Dataset Information

Machine Learning Methods Uncover Radiomorphologic Dose Patterns in Salivary Glands that Predict Xerostomia in Patients with Head and Neck Cancer.

ABSTRACT:

Purpose

Patients with head-and-neck cancer (HNC) may experience xerostomia after radiation therapy (RT), which leads to compromised quality of life. The purpose of this study is to explore how the spatial pattern of radiation dose (radiomorphology) in the major salivary glands influences xerostomia in patients with HNC.

Methods and materials

A data-driven approach using spatially explicit dosimetric predictors, voxel dose (ie, actual radiation dose in voxels in parotid glands [PG] and submandibular glands [SMG]) was used to predict whether patients would develop xerostomia 3 months after RT. Using planned radiation dose data and other nondose covariates including baseline xerostomia grade of 427 patients with HNC in our database, the machine learning methods were used to investigate the influence of dose patterns across subvolumes in PG and SMG on xerostomia.

Results

Of the 3 supervised learning methods studied, ridge logistic regression yielded the best predictive performance. Ridge logistic regression was also preferred to evaluate the influence pattern of highly correlated dose on xerostomia, which showed a discriminative pattern of influence of doses in the PG and SMG on xerostomia. Moreover, the superior-anterior portion of the contralateral PG and medial portion of the ipsilateral PG were determined to be the most influential regions regarding dose effect on xerostomia. The area under the receiver operating characteristic curve from a 10-fold cross-validation was 0.70 ± 0.04.

Conclusions

Radiomorphology, combined with machine learning methods, is able to suggest patterns of dose in PG and SMG that are the most influential on xerostomia. The influence pattern identified by this data-driven approach and machine learning methods may help improve RT treatment planning and reduce xerostomia after treatment.

SUBMITTER: Jiang W

PROVIDER: S-EPMC6460328 | biostudies-literature | 2019 Apr-Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine Learning Methods Uncover Radiomorphologic Dose Patterns in Salivary Glands that Predict Xerostomia in Patients with Head and Neck Cancer.

Jiang Wei W Lakshminarayanan Pranav P Hui Xuan X Han Peijin P Cheng Zhi Z Bowers Michael M Shpitser Ilya I Siddiqui Sauleh S Taylor Russell H RH Quon Harry H McNutt Todd T

Advances in radiation oncology 20181129 2

<h4>Purpose</h4>Patients with head-and-neck cancer (HNC) may experience xerostomia after radiation therapy (RT), which leads to compromised quality of life. The purpose of this study is to explore how the spatial pattern of radiation dose (radiomorphology) in the major salivary glands influences xerostomia in patients with HNC.<h4>Methods and materials</h4>A data-driven approach using spatially explicit dosimetric predictors, voxel dose (ie, actual radiation dose in voxels in parotid glands [PG] ...[more]

PMID: 31011686

Similar Datasets

Project description:To assess whether, in addition to sparing the parotid glands (PGs), xerostomia after chemotherapy plus intensity-modulated radiotherapy (chemo-IMRT) for head-and-neck cancer is affected by reducing the dose to the other salivary glands.In a prospective study, 78 patients with Stage III-IV oropharynx/nasopharynx cancer underwent chemo-IMRT, with the aim of sparing the parts of the bilateral PGs, oral cavity (OC) containing the minor salivary glands, and contralateral submandibular gland (SMG) outside the target (when contralateral level I was not a target). Before therapy and periodically for 24 months, validated patient-reported xerostomia questionnaire (XQ) scores and observer-graded xerostomia scores were recorded. Also, the stimulated and unstimulated saliva was measured selectively from each of the PGs and SMGs. The mean OC doses served as surrogates of minor salivary gland dysfunction. Regression models assessed the XQ and observer-graded xerostomia predictors.Statistically significant predictors of the XQ score on univariate analysis included the OC, PG, and SMG mean doses and the baseline XQ score, time since RT, and both stimulated and unstimulated PG saliva flow rates. Similar factors were statistically significant predictors of observer-graded xerostomia. The OC, PG, and SMG mean doses were moderately intercorrelated (r = 0.47-0.55). On multivariate analyses, after adjusting for the PG and SMG doses, the OC mean dose (p < .0001), interval from RT (p < .0001), and stimulated PG saliva (p < .0025) were significant predictors of the XQ scores and the OC mean dose and time for observer-graded xerostomia. Although scatter plots showed no thresholds, an OC mean dose of <40 Gy and contralateral SMG mean dose of <50 Gy were each associated with low patient-reported and observer-rated xerostomia at almost all post-therapy points.The PG, SMG, and OC mean doses were significant predictors of both patient-reported and observer-rated xerostomia after chemo-IMRT, with OC doses remaining significant after adjusting for the PG and SMG doses. These results support efforts to spare all the salivary glands by IMRT, beyond the PGs alone.

Project description:PurposeTo analyze baseline CT/MR-based image features of salivary glands to predict radiation-induced xerostomia 3-months after head-and-neck cancer (HNC) radiotherapy.MethodsA retrospective analysis was performed on 266 HNC patients who were treated using radiotherapy at our institution between 2009 and 2018. CT and T1 post-contrast MR images along with NCI-CTCAE xerostomia grade (3-month follow-up) were prospectively collected at our institution. CT and MR images were registered on which parotid/submandibular glands were contoured. Image features were extracted for ipsilateral/contralateral parotid and submandibular glands relative to the location of the primary tumor. Dose-volume-histogram (DVH) parameters were also acquired. Features were pre-selected based on Spearman correlation before modelling by examining the correlation with xerostomia (p?<?0.05). A shrinkage regression analysis of the pre-selected features was performed using LASSO. The internal validity of the variable selection was estimated by repeating the entire variable selection procedure using a leave-one-out-cross-validation. The most frequently selected variables were considered in the final model. A generalized linear regression with repeated ten-fold cross-validation was developed to predict radiation-induced xerostomia at 3-months after radiotherapy. This model was tested in an independent dataset (n?=?50) of patients who were treated at the same institution in 2017-2018. We compared the prediction performances under eight conditions (DVH-only, CT-only, MR-only, CT?+?MR, DVH?+?CT, DVH?+?CT?+?MR, Clinical+CT?+?MR, and Clinical+DVH?+?CT?+?MR) using the area under the receiver operating characteristic curve (ROC-AUC).ResultsAmong extracted features, 7 CT, 5 MR, and 2 DVH features were selected. The internal cohort (n?=?216) ROC-AUC values for DVH, CT, MR, and Clinical+DVH?+?CT?+?MR features were 0.73?±?0.01, 0.69?±?0.01, 0.70?±?0.01, and 0.79?±?0.01, respectively. The validation cohort (n?=?50) ROC-AUC values for DVH, CT, MR, and Clinical+DVH?+?CT?+?MR features were 0.63, 0.57, 0.66, and 0.68, respectively. The DVH-ROC was not significantly different than the CT-ROC (p?=?0.8) or MR-ROC (p?=?0.4). However, the CT?+?MR-ROC was significantly different than the CT-ROC (p?=?0.03), but not the Clinical+DVH?+?CT?+?MR model (p?=?0.5).ConclusionOur results suggest that baseline CT and MR image features may reflect baseline salivary gland function and potential risk for radiation injury. The integration of baseline image features into prediction models has the potential to improve xerostomia risk stratification with the ultimate goal of truly personalized HNC radiotherapy.

Project description:PurposeTo determine whether serial cone beam computed tomography (CBCT) images taken during head and neck radiation therapy (HNR) can improve chronic xerostomia prediction.Methods and materialsIn a retrospective analysis, parotid glands (PGs) were delineated on daily kV CBCT images using deformable image registration for 119 HNR patients (60 or 70 Gy in 2 Gy fractions over 6 or 7 weeks). Deformable image registration accuracy for a subset of deformed contours was quantified using the Dice similarity coefficient and mean distance to agreement in comparison with manually drawn contours. Average weekly changes in CBCT-measured mean Hounsfield unit intensity and volume were calculated for each PG relative to week 1. Dose-volume histogram statistics were extracted from each plan, and interactions among dose, volume, and intensity were investigated. Univariable analysis and penalized logistic regression were used to analyze association with observer-rated xerostomia at 1 year after HNR. Models including CBCT delta imaging features were compared with clinical and dose-volume histogram-only models using area under the receiver operating characteristic curve (AUC) for grade ≥1 and grade ≥2 xerostomia prediction.ResultsAll patients experienced end-treatment PG volume reduction with mean (range) ipsilateral and contralateral PG shrinkage of 19.6% (0.9%-58.4%) and 17.7% (4.4%-56.3%), respectively. Midtreatment volume change was highly correlated with mean PG dose (r = -0.318, P < 1e-6). Incidence of grade ≥1 and grade ≥2 xerostomia was 65% and 16%, respectively. For grade ≥1 xerostomia prediction, the delta-imaging model had an AUC of 0.719 (95% confidence interval [CI], 0.603-0.830), compared with 0.709 (95% CI, 0.603-0.815) for the dose/clinical model. For grade ≥2 xerostomia prediction, the dose/clinical model had an AUC of 0.692 (95% CI, 0.615-0.770), and the addition of contralateral PG changes modestly improved predictive performance, with an AUC of 0.776 (0.643-0.912).ConclusionsThe rate of CBCT-measured PG image feature changes improves prediction over dose alone for chronic xerostomia prediction. Analysis of CBCT images acquired for treatment positioning may provide an inexpensive monitoring system to support toxicity-reducing adaptive radiation therapy.

Project description:PurposeRadiation-induced xerostomia is one of the most prevalent symptoms during and after head and neck cancer radiation therapy (RT). We aimed to discover the spatial radiation dose-based (voxel dose) importance pattern in the major salivary glands in relation to the recovery of xerostomia 18 months after RT, and to compare the recovery voxel dose importance pattern to the acute incidence (injury) pattern.Methods and materialsThis study included all patients within our database with xerostomia outcomes after completion of curative intensity modulated RT. Common Terminology Criteria for Adverse Events xerostomia grade was used to define recovered versus nonrecovered group at baseline, between end of treatment and 18 months post-RT, and beyond 18 months, respectively. Ridge logistic regression was performed to predict the probability of xerostomia recovery. Voxel doses within geometrically defined parotid glands (PG) and submandibular glands (SMG), demographic characteristics, and clinical factors were included in the algorithm. We plotted the normalized learned weights on the 3-dimensional PG and SMG structures to visualize the voxel dose importance for predicting xerostomia recovery.ResultsA total of 146 head and neck cancer patients from 2008 to 2016 were identified. The superior region of the ipsilateral and contralateral PG was the most influencial for xerostomia recovery. The area under the receiver operating characteristic curve evaluated using 10-fold cross-validation for ridge logistic regression was 0.68 ± 0.07. Compared with injury, the recovery voxel dose importance pattern was more symmetrical and was influenced by lower dose voxels.ConclusionsThe superior portion of the 2 PGs (low dose region) are the most influential on xerostomia recovery and seem to be equal in their contribution. The dissimilarity of the influence pattern between injury and recovery suggests different underlying mechanisms. The importance pattern identified by spatial radiation dose and machine learning methods can improve our understanding of normal tissue toxicities in RT. Further external validation is warranted.

Project description:AimData from a local quality registry are used to model the risk of late xerostomia after radiotherapy for head and neck cancer (HNC), based on dosimetric- and clinical variables. Strengths and weaknesses of using quality registry data are explored.MethodsHNC patients treated with radiotherapy at the Karolinska University hospital are entered into a quality registry at routine follow up, recording morbidity according to a modified RTOG/LENT-SOMA scale. Other recorded parameters are performance status, age, gender, tumor location, tumor stage, smoking status, chemotherapy and radiotherapy data, including prescribed dose and organ-at-risk (OAR) dose. Most patients are entered at several time points, but at variable times after treatment. Xerostomia was modeled based on follow-up data from January 2014 to October 2018, resulting in 753 patients. Two endpoints were considered: maximum grade ≥2 (XERG≥2) or grade ≥3 (XERG≥3) late xerostomia. Univariate Cox regression was used to select variables for two multivariate models for each endpoint, one based on the mean dose to the total parotid volume (Dtot) and one based on the mean dose to the contralateral parotid (Dcontra). Cox regression allows the estimation of the risk of xerostomia at different time points; models were presented visually as nomograms estimating the risk at 9, 12, and 24 months respectively.ResultsThe toxicity rates were 366/753 (49%) for XERG≥2 and 40/753 (5.3%) for XERG≥3. The multivariate models included several variables for XERG≥2, and dose, concomitant chemotherapy and age were included for XERG≥3. Induction chemotherapy and an increased number of fractions per week were associated with a lower risk of XERG≥2. However, since the causality of these relationships have limited support from previous studies, alternative models without these variables were also presented. The models based on the mean dose to the total parotid volume and the contralateral parotid alone were very similar.ConclusionLate xerostomia after radiotherapy can be modeled with reasonable predictive power based on registry data; models are presented for different endpoints highly relevant in clinical practice. However, the risk of modeling indirect relationships, given the unavoidably heterogeneous registry data, needs to be carefully considered in the interpretation of the results.

Dataset Information

Machine Learning Methods Uncover Radiomorphologic Dose Patterns in Salivary Glands that Predict Xerostomia in Patients with Head and Neck Cancer.

Purpose

Methods and materials

Results

Conclusions

Publications

Machine Learning Methods Uncover Radiomorphologic Dose Patterns in Salivary Glands that Predict Xerostomia in Patients with Head and Neck Cancer.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets