Radiomic Analysis of Salivary Glands and Its Role for Predicting Xerostomia in Irradiated Head and Neck Cancer Patients

Development and validation of survival prognostic models for head and neck cancer patients using machine learning and dosiomics and CT radiomics features: a multicentric study

BACKGROUND

This study aimed to investigate the value of clinical, radiomic features extracted from gross tumor volumes (GTVs) delineated on CT images, dose distributions (Dosiomics), and fusion of CT and dose distributions to predict outcomes in head and neck cancer (HNC) patients.

METHODS

A cohort of 240 HNC patients from five different centers was obtained from The Cancer Imaging Archive. Seven strategies, including four non-fusion (Clinical, CT, Dose, DualCT-Dose), and three fusion algorithms (latent low-rank representation referred (LLRR),Wavelet, weighted least square (WLS)) were applied. The fusion algorithms were used to fuse the pre-treatment CT images and 3-dimensional dose maps. Overall, 215 radiomics and Dosiomics features were extracted from the GTVs, alongside with seven clinical features incorporated. Five feature selection (FS) methods in combination with six machine learning (ML) models were implemented. The performance of the models was quantified using the concordance index (CI) in one-center-leave-out 5-fold cross-validation for overall survival (OS) prediction considering the time-to-event.

RESULTS

The mean CI and Kaplan-Meier curves were used for further comparisons. The CoxBoost ML model using the Minimal Depth (MD) FS method and the glmnet model using the Variable hunting (VH) FS method showed the best performance with CI = 0.73 ± 0.15 for features extracted from LLRR fused images. In addition, both glmnet-Cindex and Coxph-Cindex classifiers achieved a CI of 0.72 ± 0.14 by employing the dose images (+ incorporated clinical features) only.

CONCLUSION

Our results demonstrated that clinical features, Dosiomics and fusion of dose and CT images by specific ML-FS models could predict the overall survival of HNC patients with acceptable accuracy. Besides, the performance of ML methods among the three different strategies was almost comparable.

Dosiomics improves prediction of locoregional recurrence for intensity modulated radiotherapy treated head and neck cancer cases

OBJECTIVES

To investigate whether dosiomics can benefit to IMRT treated patient's locoregional recurrences (LR) prediction through a comparative study on prediction performance inspection between radiomics methods and that integrating dosiomics in head and neck cancer cases.

MATERIALS AND METHODS

A cohort of 237 patients with head and neck cancer from four different institutions was obtained from The Cancer Imaging Archive and utilized to train and validate the radiomics-only prognostic model and integrate the dosiomics prognostic model. For radiomics, the radiomics features were initially extracted from images, including CTs and PETs, and selected on the basis of their concordance index (CI) values, then condensed via principle component analysis. Lastly, multivariate Cox proportional hazards regression models were constructed with class-imbalance adjustment as the LR prediction models by inputting those condensed features. For dosiomics integration model establishment, the initial features were similar, but with additional 3-dimensional dose distribution from radiation treatment plans. The CI and the Kaplan-Meier curves with log-rank analysis were used to assess and compare these models.

RESULTS

Observed from the independent validation dataset, the CI of the model for dosiomics integration (0.66) was significantly different from that for radiomics (0.59) (Wilcoxon test, p=5.9×10^-31). The integrated model successfully classified the patients into high- and low-risk groups (log-rank test, p=2.5×10^-02), whereas the radiomics model was not able to provide such classification (log-rank test, p=0.37).

CONCLUSION

Dosiomics can benefit in predicting the LR in IMRT-treated patients and should not be neglected for related investigations.

Predicting acute radiation induced xerostomia in head and neck Cancer using MR and CT Radiomics of parotid and submandibular glands

Purpose

To analyze baseline CT/MR-based image features of salivary glands to predict radiation-induced xerostomia 3-months after head-and-neck cancer (HNC) radiotherapy.

Methods

A 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).

Results

Among 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).

Conclusion

Our 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.

Electronic supplementary material

The online version of this article (10.1186/s13014-019-1339-4) contains supplementary material, which is available to authorized users.

NCTN Assessment on Current Applications of Radiomics in Oncology

Radiomics is a fast-growing research area based on converting standard-of-care imaging into quantitative minable data and building subsequent predictive models to personalize treatment. Radiomics has been proposed as a study objective in clinical trial concepts and a potential biomarker for stratifying patients across interventional treatment arms. In recognizing the growing importance of radiomics in oncology, a group of medical physicists and clinicians from NRG Oncology reviewed the current status of the field and identified critical issues, providing a general assessment and early recommendations for incorporation in oncology studies.

Needs and Challenges for Radiation Oncology in the Era of Precision Medicine

Modern medicine, including the care of the cancer patient, has significantly advanced, with the evidence-based medicine paradigm serving to guide clinical care decisions. Yet we now also recognize the tremendous heterogeneity not only of disease states but of the patient and his or her environment as it influences treatment outcomes and toxicities. These reasons and many others have led to a reevaluation of the generalizability of randomized trials and growing interest in accounting for this heterogeneity under the rubric of precision medicine as it relates to personalizing clinical care predictions, decisions, and therapy for the disease state. For the cancer patient treated with radiation therapy, characterizing the spatial treatment heterogeneity has been a fundamental tenet of routine clinical care facilitated by established database and imaging platforms. Leveraging these platforms to further characterize and collate all clinically relevant sources of heterogeneity that affect the longitudinal health outcomes of the irradiated cancer patient provides an opportunity to generate a critical informatics infrastructure on which precision radiation therapy may be realized. In doing so, data science-driven insight discoveries, personalized clinical decisions, and the potential to accelerate translational efforts may be realized ideally within a network of institutions with locally developed yet coordinated informatics infrastructures. The path toward realizing these goals has many needs and challenges, which we summarize, with many still to be realized and understood. Early efforts by our group have identified the feasibility of this approach using routine clinical data sets and offer promise that this transformation can be successfully realized in radiation oncology.

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

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.

The Needs and Benefits of Continuous Model Updates on the Accuracy of RT-Induced Toxicity Prediction Models Within a Learning Health System

PURPOSE

Clinical data collection and development of outcome prediction models by machine learning can form the foundation for a learning health system offering precision radiation therapy. However, changes in clinical practice over time can affect the measures and patient outcomes and, hence, the collected data. We hypothesize that regular prediction model updates and continuous prospective data collection are important to prevent the degradation of a model's predication accuracy.

METHODS AND MATERIALS

Clinical and dosimetric data from head and neck patients receiving intensity modulated radiation therapy from 2008 to 2015 were prospectively collected as a routine clinical workflow and anonymized for this analysis. Prediction models for grade ≥2 xerostomia at 3 to 6 months of follow-up were developed by bivariate logistic regression using the dose-volume histogram of parotid and submandibular glands. A baseline prediction model was developed with a training data set from 2008 to 2009. The selected predictor variables and coefficients were updated by 4 different model updating methods. (A) The prediction model was updated by using only recent 2-year data and applied to patients in the following test year. (B) The model was updated by increasing the training data set yearly. (C) The model was updated by increasing the training data set on the condition that the area under the curve (AUC) of the recent test year was less than 0.6. (D) The model was not updated. The AUC of the test data set was compared among the 4 model updating methods.

RESULTS

Dose to parotid and submandibular glands and grade of xerostomia showed decreasing trends over the years (2008-2015, 297 patients; P < .001). The AUC of predicting grade ≥2 xerostomia for the initial training data set (2008-2009, 41 patients) was 0.6196. The AUC for the test data set (2010-2015, 256 patients) decreased to 0.5284 when the initial model was not updated (D). However, the AUC was significantly improved by model updates (A: 0.6164; B: 0.6084; P < .05). When the model was conditionally updated, the AUC was 0.6072 (C).

CONCLUSIONS

Our preliminary results demonstrate that updating prediction models with prospective data collection is effective for maintaining the performance of xerostomia prediction. This suggests that a machine learning framework can handle the dynamic changes in a radiation oncology clinical practice and may be an important component for the construction of a learning health system.