Tensor Regression-based Model to Investigate Heterogeneous Spatial Radiosensitivity After I-125 Seed Implantation for Prostate Cancer (original) (raw)
Related papers
in Vivo, 2019
Aim: To develop a population-based statistical model in order to find a spatial pattern of dose distribution which is related to lower urinary tract symptoms (LUTS) after iodine-125 (125 I) seed implantation for prostate cancer. Patients and Methods: A total of 75 patients underwent 125 I seed implantation for prostate cancer. Principal component analysis was applied to the standardized dose array and for each patient dose distribution was uniquely characterized by a combination of weighted eigenvectors. The correlation between eigenvectors and the severity of LUTS was investigated with linear regression analysis. Results: Eight eigenvectors were identified as being significantly associated with the severity of LUTS (p<0.05). Multivariate regression model identified that intraprostatic parameters, which were positively associated with the severity of LUTS, were distributed around a portion of the urethral base and a peripheral region of the prostate. Conclusion: We established a population-based statistical model that may indicate a significant dose pattern associated with the severity of radiation toxicity.
Physics in Medicine and Biology, 2013
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 80Gy to the prostate by IMRT. Within the patients presenting bleeding, a significant dose excess (6Gy on average, p<0.01) was found in a region of the anterior rectal wall. This region, close to the prostate (1cm), 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.
Intensity Modulated Radiotherapy (IMRT) allows delivering of highly conformal dose to complex targets, implying nevertheless the choice of optimal constraints for the organs at risk (OAR) with the aim of reducing toxicity. To estimate the risk of toxicity, current predictive models stand on the dose-volume histograms (DVH) whose main drawback is the lack of spatial accuracy as they consider the organs as a whole volume and thus ignore the heterogeneous intraorgan radio-sensitivity. A framework for finding relationships between local dose and toxicity is proposed here. In this approach, the planned dose distributions are registered together on a common coordinate system and compared across a population at a voxel level, thereby allowing the highlighting of 3D anatomical patterns which may be in part responsible of toxicity. We demonstrated here the value of the approach by explaining rectal toxicity in prostate cancer radiotherapy (PCRT). 116 patients with 31 month median follow-up were considered. They received a total dose of 80 Gy in the prostate by IMRT. When analyzing rectal toxicity, significant difference of dose was found in large regions within the anterior wall close to the prostate (1cm). This promising voxel-wise approach allowed the highlighting of regions that may be involved in rectal toxicity.
Lecture Notes in Computer Science, 2013
HAL is a multidisciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.
International Journal of Radiation Oncology*Biology*Physics, 2019
RdC, EM and OA designed the study. RdC was the principal investigator of the STIC-IGRT trial. SS was the principal investigator of the French cohort belonging to the PROFIT trial. RdC, SS, CL, NM and SC recruited and treated patients. EM, OA, TL , JC and RdC performed the image processing and the statistical analysis. All authors interpreted data, wrote and reviewed the manuscript. Short running tittle Voxel-based analysis predicting urinary toxicity Declaration of interests We declare no competing interests.
On feature extraction and classification in prostate cancer radiotherapy using tensor decompositions
Medical Engineering & Physics, 2015
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.
Radiotherapy and Oncology, 2013
Background and purpose: In radiotherapy (RT) of prostate cancer the key organs at risk (ORs) -the rectum and the bladder -display considerable motion, which may influence the dose/volume parameters predicting for morbidity. In this study we compare motion-inclusive doses to planned doses for the rectum and bladder and explore their associations with prospectively recorded morbidity. Materials and methods: The study included 38 prostate cancer patients treated with hypo-fractionated image-guided intensity-modulated RT that had an average of nine repeat CT scans acquired during treatment. These scans were registered to the respective treatment planning CT (pCT) followed by a new dose calculation from which motion-inclusive dose distributions were derived. The pCT volumes, the treatment course averaged volumes as well as the planned and motion-inclusive doses were associated with acute and late morbidity (morbidity cut-off: PGrade 2). Results: Acute rectal morbidity (observed in 29% of cases) was significantly associated with both smaller treatment course averaged rectal volumes (population median: 75 vs. 94 cm 3 ) and the motion-inclusive volume receiving doses close to the prescription dose (2 Gy-equivalent dose of 76 Gy). Conclusion: Variation in rectum and bladder volumes leads to deviations between planned and delivered dose/volume parameters that should be accounted for to improve the ability to predict morbidity following RT.
La radiologia medica, 2019
Objective To develop different radiomic models based on the magnetic resonance imaging (MRI) radiomic features and machine learning methods to predict early intensity-modulated radiation therapy (IMRT) response, Gleason scores (GS) and prostate cancer (Pca) stages. Methods Thirty-three Pca patients were included. All patients underwent pre-and post-IMRT T2-weighted (T2 W) and apparent diffusing coefficient (ADC) MRI. IMRT response was calculated in terms of changes in the ADC value, and patients were divided as responders and non-responders. A wide range of radiomic features from different feature sets were extracted from all T2 W and ADC images. Univariate radiomic analysis was performed to find highly correlated radiomic features with IMRT response, and a paired t test was used to find significant features between responders and non-responders. To find high predictive radiomic models, tenfold cross-validation as the criterion for feature selection and classification was applied on the pre-, post-and delta IMRT radiomic features, and area under the curve (AUC) of receiver operating characteristics was calculated as model performance value. Results Of 33 patients, 15 patients (45%) were found as responders. Univariate analysis showed 20 highly correlated radiomic features with IMRT response (20 ADC and 20 T2). Two and fifteen T2 and ADC radiomic features were found as significant (P-value ≤ 0.05) features between responders and non-responders, respectively. Several cross-combined predictive radiomic models were obtained, and post-T2 radiomic models were found as high predictive models (AUC 0.632) followed by pre-ADC (AUC 0.626) and pre-T2 (AUC 0.61). For GS prediction, T2 W radiomic models were found as more predictive (mean AUC 0.739) rather than ADC models (mean AUC 0.70), while for stage prediction, ADC models had higher prediction performance (mean AUC 0.675). Conclusions Radiomic models developed by MR image features and machine learning approaches are noninvasive and easy methods for personalized prostate cancer diagnosis and therapy.
Predictive models of toxicity with external radiotherapy for prostate cancer: Clinical issues
Cancer, 2009
The objective of the current study was to analyze the state of the art and present limitations of available predictive clinical models (when available) estimating the risk of genitourinary tract and small bowel complications, erectile dysfunction, and acute and late symptoms of the rectal syndrome caused by prostate cancer external irradiation. An analysis of the literature indicated that very limited attention has been devoted to the development of “integrated,” patient-tailored, user-friendly, and clinically usable tools for the prediction of external beam radiotoxicity. In this article, the authors reported on the multivariate correlation between late genitourinary and gastrointestinal toxicities and clinical/dosimetric risk factors, as well as on the first set of nomograms developed to predict acute and late rectal side effects. At the present state of knowledge, the use of nomograms as predictive instruments of radiotoxicity appears to be particularly attractive for several main reasons. They are “user friendly” and easily developed using the results of multivariate analyses, as they weigh the combined effects of multiple independent factors found to be correlated with the selected clinical endpoint. The integrated evaluation of clinical and dosimetric parameters in the single patient can help to provide a tailored probability of the specific outcome considered. Predicting a high probability of toxicity could avoid unnecessary daily costs for the individual patient in terms of quality of life modification during and after treatment, helping patients in the decision-making process of choosing the best individual, quality of life–related treatment, and clinicians in better tailoring the treatment to patient's characteristics. Cancer 2009;115(13 suppl):3141–9. © 2009 American Cancer Society.
Radiation oncology (London, England), 2018
To estimate the radiobiological parameters of three popular normal tissue complication probability (NTCP) models, which describe the dose-response relations of bladder regarding different acute urinary symptoms during post-prostatectomy radiotherapy (RT). To evaluate the goodness-of-fit and the correlation of those models with those symptoms. Ninety-three consecutive patients treated from 2010 to 2015 with post-prostatectomy image-guided intensity modulated radiotherapy (IMRT) were included in this study. Patient-reported urinary symptoms were collected pre-RT and weekly during treatment using the validated Prostate Cancer Symptom Indices (PCSI). The assessed symptoms were flow, dysuria, urgency, incontinence, frequency and nocturia using a Likert scale of 1 to 4 or 5. For this analysis, an increase by ≥2 levels in a symptom at any time during treatment compared to baseline was considered clinically significant. The dose volume histograms of the bladder were calculated. The Lyman-Ku...