding, respectively. The classification is then achieved by calculating the distance of a given patient to the two subspaces. The results, obtained on a cohort of 87 patients (at two year follow-up) treated with radiotherapy, showed high performance in terms of sensitivity and specificity.

Segmentation of pelvic structures for planning CT using a geometrical shape model tuned by a multi-scale edge detector.

Accurate segmentation of the prostate and organs at risk in computed tomography (CT) images is a crucial step for radiotherapy planning. Manual segmentation, as performed nowadays, is a time consuming process and prone to errors due to the a high intra- and inter-expert variability. This paper introduces a new automatic method for prostate, rectum and bladder segmentation in planning CT using a geometrical shape model under a Bayesian framework. A set of prior organ shapes are first built by applying principal component analysis to a population of manually delineated CT images. Then, for a given individual, the most similar shape is obtained by mapping a set of multi-scale edge observations to the space of organs with a customized likelihood function. Finally, the selected shape is locally deformed to adjust the edges of each organ. Experiments were performed with real data from a population of 116 patients treated for prostate cancer. The data set was split in training and test groups, with 30 and 86 patients, respectively. Results show that the method produces competitive segmentations w.r.t standard methods (averaged dice = 0.91 for prostate, 0.94 for bladder, 0.89 for rectum) and outperforms the majority-vote multi-atlas approaches (using rigid registration, free-form deformation and the demons algorithm).

Comparison between two treatment planning systems for volumetric modulated arc therapy optimization for prostate cancer.

PURPOSE: To investigate the performances of two commercial treatment planning systems (TPS) for Volumetric Modulated Arc Therapy (VMAT) optimization regarding prostate cancer. The TPS were compared in terms of dose distributions, treatment delivery parameters and quality control results. MATERIALS AND METHODS: For ten patients, two VMAT plans were generated: one with Monaco TPS (Elekta) and one with Pinnacle TPS (Philips Medical Systems). The total prescribed dose was 78 Gy delivered in one 360° arc with a Synergy(®) linear accelerator equipped with a MLCi2(®). RESULTS: VMAT with Monaco provided better homogeneity and conformity indexes but lower mean dose to PTVs than Pinnacle. For the bladder wall (p = 0.019), the femoral heads (p = 0.017), and healthy tissues (p = 0.005), significantly lower mean doses were found using Monaco. For the rectal wall, VMAT with Pinnacle provided a significantly (p = 0.047) lower mean dose, and lower dose into 50% of the volume (p = 0.047) compared to Monaco. Despite a greater number of monitor units (factor 1.5) for Monaco TPS, the total treatment time was equivalent to that of Pinnacle. The treatment delivery parameter analysis showed larger mean MLC area for Pinnacle and lower mean dose rate compared to Monaco. The quality control results gave a high passing rate (>97.4%) for the gamma index for both TPS but Monaco provided slightly better results. CONCLUSION: For prostate cancer patients, VMAT treatment plans obtained with Monaco and Pinnacle offered clinically acceptable dose distributions. Further investigations are in progress to confirm the performances of the two TPS for irradiating more complex volumes.

Voxel-based population analysis for correlating local dose and rectal toxicity in prostate cancer radiotherapy.

The majority of current models utilized for predicting toxicity in prostate cancer radiotherapy are based on dose-volume histograms. One of their main drawbacks is the lack of spatial accuracy, since they consider the organs as a whole volume and thus ignore the heterogeneous intra-organ radio-sensitivity. In this paper, we propose a dose-image-based framework to reveal the relationships between local dose and toxicity. In this approach, the three-dimensional (3D) planned dose distributions across a population are non-rigidly registered into a common coordinate system and compared at a voxel level, therefore enabling the identification of 3D anatomical patterns, which may be responsible for toxicity, at least to some extent. Additionally, different metrics were employed in order to assess the quality of the dose mapping. The value of this approach was demonstrated by prospectively analyzing rectal bleeding (≥Grade 1 at 2 years) according to the CTCAE v3.0 classification in a series of 105 patients receiving 80 Gy to the prostate by intensity modulated radiation therapy (IMRT). Within the patients presenting bleeding, a significant dose excess (6 Gy on average, p < 0.01) was found in a region of the anterior rectal wall. This region, close to the prostate (1 cm), represented less than 10% of the rectum. This promising voxel-wise approach allowed subregions to be defined within the organ that may be involved in toxicity and, as such, must be considered during the inverse IMRT planning step.

A tensor-based population value decomposition to explain rectal toxicity after prostate cancer radiotherapy.

In prostate cancer radiotherapy the association between the dose distribution and the occurrence of undesirable side-effects is yet to be revealed. In this work a method to perform population analysis by comparing the dose distributions is proposed. The method is a tensor-based approach that generalises an existing method for 2D images and allows for the highlighting of over irradiated zones correlated with rectal bleeding after prostate cancer radiotherapy. Thus, the aim is to contribute to the elucidation of the dose patterns correlated with rectal toxicity. The method was applied to a cohort of 63 patients and it was able to build up a dose pattern characterizing the difference between patients presenting rectal bleeding after prostate cancer radiotherapy and those who did not.