Parotid gland shrinkage during IMRT predicts the time to Xerostomia resolution

Multi-organ spatial stratification of 3-D dose distributions improves risk prediction of long-term self-reported severe symptoms in oropharyngeal cancer patients receiving radiotherapy: development of a pre-treatment decision support tool

Purpose

Identify Oropharyngeal cancer (OPC) patients at high-risk of developing long-term severe radiation-associated symptoms using dose volume histograms for organs-at-risk, via unsupervised clustering.

Material and methods

All patients were treated using radiation therapy for OPC. Dose-volume histograms of organs-at-risk were extracted from patients' treatment plans. Symptom ratings were collected via the MD Anderson Symptom Inventory (MDASI) given weekly during, and 6 months post-treatment. Drymouth, trouble swallowing, mucus, and vocal dysfunction were selected for analysis in this study. Patient stratifications were obtained by applying Bayesian Mixture Models with three components to patient's dose histograms for relevant organs. The clusters with the highest total mean doses were translated into dose thresholds using rule mining. Patient stratifications were compared against Tumor staging information using multivariate likelihood ratio tests. Model performance for prediction of moderate/severe symptoms at 6 months was compared against normal tissue complication probability (NTCP) models using cross-validation.

Results

A total of 349 patients were included for long-term symptom prediction. High-risk clusters were significantly correlated with outcomes for severe late drymouth (p <.0001, OR = 2.94), swallow (p = .002, OR = 5.13), mucus (p = .001, OR = 3.18), and voice (p = .009, OR = 8.99). Simplified clusters were also correlated with late severe symptoms for drymouth (p <.001, OR = 2.77), swallow (p = .01, OR = 3.63), mucus (p = .01, OR = 2.37), and voice (p <.001, OR = 19.75). Proposed cluster stratifications show better performance than NTCP models for severe drymouth (AUC.598 vs.559, MCC.143 vs.062), swallow (AUC.631 vs.561, MCC.20 vs -.030), mucus (AUC.596 vs.492, MCC.164 vs -.041), and voice (AUC.681 vs.555, MCC.181 vs -.019). Simplified dose thresholds also show better performance than baseline models for predicting late severe ratings for all symptoms.

Conclusion

Our results show that leveraging the 3-D dose histograms from radiation therapy plan improves stratification of patients according to their risk of experiencing long-term severe radiation associated symptoms, beyond existing NTPC models. Our rule-based method can approximate our stratifications with minimal loss of accuracy and can proactively identify risk factors for radiation-associated toxicity.

World Workshop on Oral Medicine VIII: Development of a Core Outcome Set for Dry Mouth: A Systematic Review of Outcome Domains for Xerostomia

OBJECTIVE

The purpose of this study was to identify all outcome domains used in clinical studies of xerostomia, that is, subjective sensation of dry mouth. This study is part of the extended project "World Workshop on Oral Medicine Outcomes Initiative for the Direction of Research" to develop a core outcome set for dry mouth.

STUDY DESIGN

A systematic review was performed on MEDLINE, EMBASE, CINAHL, and Cochrane Central Register of Controlled Trials databases. All clinical and observational studies that assessed xerostomia in human participants from 2001 to 2021 were included. Information on outcome domains was extracted and mapped to the Core Outcome Measures in Effectiveness Trials taxonomy. Corresponding outcome measures were summarized.

RESULTS

From a total of 34,922 records retrieved, 688 articles involving 122,151 persons with xerostomia were included. There were 16 unique outcome domains and 166 outcome measures extracted. None of these domains or measures were consistently used across all the studies. The severity of xerostomia and physical functioning were the 2 most frequently assessed domains.

CONCLUSION

There is considerable heterogeneity in outcome domains and measures reported in clinical studies of xerostomia. This highlights the need for harmonization of dry mouth assessment to enhance comparability across studies and facilitate the synthesis of robust evidence for managing patients with xerostomia.

Integrated radiomics, dose-volume histogram criteria and clinical features for early prediction of saliva amount reduction after radiotherapy in nasopharyngeal cancer patients

PURPOSE

Previously, the evaluation of xerostomia depended on subjective grading systems, rather than the accurate saliva amount reduction. Our aim was to quantify acute xerostomia with reduced saliva amount, and apply radiomics, dose-volume histogram (DVH) criteria and clinical features to predict saliva amount reduction by machine learning techniques.

MATERIAL AND METHODS

Computed tomography (CT) of parotid glands, DVH, and clinical data of 52 patients were collected to extract radiomics, DVH criteria and clinical features, respectively. Firstly, radiomics, DVH criteria and clinical features were divided into 3 groups for feature selection, in order to alleviate the masking effect of the number of features in different groups. Secondly, the top features in the 3 groups composed integrated features, and features selection was performed again for integrated features. In this study, feature selection was used as a combination of eXtreme Gradient Boosting (XGBoost) and SHapley Additive exPlanations (SHAP) to alleviate multicollinearity. Finally, 6 machine learning techniques were used for predicting saliva amount reduction. Meanwhile, top radiomics features were modeled using the same machine learning techniques for comparison.

RESULT

17 integrated features (10 radiomics, 4 clinical, 3 DVH criteria) were selected to predict saliva amount reduction, with a mean square error (MSE) of 0.6994 and a R² score of 0.9815. Top 17 and 10 selected radiomics features predicted saliva amount reduction, with MSE of 0.7376, 0.7519, and R² score of 0.9805, 0.9801, respectively.

CONCLUSION

With the same number of features, integrated features (radiomics + DVH criteria + clinical) performed better than radiomics features alone. The important DVH criteria and clinical features mainly included, white blood cells (WBC), parotid_glands_Dmax, Age, parotid_glands_V15, hemoglobin (Hb), BMI and parotid_glands_V45.

Adaptive Radiotherapy in Head and Neck Cancer Using Volumetric Modulated Arc Therapy

A dosimetric study was performed to show the importance of adaptive radiotherapy (ART) for head and neck cancer (HNC) patients using volumetric modulated arc therapy (VMAT). A total of 13 patients with HNC who required replanning during radiotherapy were included in this study. All plans succeeded to achieve the set objectives regarding target volume coverage and organ sparing. All target volumes presented a significant decrease with an average of 76.44 cm3 (p = 0.007) for PTVlow risk, 102.81 cm3 (p = 0.021) for PTVintermediate risk, and 47.10 cm3 (p = 0.003) for PTVhigh risk. Additionally, a positive correlation was found between PTV shrinkage and the number of fractions completed before replanning. Significant volume decrease was also observed for the parotid glands. The ipsilateral parotid decreased in volume by a mean of 3.75 cm3 (14.43%) (p = 0.067), while the contralateral decreased by 4.23 cm3 (13.23%) (p = 0.033). For all analyzed organs, a reduction in the final dose received after replanning was found. Our study showed that ART via rescanning, recontouring, and replanning using VMAT is essential whenever anatomical and positional variations occur. Furthermore, comparison with the literature has confirmed that ART using VMAT offers similar results to ART with intensity modulated radiotherapy.

The Role of Patient- and Treatment-Related Factors and Early Functional Imaging in Late Radiation-Induced Xerostomia in Oropharyngeal Cancer Patients

Simple Summary

In the present prospective study, we assessed the role of various Magnetic Resonance Imaging biomarkers combined with self-assessed xerostomia questionnaires and patient- and treatment-related factors, in predicting xerostomia at 12 months after chemoradiotherapy for oropharyngeal squamous cell carcinoma. We hypothesized that the integration of pre-treatment imaging biomarkers, which addresses the tissue heterogeneity and individual variations among patients, could improve the accuracy of conventional prediction models that are based only on dose information, ultimately providing a better understanding of the pathophysiological mechanisms underlying radiation induced salivary dysfunction. The implementation of multifactorial models, driven by machine learning algorithms, may improve prediction accuracy of radiation-induced toxicity and tailor individual treatment options for patients.

Abstract

The advent of quantitative imaging in personalized radiotherapy (RT) has offered the opportunity for a better understanding of individual variations in intrinsic radiosensitivity. We aimed to assess the role of magnetic resonance imaging (MRI) biomarkers, patient-related factors, and treatment-related factors in predicting xerostomia 12 months after RT (XER₁₂) in patients affected by oropharyngeal squamous cell carcinoma (OSCC). Patients with locally advanced OSCC underwent diffusion-weighted imaging (DWI) and dynamic-contrast enhanced MRI at baseline; DWI was repeated at the 10th fraction of RT. The Radiation Therapy Oncology Group (RTOG) toxicity scale was used to evaluate salivary gland toxicity. Xerostomia-related questionnaires (XQs) were administered weekly during and after RT. RTOG toxicity ≥ grade 2 at XER₁₂ was considered as endpoint to build prediction models. A Decision Tree classification learner was applied to build the prediction models following a five-fold cross-validation. Of the 89 patients enrolled, 63 were eligible for analysis. Thirty-six (57.1%) and 21 (33.3%) patients developed grade 1 and grade 2 XER₁₂, respectively. Including only baseline variables, the model based on DCE-MRI and V65 (%) (volume of both glands receiving doses ≥ 65 Gy) had a fair accuracy (77%, 95% CI: 66.5–85.4%). The model based on V65 (%) and XQ-Int_mid (integral of acute XQ scores from the start to the middle of RT) reached the best accuracy (81%, 95% CI: 71–88.7%). In conclusion, non-invasive biomarkers from DCE-MRI, in combination with dosimetric variables and self-assessed acute XQ scores during treatment may help predict grade 2 XER₁₂ with a fair to good accuracy.

Can the Risk of Dysphagia in Head and Neck Radiation Therapy Be Predicted by an Automated Transit Fluence Monitoring Process During Treatment? A First Comparative Study of Patient Reported Quality of Life and the Fluence-Based Decision Support Metric

PURPOSE/OBJECTIVE(S)

The additional personnel and imaging procedures required for Adaptive Radiation Therapy (ART) pose a challenge for a broad implementation. We hypothesize that a change in transit fluence during the treatment course is correlated with the change of quality of life and thus can be used as a replanning trigger.

MATERIALS/METHODS

Twenty-one head and neck cancer (HNC) patients filled out an MD Anderson Dysphagia Inventory (MDADI) questionnaire, before-and-after the radiotherapy treatment course. The transit fluence was measured by the Watchdog (WD) in-vivo portal dosimetry system. The patients were monitored with daily WD and weekly CBCTs. The region of interest (ROI) of each patient was defined as the outer contour of the patient between approximate spine levels C1 to C4, essentially the neck and mandible inside the beam's eye view. The nth day integrated transit fluence change, Δϕ_n, and the volume change, ΔV_ROI, of the ROI of each patient was calculated from the corresponding WD and CBCT measurements. The correlation between MDADI scores and age, gender, planning mean dose to salivary glands <D_sg>, weight change ΔW, ΔV_ROI, and Δϕ_n, were analyzed using the ranked-Pearson correlation.

RESULTS

No statistically significant correlation was found for age, gender and ΔW. <D_sg> was found to have clinically important correlation with functional MDADI (ρ = -0.39, P = 0.081). ΔV_ROI was found to have statistically significant correlation of 0.44, 0.47 and 0.44 with global, physical and functional MDADI (P-value < 0.05). Δϕ_n was found to have statistically significant ranked-correlation (-0.46, -0.46 and -0.45) with physical, functional and total MDADI (P-value < 0.05).

CONCLUSION

A transit fluence based decision support metric (DSM) is statistically correlated with the dysphagia risk. It can not only be used as an early signal in assisting clinicians in the ART patient selection for replanning, but also lowers the resource barrier of ART implementation.

Investigation of Radiation-Induced Toxicity in Head and Neck Cancer Patients through Radiomics and Machine Learning: A Systematic Review

Background. Radiation-induced toxicity represents a crucial concern in oncological treatments of patients affected by head and neck neoplasms, due to its impact on survivors' quality of life. Published reports suggested the potential of radiomics combined with machine learning methods in the prediction and assessment of radiation-induced toxicities, supporting a tailored radiation treatment management. In this paper, we present an update of the current knowledge concerning these modern approaches.

MATERIALS AND METHODS

A systematic review according to PICO-PRISMA methodology was conducted in MEDLINE/PubMed and EMBASE databases until June 2019. Studies assessing the use of radiomics combined with machine learning in predicting radiation-induced toxicity in head and neck cancer patients were specifically included. Four authors (two independently and two in concordance) assessed the methodological quality of the included studies using the Radiomic Quality Score (RQS). The overall score for each analyzed study was obtained by the sum of the single RQS items; the average and standard deviation values of the authors' RQS were calculated and reported.

RESULTS

Eight included papers, presenting data on parotid glands, cochlea, masticatory muscles, and white brain matter, were specifically analyzed in this review. Only one study had an average RQS was ≤ 30% (50%), while 3 studies obtained a RQS almost ≤ 25%. Potential variability in the interpretations of specific RQS items could have influenced the inter-rater agreement in specific cases.

CONCLUSIONS

Published radiomic studies provide encouraging but still limited and preliminary data that require further validation to improve the decision-making processes in preventing and managing radiation-induced toxicities.

A longitudinal study on parotid and submandibular gland changes assessed by magnetic resonance imaging and ultrasonography in post-radiotherapy nasopharyngeal cancer patients

Objectives

With regard to the intensity modulated radiotherapy (IMRT) of nasopharyngeal carcinoma (NPC) patients, this longitudinal study evaluated the radiation-induced changes in the parotid and submandibular glands in terms of gland size, echogenicity and haemodynamic parameters.

Methods

21 NPC patients treated by IMRT underwent MRI and ultrasound scans before radiotherapy, and at 6, 12, 18 and 24 months after treatment. Parotid and submandibular gland volumes were measured from the MRI images, whereas the parotid echogenicity and haemodynamic parameters including the resistive index, pulsatility index, peak systolic velocity and end diastolic velocity were evaluated by ultrasonography. Trend lines were plotted to show the pattern of changes. The correlations of gland doses and the post-RT changes were also studied.

Results

The volume of the parotid and submandibular glands demonstrated a significant drop from pre-RT to 6 months post-RT. The parotid gland changed from hyperechoic before RT to either isoechoic or hypoechoic after treatment. The resistive index and pulsatility index decreased from pre-RT to 6 month post-RT, then started to increase at 12 month time interval. Both peak systolic velocity and end diastolic velocity increased after 6 months post-RT then followed a decreasing trend up to 24 months post-RT. There was mild correlation between post-RT gland dose and gland volume, but not with haemodynamic changes.

Conclusions

Radiation from IMRT caused shrinkage of parotid and submandibular glands in NPC patients. It also changed the echogenicity and vascular condition of the parotid gland. The most significant changes were observed at 6 months after radiotherapy.

Advances in knowledge

It is the first paper that reports on the longitudinal changes of salivary gland volume, echogenicity and haemodynamic parameters altogether in NPC patients after radiotherapy. The results are useful for the prediction of glandular changes that is associated with xerostomia, which help to provide timely management of the complication when the patients attend follow-up visits.

Radiomics for radiation oncologists: are we ready to go?

Radiomics have emerged as an exciting field of research over the past few years, with very wide potential applications in personalised and precision medicine of the future. Radiomics-based approaches are still however limited in daily clinical practice in oncology. This review focus on how radiomics could be incorporated into the radiation therapy pipeline, and globally help the radiation oncologist, from the tumour diagnosis to follow-up after treatment. Radiomics could impact on all steps of the treatment pipeline, once the limitations in terms of robustness and reproducibility are overcome. Major ongoing efforts should be made to collect and share data in the most standardised manner possible.

Investigation of a Novel Decision Support Metric for Head and Neck Adaptive Radiation Therapy Using a Real-Time In Vivo Portal Dosimetry System

In adaptive radiation therapy of head and neck cancer, any significant anatomical changes observed are used to adapt the treatment plan to maintain target coverage without elevating the risk of xerostomia. However, the additional resources required for adaptive radiation therapy pose a challenge for broad-based implementation. It is hypothesized that a change in transit fluence is associated with volumetric change in the vicinity of the target and therefore can be used as a decision support metric for adaptive radiation therapy. This was evaluated by comparing the fluence with volumetric changes in 12 patients. Transit fluence was measured by an in vivo portal dosimetry system. Weekly cone beam computed tomography was used to determine volume change in the rectangular region of interest from condyloid process to C6. The integrated transit fluence through the region of interest on the day of the cone beam computed tomography scan was calculated with the first treatment as the baseline. The correlation between fluence change and volume change was determined. A logistic regression model was also used to associate the 5% region of interest volume reduction replanning trigger point and the fluence change. The model was assessed by a chi-square test. The area under the receiver-operating characteristic curve was also determined. A total of 46 pairs of measurements were obtained. The correlation between fluence and volumetric changes was found to be -0.776 (P value <.001). The negative correlation is attributed to the increase in the photon fluence transport resulting from the volume reduction. The chi-square of the logistic regression was found to be 17.4 (P value <.001). The area under the receiver-operating characteristic curve was found to be 0.88. Results indicate the change in transit fluence, which can be measured without consuming clinical resources or requiring additional time in the treatment room, can be used as a decision support metric for adaptive therapy.

Impact of xerostomia on the quality of life of patients submitted to head and neck radiotherapy

Background

The aim of the present work was to evaluate the impact of xerostomia on the quality of life of patients who underwent radiotherapy in the head and neck region.

Material and Methods

This was a cross-sectional, quantitative study. The sample comprised 40 patients whose xerostomia was classified through the xerostomia inventory and the quality of life evaluated through the oral health impact profile questionnaire (OHIP).

Results

The majority of participants were male (75%), mean age 58.7 years. According to the degree of severity of the xerostomia, the average score among the participants was 36 points, this being considered moderate xerostomia. A significant impact was observed, with the median score 11 points, with the highest scores in the domains related to functional limitation, physical pain and physical disability. The majority of the participants (97.5%) had reduced salivary flow after the end of radiotherapy. There was a significant positive correlation between the degree of xerostomia and reduced quality of life, Pearson correlation 0.5421, (p< 0.05).

Conclusions

Based upon the results it is concluded that xerostomia has a negative impact on the quality of life of patients who undergo radiotherapy in the head and neck region.

Key words:Head and neck neoplasms, radiotherapy, xerostomia, quality of life.

Impact of adaptive intensity-modulated radiotherapy on the neutrophil-to-lymphocyte ratio in patients with nasopharyngeal carcinoma

Purpose

Nutritional status and haematological parameters are related to the prognosis of patients treated with radiotherapy, but the correlation between adaptive radiotherapy (ART) and haematological indicators has never been reported. This study explores the influence of ART on the change in haematological indicators and provides a theoretical basis for the use of ART in patients with nasopharyngeal carcinoma (NPC).

Patients and methods

We retrospectively analysed 122 patients with NPC from January 2014 to December 2015. Patients in two treatment groups were matched using the propensity score matching method at a ratio of 1:1. The data were analysed with the Kaplan–Meier method, log-rank tests, regression analyses and paired t tests.

Results

Significant differences were detected for changes in the neutrophil-to-lymphocyte ratio (ΔNLR), circulating lymphocyte count (ΔCLC), circulating platelet count (ΔCPC), and circulating neutrophil granulocyte count (ΔCNC) during radiotherapy (P = 0.002, P < 0.001, and P = 0.036, respectively) between the ART and non-ART groups. Differences in acute radiation injury to the parotid glands (PGs) (P < 0.001), skin (P < 0.001), and oral structures (P < 0.001), Δweight (kg) (P = 0.025), and Δweight (%) (P = 0.030) were also significant between the two groups. According to univariate and multivariate analyses, ART (R = 0.531, P = 0.004), skin-related side effects (R = 0.328, P = 0.020), and clinical stage (R = -0.689, P < 0.001) are influencing factors for the ΔNLR in patients. ART is also the influencing factor for the ΔCLC (R = 2.108, P < 0.001) and the only factor affecting the ΔCPC (R = 0.121, P = 0.035). Based on subgroup analyses, for stage T1–2N0–3 disease, ΔCLC was higher in patients in the ART group than in patients in the non-ART group (P < 0.001, P = 0.003, and P = 0.003).

Conclusion

ART ameliorates changes in haematological indexes (ΔNLR, ΔCLC, and ΔCPC) and reduces side effects to the skin and PGs and weight loss during radiotherapy in patients with NPC, and patients with stage T1–2 disease experience a greater benefit.

Electronic supplementary material

The online version of this article (10.1186/s13014-019-1350-9) contains supplementary material, which is available to authorized users.

The GIRAFE phase II trial on MVCT-based "volumes of the day" and "dose of the day" addresses when and how to implement adaptive radiotherapy for locally advanced head and neck cancer

During exclusive curative radiotherapy for head and neck tumors, the patient's organs at risk (OAR) and target volumes frequently change size and shape, leading to a risk of higher toxicity and lower control than expected on planned dosimetry. Adaptive radiotherapy is often necessary but 1) tools are needed to define the optimal time for replanning, and 2) the subsequent workflow is time-consuming. We designed a prospective study to evaluate 1) the validity of automatically deformed contours on the daily MVCT, in order to safely use the "dose-of the day" tool to check daily if replanning is necessary; 2) the automatically deformed contours on the replanning CT and the time gained in the replanning workflow. Forty-eight patients with T3-T4 and/or involved node >2 cm head and neck squamous cell carcinomas, planned for curative radiotherapy without surgery, will be enrolled. They will undergo treatment with helical IMRT including daily repositioning MVCTs. The contours proposed will be compared weekly on intermediate planning CTs (iCTs) on weeks 3, 4, 5 and 6. On these iCTs both manual recontouring and automated deformable registration of the initial contours will be compared with the contours automatically defined on the MVCT. The primary objective is to evaluate the Dice similarity coefficient (DSC) of the volumes of each parotid gland. The secondary objectives will evaluate, for target volumes and all OARs: the DSC, the mean distance to agreement, and the average surface-to-surface distance. Time between the automatic and the manual recontouring workflows will be compared.

Early Prediction of Acute Xerostomia During Radiation Therapy for Head and Neck Cancer Based on Texture Analysis of Daily CT

PURPOSE

To investigate radiation-induced changes of computed tomography (CT) textures in parotid glands (PG) to predict acute xerostomia during radiotherapy (RT) for head and neck cancer (HNC).

METHODS AND MATERIALS

Daily or fraction kilovoltage CTs acquired using diagnostic CT scanners (eg, in-room CTs) during intensity-modulated RT for 59 HNC patients at 3 institutions were analyzed. The PG contours were generated on selected daily/fraction CTs. A series of histogram-based texture features, including the mean CT number (MCTN) in Hounsfield units, volume, standard deviation, skewness, kurtosis, and entropy for PGs were calculated for each fraction. Correlations between the changes of the texture features, radiation dose, and observed acute xerostomia were analyzed. A classifier model and the incurred CT-based xerostomia score (CTXS) were introduced to predict xerostomia based on combined changes of MCTN and volume of PGs. The t test and Spearman and Pearson correlation tests were used in the analyses.

RESULTS

Substantial changes in various CT texture features of PGs were observed during RT delivery. The changes of PG MCTN or volume are not strongly correlated with the observed xerostomia grades if they are considered separately. The CTXS showed a significant correlation to the observed xerostomia grades (r = 0.71, P < .00001). The CTXS-based classifier can predict the xerostomia severity with a success rate ranging from 79% to 98%. The xerostomia severity at the end of treatment can be predicted based on the CTXS determined at the fifth week with a precision and sensitivity of 100%.

CONCLUSION

Significant changes in the CT histogram features of the parotid glands were observed during RT of HNC. A practical method of using the changes of MCTN and volume of PGs is proposed to predict radiation-induced acute xerostomia, which may be used to help design adaptive treatment.

Geometric Image Biomarker Changes of the Parotid Gland Are Associated With Late Xerostomia

PURPOSE

To identify a surrogate marker for late xerostomia 12 months after radiation therapy (Xer_12m), according to information obtained shortly after treatment.

METHODS AND MATERIALS

Differences in parotid gland (PG) were quantified in image biomarkers (ΔIBMs) before and 6 weeks after radiation therapy in 107 patients. By performing stepwise forward selection, ΔIBMs that were associated with Xer_12m were selected. Subsequently other variables, such as PG dose and acute xerostomia scores, were added to improve the prediction performance. All models were internally validated.

RESULTS

Prediction of Xer_12m based on PG surface reduction (ΔPG-surface) was good (area under the receiver operating characteristic curve, 0.82). Parotid gland dose was related to ΔPG-surface (P<.001, R² = 0.27). The addition of acute xerostomia scores to the ΔPG-surface improved the prediction of Xer_12m significantly, and vice versa. The final model including ΔPG-surface and acute xerostomia had outstanding performance in predicting Xer_12m early after radiation therapy (area under the receiver operating characteristic curve, 0.90).

CONCLUSIONS

Parotid gland surface reduction was associated with late xerostomia. The early posttreatment model with ΔPG-surface and acute xerostomia scores can be considered as a surrogate marker for late xerostomia.

Early prediction of radiotherapy-induced parotid shrinkage and toxicity based on CT radiomics and fuzzy classification

MOTIVATION

Patients under radiotherapy for head-and-neck cancer often suffer of long-term xerostomia, and/or consistent shrinkage of parotid glands. In order to avoid these drawbacks, adaptive therapy can be planned for patients at risk, if the prediction is obtained timely, before or during the early phase of treatment. Artificial intelligence can address the problem, by learning from examples and building classification models. In particular, fuzzy logic has shown its suitability for medical applications, in order to manage uncertain data, and to build transparent rule-based classifiers. In previous works, clinical, dosimetric and image-based features were considered separately, to find different possible predictors of parotid shrinkage. On the other hand, a few works reported possible image-based predictors of xerostomia, while the combination of different types of features has been little addressed.

OBJECTIVE

This paper proposes the application of a novel machine learning approach, based on both statistics and fuzzy logic, aimed at the classification of patients at risk of i) parotid gland shrinkage and ii) 12-months xerostomia. Both problems are addressed with the aim of individuating predictors and models to classify respective outcomes.

METHODS

Knowledge is extracted from a real dataset of radiotherapy patients, by means of a recently developed method named Likelihood-Fuzzy Analysis, based on the representation of statistical information by fuzzy rule-based models. This method enables to manage heterogeneous variables and missing data, and to obtain interpretable fuzzy models presenting good generalization power (thus high performance), and to measure classification confidence. Numerous features are extracted to characterize patients, coming from different sources, i.e. clinical features, dosimetric parameters, and radiomics-based measures obtained by texture analysis of Computed Tomography images. A learning approach based on the composition of simple models in a more complicated one allows to consider the features separately, in order to identify predictors and models to use when only some data source is available, and obtaining more accurate results when more information can be combined.

RESULTS

Regarding parotid shrinkage, a number of good predictors is detected, some already known and confirmed here, and some others found here, in particular among radiomics-based features. A number of models are also designed, some using single features and others involving models composition to improve classification accuracy. In particular, the best model to be used at the initial treatment stage, and another one applicable at the half treatment stage are identified. Regarding 12-months toxicity, some possible predictors are detected, in particular among radiomics-based features. Moreover, the relation between final parotid shrinkage rate and 12-months xerostomia is evaluated. The method is compared to the naïve Bayes classifier, which reveals similar results in terms of classification accuracy and best predictors. The interpretable fuzzy rule-based models are explicitly presented, and the dependence between predictors and outcome is explained, thus furnishing in some cases helpful insights about the considered problems.

CONCLUSION

Thanks to the performance and interpretability of the fuzzy classification method employed, predictors of both parotid shrinkage and xerostomia are detected, and their influence on each outcome is revealed. Moreover, models for predicting parotid shrinkage at initial and half radiotherapy stages are found.

Optimal adaptive IMRT strategy to spare the parotid glands in oropharyngeal cancer

PURPOSE

In oropharyngeal cancer adaptive radiation therapy (ART), this study aimed to quantify the dosimetric benefit of numerous replanning strategies, defined by various numbers and timings of replannings, with regard to parotid gland (PG) sparing.

MATERIAL AND METHODS

Thirteen oropharyngeal cancer patients had one planning and then six weekly CT scans during the seven weeks of IMRT. Weekly doses were recalculated without replanning or with replanning to spare the PG. Sixty-three ART scenarios were simulated by considering all the combinations of numbers and timings of replanning. The PG cumulated doses corresponding to "standard" IMRT and ART scenarios were estimated and compared, either by calculating the average of weekly doses or using deformable image registration (DIR).

RESULTS

Considering average weekly doses, the mean PG overdose using standard IMRT, compared to the planned dose, was 4.1Gy. The mean dosimetric benefit of 6 replannings was 3.3Gy. Replanning at weeks 1, 1-5, 1-2-5, 1-2-4-5 and 1-2-4-5-6 produced the lowest PG mean doses, 94% of the maximum benefit being obtained with 3 replannings. The percentage of patients who had a benefit superior to 5Gy for the contralateral PG was 31% for the three-replannings strategy. The same conclusions were found using DIR.

CONCLUSION

Early replannings proved the most beneficial for PG sparing, three replannings (weeks 1-2-5), representing an attractive combination for ART in oropharyngeal cancer.

Selection of head and neck cancer patients for adaptive radiotherapy to decrease xerostomia

BACKGROUND AND PURPOSE

The aim of this study was to develop and validate a method to select head and neck cancer patients for adaptive radiotherapy (ART) pre-treatment. Potential pre-treatment selection criteria presented in recent literature were included in the analysis.

MATERIALS AND METHODS

Deviations from the planned parotid gland mean dose (PG ΔDmean) were estimated for 113 head and neck cancer patients by re-calculating plans on repeat CT scans. Uni- and multivariable linear regression analyses were performed to select pre-treatment parameters, and ROC curve analysis was used to determine cut off values, for selecting patients with a PG dose deviation larger than 3Gy. The patient selection method was validated in a second patient cohort of 43 patients.

RESULTS

After multivariable analysis, the planned PG Dmean remained the only significant parameter for PG ΔDmean. A sensitivity of 91% and 80% could be obtained using a threshold of PG Dmean of 22.2Gy, for the development and validation cohorts, respectively. This would spare 38% (development cohort) and 24% (validation cohort) of patients from the labour-intensive ART procedure.

CONCLUSIONS

The presented method to select patients for ART pre-treatment reduces the labour of ART, contributing to a more effective allocation of the department resources.

Analysis of serial CT images for studying the RT effects in head-neck cancer patients

Images taken during and after RT for head and neck cancer have the potential to quantitatively assess xerostomia. Image information may be used as biomarkers of RT effects on parotid glands with significant potential to support adaptive treatment strategies. We investigated the possibility to extract information based on in-room CT images (kVCT, MVCT), acquired for daily image-guided radiotherapy treatment of head-and-neck cancer patients, in order to predict individual response in terms of toxicity. Follow-up MRI images were also used in order to investigate long term parotid gland deformation.