Predicting late radiation-induced xerostomia with parotid gland PET biomarkers and dose metrics

Xerostomia prediction in patients with nasopharyngeal carcinoma during radiotherapy using segmental dose distribution in dosiomics and radiomics models

OBJECTIVES

This study aimed to integrate radiomics and dosiomics features to develop a predictive model for xerostomia (XM) in nasopharyngeal carcinoma after radiotherapy. It explores the influence of distinct feature extraction methods and dose ranges on the performance.

MATERIALS AND METHODS

Data from 363 patients with nasopharyngeal carcinoma were retrospectively analyzed. We pioneered a dose-segmentation strategy, where the overall dose distribution (OD) was divided into four segmental dose distributions (SDs) at intervals of 15 Gy. Features were extracted using manual definition and deep learning, applying OD or SD and integrating radiomics and dosiomics, yielding corresponding feature scores (manually defined radiomics, MDR; manually defined dosiomics, MDD; deep learning-based radiomics, DLR; deep learning-based dosiomics, DLD). Subsequently, 18 models were developed by combining features and model types (random forest and support vector machine).

RESULTS AND CONCLUSION

Under OD, O(DLR_DLD) demonstrated exceptional performance, with an optimal area under the curve (AUC) of 0.81 and an average AUC of 0.71. Within SD, S(DLR_DLD) surpassed the other models, achieving an optimal AUC of 0.90 and an average AUC of 0.85. Therefore, the integration of dosiomics into radiomics can augment predictive efficacy. The dose-segmentation strategy can facilitate the extraction of more profound information. This indicates that ScoreDLR and ScoreMDR were negatively associated with XM, whereas ScoreDLD, derived from SD exceeding 15 Gy, displayed a positive association with XM. For feature extraction, deep learning was superior to manual definition.

Future of Team-based Basic and Translational Science in Radiation Oncology

To further optimize radiotherapy, a more personalized treatment towards individual patient's risk profiles, dissecting both patient-specific tumor and normal tissue response to multimodality treatments is needed. Novel developments in radiobiology, using in vitro patient-specific complex tissue resembling 3D models and multiomics approaches at a spatial single-cell level, may provide unprecedented insight into the radiation responses of tumors and normal tissue. Here, we describe the necessary team effort, including all disciplines in radiation oncology, to integrate such data into clinical prediction models and link the relatively "big data" from the clinical practice, allowing accurate patient stratification for personalized treatment approaches.

Late-xerostomia prediction model based on 18F-FDG PET image biomarkers of the main salivary glands

BACKGROUND AND PURPOSE

Recently, a comprehensive xerostomia prediction model was published, based on baseline xerostomia, mean dose to parotid glands (PG) and submandibular glands (SMG). Previously, PET imaging biomarkers (IBMs) of PG were shown to improve xerostomia prediction. Therefore, this study aimed to explore the potential improvement of the additional PET-IBMs from both PG and SMG to the recent comprehensive xerostomia prediction model (i.e., the reference model).

MATERIALS AND METHODS

Totally, 540 head and neck cancer patients were split into training and validation cohorts. PET-IBMs from the PG and SMG, were selected using bootstrapped forward selection based on the reference model. The IBMs from both the PG and SMG with the highest selection frequency were added to the reference model, resulting in a PG-IBM model and a SMG-IBM model which were combined into a composite model. Model performance was assessed using the area under the curve (AUC). Likelihood ratio test compared the predictive performance between the reference model and models including IBMs.

RESULTS

The final selected PET-IBMs were 90th percentile of the PG SUV and total energy of the SMG SUV. The additional two PET-IBMs in the composite model improved the predictive performance of the reference model significantly. The AUC of the reference model and the composite model were 0.67 and 0.69 in the training cohort, and 0.71 and 0.73 in the validation cohort, respectively.

CONCLUSION

The composite model including two additional PET-IBMs from PG and SMG improved the predictive performance of the reference xerostomia model significantly, facilitating a more personalized prediction approach.

Analysis of the Parotid Glands on an Energy Spectrum CT Iodine Map to Evaluate Irradiation-Induced Acute Xerostomia in Patients With Nasopharyngeal Carcinoma

Objective: This prospective study aims to evaluate acute irradiation-induced xerostomia during radiotherapy by utilizing the normalized iodine concentration (NIC) derived from energy spectrum computed tomography (CT) iodine maps. Methods: In this prospective study, we evaluated 28 patients diagnosed with nasopharyngeal carcinoma. At 4 distinct stages of radiotherapy (0, 10, 20, and 30 fractions), each patient underwent CT scans to generate iodine maps. The NIC of both the left and right parotid glands was obtained, with the NIC at the 0-fraction stage serving as the baseline measurement. After statistically comparing the NIC obtained in the arterial phase, early venous phase, late venous phase, and delayed phase, we chose the late venous iodine concentration as the NIC and proceeded to analyze the variations in NIC at each radiotherapy interval. Using the series of NIC values, we conducted hypothesis tests to evaluate the extent of change in NIC within the parotid gland across different stages. Furthermore, we identified the specific time point at which the NIC decay exhibited the most statistically significant results. In addition, we evaluated the xerostomia grades of the patients at these 4 stages, following the radiation therapy oncology group (RTOG) xerostomia evaluation standard, to draw comparisons with the changes observed in NIC. Results: The NIC in the late venous phase exhibited the highest level of statistical significance (P < .001). There was a noticeable attenuation in NIC as the RTOG dry mouth grade increased. Particularly, at the 20 fraction, the NIC experienced the most substantial attenuation (P < .001), a significant negative correlation was observed between the NIC of the left, right, and both parotid glands, and the RTOG evaluation grade of acute irradiation-induced xerostomia (P < .001, r = -0.46; P < .001, r = -0.45; P < .001, r = -0.47). The critical NIC values for the left, right, and both parotid glands when acute xerostomia occurred were 0.175, 0.185, and 0.345 mg/ml, respectively, with AUC = 0.73, AUC = 0.75, and AUC = 0.75. Conclusion: The NIC may be used to evaluate changes in parotid gland function during radiotherapy and acute irradiation-induced xerostomia.

The Utility of Interim Positron Emission Tomography Imaging to Inform Adaptive Radiotherapy for Head and Neck Squamous Cell Carcinoma

ABSTRACT

In this article, as part of this special issue on biomarkers of early response, we review the current evidence to support the use of positron emission tomography (PET) imaging during chemoradiation therapy to inform biologically adaptive radiotherapy for head and neck squamous cell carcinoma. We review literature covering this topic spanning nearly 3 decades, including the use of various radiotracers and discoveries of novel predictive PET biomarkers. Through understanding how observational trials have informed current interventional clinical trials, we hope that this review will encourage researchers and clinicians to incorporate PET response criteria in new trial designs to advance biologically optimized radiotherapy.

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.

Validation of the 18F-FDG PET image biomarker model predicting late xerostomia after head and neck cancer radiotherapy

BACKGROUND AND PURPOSE

Previously, PET image biomarkers (PET-IBMs) - the 90^th percentile standardized uptake value (P90-SUV) and the Mean SUV (Mean-SUV) of the contralateral parotid gland (cPG) - were identified as predictors for late-xerostomia following head and neck cancer (HNC) radiotherapy. The aim of the current study was to assess in an independent validation cohort whether these pre-treatment PET-IBM can improve late-xerostomia prediction compared to the prediction with baseline xerostomia and mean cPG dose alone.

MATERIALS AND METHODS

The prediction endpoint was patient-rated moderate-to-severe xerostomia at 12 months after radiotherapy. The PET-IBMs were extracted from pre-treatment ¹⁸ F-FDG PET images. The performance of the model (base model) with baseline xerostomia and mean cPG dose alone and models with additionally P90-SUV or Mean-SUV were tested in the current independent validation cohort. Specifically, model discrimination (area under the curve: AUC) and calibration (calibration plot) were evaluated.

RESULTS

The current validation cohort consisted of 137 patients of which 40% developed moderate-to-severe xerostomia at 12 months. Both the PET-P90 model (AUC:PET-P90 = 0.71) and the PET-Mean model (AUC: PET-Mean = 0.70) performed well in the current validation cohort. Moreover, their performance were improved compared to the base model (AUC:base model= 0.68). The calibration plots showed a good fit of the prediction to the actual rates for all tested models.

CONCLUSION

PET-IBMs showed an improved prediction of late-xerostomia when added to the base model in this validation cohort. This contributed to the published hypothesis that PET-IBMs include individualized information and can serve as a pre-treatment risk factor for late-xerostomia.

Clinical use of positron emission tomography for radiotherapy planning - Medical physics considerations

PET/CT imaging plays an increasing role in radiotherapy treatment planning. The aim of this article was to identify the major use cases and technical as well as medical physics challenges during integration of these data into treatment planning. Dedicated aspects, such as (i) PET/CT-based radiotherapy simulation, (ii) PET-based target volume delineation, (iii) functional avoidance to optimized organ-at-risk sparing and (iv) functionally adapted individualized radiotherapy are discussed in this article. Furthermore, medical physics aspects to be taken into account are summarized and presented in form of check-lists.

Sub-regional analysis of the parotid glands: model development for predicting late xerostomia with radiomics features in head and neck cancer patients

BACKGROUND

The irradiation of sub-regions of the parotid has been linked to xerostomia development in patients with head and neck cancer (HNC). In this study, we compared the xerostomia classification performance of radiomics features calculated on clinically relevant and de novo sub-regions of the parotid glands of HNC patients.

MATERIAL AND METHODS

All patients (N = 117) were treated with TomoTherapy in 30-35 fractions of 2-2.167 Gy per fraction with daily mega-voltage-CT (MVCT) acquisition for image-guidance purposes. Radiomics features (N = 123) were extracted from daily MVCTs for the whole parotid gland and nine sub-regions. The changes in feature values after each complete week of treatment were considered as predictors of xerostomia (CTCAEv4.03, grade ≥ 2) at 6 and 12 months. Combinations of predictors were generated following the removal of statistically redundant information and stepwise selection. The classification performance of the logistic regression models was evaluated on train and test sets of patients using the Area Under the Curve (AUC) associated with the different sub-regions at each week of treatment and benchmarked with the performance of models solely using dose and toxicity at baseline.

RESULTS

In this study, radiomics-based models predicted xerostomia better than standard clinical predictors. Models combining dose to the parotid and xerostomia scores at baseline yielded an AUCtest of 0.63 and 0.61 for xerostomia prediction at 6 and 12 months after radiotherapy while models based on radiomics features extracted from the whole parotid yielded a maximum AUCtest of 0.67 and 0.75, respectively. Overall, across sub-regions, maximum AUCtest was 0.76 and 0.80 for xerostomia prediction at 6 and 12 months. Within the first two weeks of treatment, the cranial part of the parotid systematically yielded the highest AUCtest.

CONCLUSION

Our results indicate that variations of radiomics features calculated on sub-regions of the parotid glands can lead to earlier and improved prediction of xerostomia in HNC patients.

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.

Dose response modelling of secretory cell loss in salivary glands using PSMA PET

BACKGROUND AND PURPOSE

Xerostomia remains a common side effect of radiotherapy (RT) for patients with head and neck (H&N) cancer despite advancements in treatment planning and delivery. Secretory salivary gland cells express the prostate-specific membrane antigen (PSMA), and show significant uptake on PET scans using ⁶⁸Ga/¹⁸F-PSMA-ligands. We aimed to objectively quantify the dose-response of salivary glands to RT using PSMA PET.

METHODS AND MATERIALS

28H&N cancer patients received RT with 70 Gy in 35 fractions over 7 weeks. PSMA PET/CT was acquired at baseline (BL), during treatment (DT) and at 1-&6-months post-treatment (PT_1M/PT_6M). Dose, BL- PT_1M- and PT_6M-SUV were extracted for every voxel inside each parotid (PG) and submandibular (SMG) gland. The PT_1M/6M data was analysed using a generalised linear mixed effects model.Patient-reported xerostomia and DT-PSMA loss was also analysed.

RESULTS

Dose had a relative effect on BL SUV. For a population average gland (BL-SUV of 10), every 1 Gy increment, decreased the PT_1M/PT_6M-SUV by 1.6 %/1.6 % for PGs and by 0.9 %/1.8 % for SMGs. TD₅₀ of the population curves was 26.5/31.3 Gy for PGs, and 22.9/27.8 Gy for SMGs at PT_1M /PT_6M. PSMA loss correlated well with patient-reported xerostomia at DT/PT_1M (Spearman's ρ = -0.64, -0.50).

CONCLUSION

A strong relationship was demonstrated between radiation dose and loss of secretory cells in salivary glands derived using PSMA PET/CT. The population curve could potentially be used as a dose planning objective, by maximising the predicted post-treatment SUV. BL scans could be used to further tailor this to individual patients.

Radiomics-guided radiation therapy: opportunities and challenges

Radiomics is an advanced image-processing framework, which extracts image features and considers them as biomarkers towards personalized medicine. Applications include disease detection, diagnosis, prognosis, and therapy response assessment/prediction. As radiation therapy aims for further individualized treatments, radiomics could play a critical role in various steps before, during and after treatment. Elucidation of the concept of radiomics-guided radiation therapy (RGRT) is the aim of this review, attempting to highlight opportunities and challenges underlying the use of radiomics to guide clinicians and physicists towards more effective radiation treatments. This work identifies the value of RGRT in various steps of radiotherapy from patient selection to follow-up, and subsequently provides recommendations to improve future radiotherapy using quantitative imaging features.

A nomogram for predicting late radiation-induced xerostomia among locoregionally advanced nasopharyngeal carcinoma in intensity modulated radiation therapy era

Background: Dry mouth sensation cannot be improved completely even though parotids are spared correctly. Our purpose is to develop a nomogram to predict the moderate-to-severe late radiation xerostomia for patients with locoregionally advanced nasopharyngeal carcinoma (LA-NPC) in intensity modulated radiation therapy (IMRT) / volumetric modulated arc radiotherapy (VMAT) era.

Methods: A dataset of 311 patients was retrospectively collected between January 2010 and February 2013. The binary logistic regression was to estimate each factor’s prognostic value for development of moderate-to-severe patient-reported xerostomia at least 2 years (Xer2y) after completion of radiotherapy. Therefore, we can develop a nomogram according to binary logistic regression coefficients. This novel model was validated by bootstrapping analyses.

Results: Contralateral Parotid mean dose (coMD<24.4Gy), VMAT (yes), and platinum-based concurrent chemoradiotherapy (no) were significantly related to patient-reported xerostomia at least 2 years (Xer2y) (all p < 0.001), and were included in the nomogram. Receiver operating characteristic (ROC) analysis revealed AUC (area under the ROC curve) with the value of 0.811 (0.710-0.912) of the nomogram, which was significantly higher than coMD 0.698 (0.560-0.840) from QUANTEC2010 (p<0.001). Calibration plots illustrated that the predicted Xer2y was close to the actual observation, and decision curve analyses (DCA) indicated valid positive net benefits.

Conclusion: We developed a feasible nomogram to predict patient-rated Xer2y based on comprehensive individual data in patients with LA-NPC in the real world. The proposed model is able to facilitate the development of treatment plan and quality of life improvement.

Serum MicroRNAs as Xerostomia Biomarkers in Patients With Oropharyngeal Cancer Undergoing Radiation Therapy

PURPOSE

Severe xerostomia is noted in the majority of patients irradiated for oropharyngeal cancer. Extracellular microRNAs (miRNAs) may serve as effective tools allowing prediction of radiation-related toxicity. The aim of this study was to create an efficient prognostic miRNA-based test for severe, patient-rated xerostomia 3 months after primary treatment.

METHODS AND MATERIALS

This prospective study enrolled patients with oropharyngeal cancer treated between 2016 and 2018 in 3 centers in Poland. The primary endpoint was severe (grade ≥3) xerostomia as assessed by the European Organisation for Research and Treatment of Cancer H&N-35 questionnaires. Initially, a group of 10 patients with severe xerostomia was randomly selected and matched with a comparative group of 10 patients without severe xerostomia. Samples were collected before radiation therapy, after receiving 20 Gy, and within 24 hours after treatment completion. Quantitative real-time polymerase chain reaction arrays (QIAGEN, Hilden, Germany) were used to quantify expression levels of 752 miRNAs in the serum at all timepoints. The resulting logistic-regression based model was validated in additional 60 patients: 30 with grade >3 xerostomia and 30 without.

RESULTS

Of 152 eligible patients, we successfully recruited 111 patients. Severe xerostomia 3 months after treatment was reported by 63 patients (56.8%). Mean dose delivered to parotid glands was higher in both the exploratory and validation cohort. The model based on miR-185-5p and miR-425-5p expression levels measured before the start of radiation therapy had an area under the curve of 0.96 (95% confidence interval, 0.88-1.00). The model based on the same miRNAs remained robust when parameters were measured after 20 Gy (area under the curve 0.90; 95% confidence interval, 0.75-1.00). These results were confirmed in the validation group. In the validation group, preradiation therapy model application yielded 73.3% sensitivity and 80.0% specificity. In the samples taken after 20 Gy, the same 2 miRNAs yielded 67.7% sensitivity and 72.4% specificity. The model including pretreatment miR-185-5p and miR-425-5p levels together with mean parotid dose yielded 90.0% sensitivity and 80.0% specificity. In the validation cohort, this model yielded 80.6% sensitivity and 55.2% specificity. The model based on miRNA levels measured after 20 Gy and mean parotid dose had 80.0% sensitivity and 100% specificity in the exploratory group. In the validation cohort its performance fell to 71.0% sensitivity and 58.6% specificity.

CONCLUSIONS

Serum expression levels of miR-425-5p and miR-185-5p measured before the start of radiation therapy or during therapy (after 20 Gy) had significant prognostic value for the occurrence of severe xerostomia 3 months after treatment completion. The variability explained by miRNAs appears to be, at least partially, independent from that related to the dosimetric data.

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.

Application of Radiomics for the Prediction of Radiation-Induced Toxicity in the IMRT Era: Current State-of-the-Art

Normal tissue complication probability (NTCP) models that were formulated in the Quantitative Analyses of Normal Tissue Effects in the Clinic (QUANTEC) are one of the pillars in support of everyday’s clinical radiation oncology. Because of steady therapeutic refinements and the availability of cutting-edge technical solutions, the ceiling of organs-at-risk-sparing has been reached for photon-based intensity modulated radiotherapy (IMRT). The possibility to capture heterogeneity of patients and tissues in the prediction of toxicity is still an unmet need in modern radiation therapy. Potentially, a major step towards a wider therapeutic index could be obtained from refined assessment of radiation-induced morbidity at an individual level. The rising integration of quantitative imaging and machine learning applications into radiation oncology workflow offers an unprecedented opportunity to further explore the biologic interplay underlying the normal tissue response to radiation. Based on these premises, in this review we focused on the current-state-of-the-art on the use of radiomics for the prediction of toxicity in the field of head and neck, lung, breast and prostate radiotherapy.