Modeling of Normal Tissue Complications Using Imaging and Biomarkers After Radiation Therapy for Hepatocellular Carcinoma

Comparison prediction models of bladder toxicity based on radiomic features of CT and MRI in patients with prostate cancer undergoing radiotherapy

PURPOSE

This study aimed to assess the radiomic features of computed tomography (CT) and magnetic resonance imaging (MRI) of the bladder wall before radiotherapy using machine learning (ML) methods to predict bladder radiotoxicity in patients with prostate cancer.

METHODS

This study enrolled 70 patients with pathologically confirmed prostate cancer who were candidates for radiation therapy (RT). CT and MRI of the bladder wall before radiotherapy were used to extract radiomic features. The least absolute shrinkage and selection operator (LASSO) was used for feature selection. Algorithms such as Random Forest (RF), Decision Tree (DT), Logistic Regression (LR), and K-Nearest Neighbors (KNN) have been used to develop models based on radiomic, dosimetry, and clinical parameters. The area under the curve (AUC) of the receiver operating characteristic (ROC) curve and accuracy were used to analyze the predictive power of all models.

RESULTS

The RF and LR models based on the radiomic features of MRI and clinical/dosimetry parameters with an AUC of 0.95 and 0.93, and an accuracy of 86% and 86%, respectively, had the highest performance in the prediction of bladder radiation toxicity.

CONCLUSIONS

This study showed that, firstly, CT and MRI radiomic features of the bladder wall before treatment could be used to predict bladder radiotoxicity. Second, MRI is better than CT in predicting bladder toxicity caused by radiation. And thirdly, the performance of the predictive models based on the combination of radiomic, clinical, and dosimetry characteristics was improved.

Data Science Opportunities To Improve Radiotherapy Planning and Clinical Decision Making

Radiotherapy aims to achieve a high tumor control probability while minimizing damage to normal tissues. Personalizing radiotherapy treatments for individual patients, therefore, depends on integrating physical treatment planning with predictive models of tumor control and normal tissue complications. Predictive models could be improved using a wide range of rich data sources, including tumor and normal tissue genomics, radiomics, and dosiomics. Deep learning will drive improvements in classifying normal tissue tolerance, predicting intra-treatment tumor changes, tracking accumulated dose distributions, and quantifying the tumor response to radiotherapy based on imaging. Mechanistic patient-specific computer simulations ('digital twins') could also be used to guide adaptive radiotherapy. Overall, we are entering an era where improved modeling methods will allow the use of newly available data sources to better guide radiotherapy treatments.

Novel utilization and quantification of Xsight diaphragm tracking for respiratory motion compensation in Cyberknife Synchrony treatment of liver tumors

PURPOSE

The Xsight lung tracking system (XLTS) utilizes an advanced image processing algorithm to precisely identify the position of a tumor and determine its location in orthogonal x-ray images, instead of finding fiducials, thereby minimizing the risk of fiducial insertion-related side effects. To assess and gauge the effectiveness of CyberKnife Synchrony in treating liver tumors located in close proximity to or within the diaphragm, we employed the Xsight diaphragm tracking system (XDTS), which was based on the XLTS.

METHODS

We looked back at the treatment logs of 11 patients (8/11 [XDTS], 3/11 [Fiducial-based Target Tracking System-FTTS]) who had liver tumors in close proximity to or within the diaphragm. And the results are compared with the patients who undergo the treatment of FTTS. The breathing data information was calculated as a rolling average to reduce the effect of irregular breathing. We tested the tracking accuracy with a dynamic phantom (18023-A) on the basis of patient-specific respiratory curve.

RESULTS

The average values for the XDTS and FTTS correlation errors were 1.38 ± 0.65  versus 1.50 ± 0.26 mm (superior-inferior), 1.28 ± 0.48  versus 0.40 ± 0.09 mm (left-right), and 0.96 ± 0.32  versus 0.47 ± 0.10 mm(anterior-posterior), respectively. The prediction errors for two methods of 0.65 ± 0.16  versus 5.48 ± 3.33 mm in the S-I direction, 0.34 ± 0.10  versus 1.41 ± 0.76 mm in the A-P direction, and 0.22 ± 0.072  versus 1.22 ± 0.48 mm in the L-R direction. The coverage rate of FTTS slightly less than that of XDTS, such as 96.53 ± 8.19% (FTTS) versus 98.03 ± 1.54 (XDTS). The prediction error, the motion amplitude, and the variation of the respiratory center phase were strongly related to each other. Especially, the higher the amplitude and the variation, the higher the prediction error.

CONCLUSION

The diaphragm has the potential to serve as an alternative to gold fiducial markers for detecting liver tumors in close proximity or within it. We also found that we needed to reduce the motion amplitude and train the respiration of the patients during liver radiotherapy, as well as control and evaluate their breathing.

Deep Learning-Guided Dosimetry for Mitigating Local Failure of Patients With Non-Small Cell Lung Cancer Receiving Stereotactic Body Radiation Therapy

PURPOSE

Non-small cell lung cancer (NSCLC) stereotactic body radiation therapy with 50 Gy/5 fractions is sometimes considered controversial, as the nominal biologically effective dose (BED) of 100 Gy is felt by some to be insufficient for long-term local control of some lesions. In this study, we analyzed such patients using explainable deep learning techniques and consequently proposed appropriate treatment planning criteria. These novel criteria could help planners achieve optimized treatment plans for maximal local control.

METHODS AND MATERIALS

A total of 535 patients treated with 50 Gy/5 fractions were used to develop a novel deep learning local response model. A multimodality approach, incorporating computed tomography images, 3-dimensional dose distribution, and patient demographics, combined with a discrete-time survival model, was applied to predict time to failure and the probability of local control. Subsequently, an integrated gradient-weighted class activation mapping method was used to identify the most significant dose-volume metrics predictive of local failure and their optimal cut-points.

RESULTS

The model was cross-validated, showing an acceptable performance (c-index: 0.72, 95% CI, 0.68-0.75); the testing c-index was 0.69. The model's spatial attention was concentrated mostly in the tumors' periphery (planning target volume [PTV] - internal gross target volume [IGTV]) region. Statistically significant dose-volume metrics in improved local control were BED Dnear-min ≥ 103.8 Gy in IGTV (hazard ratio [HR], 0.31; 95% CI, 015-0.63), V104 ≥ 98% in IGTV (HR, 0.30; 95% CI, 0.15-0.60), gEUD ≥ 103.8 Gy in PTV-IGTV (HR, 0.25; 95% CI, 0.12-0.50), and Dmean ≥ 104.5 Gy in PTV-IGTV (HR, 0.25; 95% CI, 0.12-0.51).

CONCLUSIONS

Deep learning-identified dose-volume metrics have shown significant prognostic power (log-rank, P = .003) and could be used as additional actionable criteria for treatment planning in NSCLC stereotactic body radiation therapy patients receiving 50 Gy in 5 fractions. Although our data do not confirm or refute that a significantly higher BED for the prescription dose is necessary for tumor control in NSCLC, it might be clinically effective to escalate the nominal prescribed dose from BED 100 to 105 Gy.

Modulation of Ionizing Radiation-Induced Apoptosis by Taurine in Human Peripheral Blood Lymphocytes: Flow Cytometry-based Quantification

Background

Radiotherapy, a highly effective method of radiation-based treating cancers, can reduce the size of tumors and affect healthy tissues. Radiation-induced lymphopenia as a side effect of radiation therapy can reduce the effectiveness of the treatment.

Objective

This study aimed to examine how taurine can protect peripheral blood lymphocytes from radiation-based apoptosis.

Material and Methods

In this experimental study, the effects of the taurine on lymphocytes were studied, and blood samples were divided into three groups: a negative control group that was not treated, a positive control group that was treated with cysteine (100 μg/ml), and a group that was treated with taurine (100 µg. mL-1) in three different doses (4, 8 & 12 Gy) before irradiation. The percentage of apoptotic and necrotic lymphocytes was measured using flow cytometry 48 and 72 hours after the irradiation, respectively.

Results

According to the groups treated with taurine, the number of lymphocytes undergoing apoptosis was lower and higher compared to the negative and positive control groups, respectively. The decrease in this value was more pronounced 48 hours after radiation compared to 72 hours. Furthermore, there was a slight increase in the number of apoptotic lymphocytes with increasing radiation dose.

Conclusion

Taurine effectively protects human peripheral blood lymphocytes from radiation-based apoptosis.

Improved outcome models with denoising diffusion

PURPOSE

Radiotherapy outcome modelling often suffers from class imbalance in the modelled endpoints. One of the main options to address this issue is by introducing new synthetically generated datapoints, using generative models, such as Denoising Diffusion Probabilistic Models (DDPM). In this study, we implemented DDPM to improve performance of a tumor local control model, trained on imbalanced dataset, and compare this approach with other common techniques.

METHODS

A dataset of 535 NSCLC patients treated with SBRT (50 Gy/5 fractions) was used to train a deep learning outcome model for tumor local control prediction. The dataset included complete treatment planning data (planning CT images, 3D planning dose distribution and patient demographics) with sparsely distributed endpoints (6-7 % experiencing local failure). Consequently, we trained a novel conditional 3D DDPM model to generate synthetic treatment planning data. Synthetically generated treatment planning datapoints were used to supplement the real training dataset and the improvement in the model's performance was studied. Obtained results were also compared to other common techniques for class imbalanced training, such as Oversampling, Undersampling, Augmentation, Class Weights, SMOTE and ADASYN.

RESULTS

Synthetic DDPM-generated data were visually trustworthy, with Fréchet inception distance (FID) below 50. Extending the training dataset with the synthetic data improved the model's performance by more than 10%, while other techniques exhibited only about 4% improvement.

CONCLUSIONS

DDPM introduces a novel approach to class-imbalanced outcome modelling problems. The model generates realistic synthetic radiotherapy planning data, with a strong potential to increase performance and robustness of outcome models.

Radiomics based predictive modeling of rectal toxicity in prostate cancer patients undergoing radiotherapy: CT and MRI comparison

BACKGROUND

Rectal toxicity is one of the common side effects after radiotherapy in prostate cancer patients. Radiomics is a non-invasive and low-cost method for developing models of predicting radiation toxicity that does not have the limitations of previous methods. These models have been developed using individual patients' information and have reliable and acceptable performance. This study was conducted by evaluating the radiomic features of computed tomography (CT) and magnetic resonance (MR) images and using machine learning (ML) methods to predict radiation-induced rectal toxicity.

METHODS

Seventy men with pathologically confirmed prostate cancer, eligible for three-dimensional radiation therapy (3DCRT) participated in this prospective trial. Rectal wall CT and MR images were used to extract first-order, shape-based, and textural features. The least absolute shrinkage and selection operator (LASSO) was used for feature selection. Classifiers such as Random Forest (RF), Decision Tree (DT), Logistic Regression (LR), and K-Nearest Neighbors (KNN) were used to create models based on radiomic, dosimetric, and clinical data alone or in combination. The area under the curve (AUC) of the receiver operating characteristic curve (ROC), accuracy, sensitivity, and specificity were used to assess each model's performance.

RESULTS

The best outcomes were achieved by the radiomic features of MR images in conjunction with clinical and dosimetric data, with a mean of AUC: 0.79, accuracy: 77.75%, specificity: 82.15%, and sensitivity: 67%.

CONCLUSIONS

This research showed that as radiomic signatures for predicting radiation-induced rectal toxicity, MR images outperform CT images.

Efficacy of a Second Course of Radiation for Patients With Metachronous Hepatocellular Carcinoma

PURPOSE

Liver-directed radiation therapy is an effective treatment for hepatocellular carcinoma (HCC), but metachronous lesions develop outside the irradiated field in >50% of patients. We hypothesized that irradiation of these new lesions would produce an outcome like that of patients receiving a first course (C1) of treatment.

METHODS AND MATERIALS

We included patients with HCC who received a second course (C2) of radiation therapy >1 month after C1. Toxicity was defined as Child-Pugh score increase ≥2 within 6 months posttreatment (binary model) and as the change in albumin-bilirubin during the year after treatment (longitudinal model). Overall survival (OS) and local failure (LF) were captured at the patient and lesion level, respectively; both were summarized with Kaplan-Meier estimates. Predictors of toxicity and OS were assessed using generalized linear mixed and Cox regression models, respectively.

RESULTS

Of 340 patients with HCC, 47 underwent irradiation for metachronous HCC, receiving similar prescription dose in C1/C2. Median follow-up was 17 months after C1 and 15 months after C2. Twenty-two percent of patients experienced toxicity after C1, and 25% experienced toxicity after C2. Worse baseline albumin-bilirubin predicted toxicity in both binary (odds ratio, 2.40; 95% CI, 1.46-3.94; P = .0005) and longitudinal models (P < .005). Two-year LF rate was 11.2% after C1 and 8.3% after C2; tumor dose (hazard ratio [HR], 0.982; 95% CI, 0.969-0.995; P = .007) and tumor size (HR, 1.135; 95% CI, 1.068-1.206; P < .005) predicted LF. Two-year OS was 46.0% after C1 and 42.6% after C2; tumor dose (HR, 0.986; 95% CI, 0.979-0.992; P < .005) and tumor size (HR, 1.049; 95% CI, 1.010-1.088; P = .0124) predicted OS. Reirradiation was not associated with toxicity (P > .7), LF (P = .79), or OS (P = .39).

CONCLUSIONS

In this largest series in the Western hemisphere, we demonstrate that irradiation for metachronous HCC offers low rates of LF with acceptable toxicity and OS like that of patients receiving a C1. These findings support judicious selection of patients for reirradiation in metachronous HCC.

Deep learning prediction of post-SBRT liver function changes and NTCP modeling in hepatocellular carcinoma based on DGAE-MRI

BACKGROUND

Stereotactic body radiation therapy (SBRT) produces excellent local control for patients with hepatocellular carcinoma (HCC). However, the risk of toxicity for normal liver tissue is still a limiting factor. Normal tissue complication probability (NTCP) models have been proposed to estimate the toxicity with the assumption of uniform liver function distribution, which is not optimal. With more accurate regional liver functional imaging available for individual patient, we can improve the estimation and be more patient-specific.

PURPOSE

To develop normal tissue complication probability (NTCP) models using pre-/during-treatment (RT) dynamic Gadoxetic Acid-enhanced (DGAE) MRI for adaptation of RT in a patient-specific manner in hepatocellular cancer (HCC) patients who receive SBRT.

METHODS

24 of 146 HCC patients who received SBRT underwent DGAE MRI. Physical doses were converted into EQD2 for analysis. Voxel-by-voxel quantification of the contrast uptake rate (k1) from DGAE-MRI was used to quantify liver function. A logistic dose-response model was used to estimate the fraction of liver functional loss, and NTCP was estimated using the cumulative functional reserve model for changes in Child-Pugh (C-P) scores. Model parameters were calculated using maximum-likelihood estimations. During-RT liver functional maps were predicted from dose distributions and pre-RT k1 maps with a conditional Wasserstein generative adversarial network (cWGAN). Imaging prediction quality was assessed using root-mean-square error (RMSE) and structural similarity (SSIM) metrics. The dose-response and NTCP were fit on both original and cWGAN predicted images and compared using a Wilcoxon signed-rank test.

RESULTS

Logistic dose response models for changes in k1 yielded D50 of 35.2 (95% CI: 26.7-47.5) Gy and k of 0.62 (0.49-0.75) for the whole population. The high baseline ALBI (poor liver function) subgroup showed a significantly smaller D50 of 11.7 (CI: 9.06-15.4) Gy and larger k of 0.96 (CI: 0.74-1.22) compared to a low baseline ALBI (good liver function) subgroup of 54.8 (CI: 38.3-79.1) Gy and 0.59 (CI: 0.48-0.74), with p-values of < 0.001 and = 0.008, respectively, which indicates higher radiosensitivity for the worse baseline liver function cohort. Subset analyses were also performed for high/low baseline CP subgroups. The corresponding NTCP models showed good agreement for the fit parameters between cWGAN predicted and the ground-truth during-RT images with no statistical differences for low ALBI subgroup.

CONCLUSIONS

NTCP models which incorporate voxel-wise functional information from DGAE-MRI k1 maps were successfully developed and feasibility was demonstrated in a small patient cohort. cWGAN predicted functional maps show promise for estimating localized patient-specific response to RT and warrant further validation in a larger patient cohort.

Evolution of Response-Based Radiotherapy for Hepatocellular Cancer

ABSTRACT

Stereotactic body radiation therapy has emerged as a safe and effective treatment modality for properly selected hepatocellular cancer (HCC) patients with normal liver function. However, many HCC patients have reduced baseline liver function due to underlying cirrhosis or prior liver-directed therapies. Therefore, because of the increased risk of hepatotoxicity, the use of stereotactic body radiation therapy for patients with reduced liver function has been approached with caution. Individualized, response-based radiotherapy incorporates models, imaging tools, and biomarkers that determine the dose-response relationship of the liver before, during, and after treatment and has been useful in reducing the likelihood of liver damage without sacrificing tumor control. This review discusses the evolution of response-based radiotherapy for HCC and highlights areas for further investigation.

The Effect of Stereotactic Body Radiation Therapy for Hepatocellular Cancer on Regional Hepatic Liver Function

PURPOSE

To investigate direct radiation dose-related and inflammation-mediated regional hepatic function losses after stereotactic body radiation therapy (SBRT) in patients with hepatocellular carcinoma (HCC) and poor liver function.

METHODS AND MATERIALS

Twenty-four patients with HCC enrolled on an IRB-approved adaptive SBRT trial had liver dynamic gadoxetic acid-enhanced magnetic resonance imaging and blood sample collections before and 1 month after SBRT. Gadoxetic acid uptake rate (k1) maps were quantified for regional hepatic function and coregistered to both 2-Gy equivalent dose and physical dose distributions. Regional k1 loss patterns from before to after SBRT were analyzed for effects of dose and patient using a mixed-effects model and logistic function and were associated with pretherapy liver-function albumin-bilirubin scores. Plasma levels of tumor necrosis factor α receptor 1 (TNFR1), an inflammation marker, were correlated with mean k1 losses in the lowest dose regions by Spearman rank correlation.

RESULTS

The whole group had a k1 loss rate of 0.4%/Gy (2-Gy equivalent dose); however, there was a significant random effect of patient in the mixed-effect model (P < .05). Patients with poor and good liver functions lost 50% of k1 values at 12.5 and 57.2 Gy and 33% and 16% of k1 values at the lowest dose regions (<5 Gy), respectively. The k1 losses at the lowest dose regions of individual patients were significantly correlated with their TNFR1 levels after SBRT (P < .02).

CONCLUSIONS

The findings suggest that regional hepatic function losses after SBRT in patients with HCC include both direct radiation dose-dependent and inflammation-mediated effects, which could influence how to manage these patients to preserve their liver function after SBRT.

Predictive Model of Liver Toxicity to Aid the Personalized Selection of Proton Versus Photon Therapy in Hepatocellular Carcinoma

PURPOSE

Our objective was to develop an externally validated model for predicting liver toxicity after radiation therapy in patients with hepatocellular carcinoma (HCC) that can integrate both photon and proton dose distributions with patient-specific characteristics.

METHODS AND MATERIALS

Training data consisted of all patients with HCC treated between 2008 and 2019 at our institution (n = 117, 60%/40% photon/proton). We developed a shallow convolutional neural network (CNN) to predict posttreatment liver dysfunction from the differential dose-volume histogram (DVH) and baseline liver metrics. To reduce bias and improve robustness, we used ensemble learning (CNNE). After a preregistered study analysis plan, we evaluated stability using internal bootstrap resampling and generalizability using a data set from a different institution (n = 88). Finally, we implemented a class activation map method to characterize the critical DVH subregions and benchmarked the model against logistic regression and XGBoost. The models were evaluated using the area under the receiver operating characteristic curve and area under the precision-recall curve.

RESULTS

The CNNE model showed similar internal performance and robustness compared with the benchmarks. CNNE exceeded the benchmark models in external validation, with an area under the receiver operating characteristic curve of 0.78 versus 0.55 to 0.70, and an area under the precision-recall curve of 0.6 versus 0.43 to 0.52. The model showed improved predictive power in the photon group, excellent specificity in both modalities, and high sensitivity in the photon high-risk group. Models built solely on DVHs confirm outperformance of the CNNE and indicate that the proposed structure efficiently abstracts features from both proton and photon dose distributions. The activation map method demonstrates the importance of the low-dose bath and its interaction with low liver function at baseline.

CONCLUSIONS

We developed and externally validated a patient-specific prediction model for hepatic toxicity based on the entire DVH and clinical factors that can integrate both photon and proton therapy cohorts. This model complements the new American Society for Radiation Oncology clinical practice guidelines and could support value-driven integration of proton therapy into the management of HCC.

Potential benefits of using radioactive ion beams for range margin reduction in carbon ion therapy

Sharp dose gradients and high biological effectiveness make ions such as ¹²C an ideal tool to treat deep-seated tumors, however, at the same time, sensitive to errors in the range prediction. Tumor safety margins mitigate these uncertainties, but during the irradiation they lead to unavoidable damage to the surrounding healthy tissue. To fully exploit the Bragg peak benefits, a large effort is put into establishing precise range verification methods. Despite positron emission tomography being widely in use for this purpose in ¹²C therapy, the low count rates, biological washout, and broad activity distribution still limit its precision. Instead, radioactive beams used directly for treatment would yield an improved signal and a closer match with the dose fall-off, potentially enabling precise in vivo beam range monitoring. We have performed a treatment planning study to estimate the possible impact of the reduced range uncertainties, enabled by radioactive ¹¹C ions treatments, on sparing critical organs in tumor proximity. Compared to ¹²C treatments, (i) annihilation maps for ¹¹C ions can reflect sub- millimeter shifts in dose distributions in the patient, (ii) outcomes of treatment planning with ¹¹C significantly improve and (iii) less severe toxicities for serial and parallel critical organs can be expected.

A human-in-the-loop based Bayesian network approach to improve imbalanced radiation outcomes prediction for hepatocellular cancer patients with stereotactic body radiotherapy

Background

Imbalanced outcome is one of common characteristics of oncology datasets. Current machine learning approaches have limitation in learning from such datasets. Here, we propose to resolve this problem by utilizing a human-in-the-loop (HITL) approach, which we hypothesize will also lead to more accurate and explainable outcome prediction models.

Methods

A total of 119 HCC patients with 163 tumors were used in the study. 81 patients with 104 tumors from the University of Michigan Hospital treated with SBRT were considered as a discovery dataset for radiation outcomes model building. The external testing dataset included 59 tumors from 38 patients with SBRT from Princess Margaret Hospital. In the discovery dataset, 100 tumors from 77 patients had local control (LC) (96% of 104 tumors) and 23 patients had at least one grade increment of ALBI (I-ALBI) during six-month follow up (28% of 81 patients). Each patient had a total of 110 features, where 15 or 20 features were identified by physicians as expert knowledge features (EKFs) for LC or I-ALBI prediction. We proposed a HITL based Bayesian network (HITL-BN) approach to enhance the capability of selecting important features from imbalanced data in terms of accuracy and explainability through humans' participation by integrating feature importance ranking and Markov blanket algorithms. A pure data-driven Bayesian network (PD-BN) method was applied to the same discovery dataset of HCC patients as a benchmark.

Results

In the training and testing phases, the areas under receiver operating characteristic curves of the HITL-BN models for LC or I-ALBI prediction during SBRT are 0.85 (95% confidence interval: 0.75-0.95) or 0.89 (0.81-0.95) and 0.77 or 0.78, respectively. They significantly outperformed the during-treatment PD-BN model in predicting LC or I-ALBI based on the discovery cross-validation and testing datasets from the Delong tests.

Conclusion

By allowing the human expert to be part of the model building process, the HITL-BN approach yielded significantly improved accuracy as well as better explainability when dealing with imbalanced outcomes in the prediction of post-SBRT treatment response of HCC patients when compared to the PD-BN method.

Machine learning-based normal tissue complication probability model for predicting albumin-bilirubin (ALBI) grade increase in hepatocellular carcinoma patients

PURPOSE

The aim of this study was to develop a normal tissue complication probability model using a machine learning approach (ML-based NTCP) to predict the risk of radiation-induced liver disease in hepatocellular carcinoma (HCC) patients.

MATERIALS AND METHODS

The study population included 201 HCC patients treated with radiotherapy. The patients' medical records were retrospectively reviewed to obtain the clinical and radiotherapy data. Toxicity was defined by albumin-bilirubin (ALBI) grade increase. The normal liver dose-volume histogram was reduced to mean liver dose (MLD) based on the fraction size-adjusted equivalent uniform dose (2 Gy/fraction and α/β = 2). Three types of ML-based classification models were used, a penalized logistic regression (PLR), random forest (RF), and gradient-boosted tree (GBT) model. Model performance was compared using the area under the receiver operating characteristic curve (AUROC). Internal validation was performed by 5-fold cross validation and external validation was done in 44 new patients.

RESULTS

Liver toxicity occurred in 87 patients (43.1%). The best individual model was the GBT model using baseline liver function, liver volume, and MLD as inputs and the best overall model was an ensemble of the PLR and GBT models. An AUROC of 0.82 with a standard deviation of 0.06 was achieved for the internal validation. An AUROC of 0.78 with a standard deviation of 0.03 was achieved for the external validation. The behaviors of the best GBT model were also in good agreement with the domain knowledge on NTCP.

CONCLUSION

We propose the methodology to develop an ML-based NTCP model to estimate the risk of ALBI grade increase.

Role of Functional MRI in Liver SBRT: Current Use and Future Directions

Stereotactic body radiation therapy (SBRT) is an emerging treatment for liver cancers whereby large doses of radiation can be delivered precisely to target lesions in 3-5 fractions. The target dose is limited by the dose that can be safely delivered to the non-tumour liver, which depends on the baseline liver functional reserve. Current liver SBRT guidelines assume uniform liver function in the non-tumour liver. However, the assumption of uniform liver function is false in liver disease due to the presence of cirrhosis, damage due to previous chemo- or ablative therapies or irradiation, and fatty liver disease. Anatomical information from magnetic resonance imaging (MRI) is increasingly being used for SBRT planning. While its current use is limited to the identification of target location and size, functional MRI techniques also offer the ability to quantify and spatially map liver tissue microstructure and function. This review summarises and discusses the advantages offered by functional MRI methods for SBRT treatment planning and the potential for adaptive SBRT workflows.

Current status and future developments in predicting outcomes in radiation oncology

Advancements in data-driven technologies and the inclusion of information-rich multiomics features have significantly improved the performance of outcomes modeling in radiation oncology. For this current trend to be sustainable, challenges related to robust data modeling such as small sample size, low size to feature ratio, noisy data, as well as issues related to algorithmic modeling such as complexity, uncertainty, and interpretability, need to be mitigated if not resolved. Emerging computational technologies and new paradigms such as federated learning, human-in-the-loop, quantum computing, and novel interpretability methods show great potential in overcoming these challenges and bridging the gap towards precision outcome modeling in radiotherapy. Examples of these promising technologies will be presented and their potential role in improving outcome modeling will be discussed.

Predictive performance of different NTCP techniques for radiation-induced esophagitis in NSCLC patients receiving proton radiotherapy

This study aimed to compare the predictive performance of different modeling methods in developing normal tissue complication probability (NTCP) models for predicting radiation-induced esophagitis (RE) in non–small cell lung cancer (NSCLC) patients receiving proton radiotherapy. The dataset was composed of 328 NSCLC patients receiving passive-scattering proton therapy and 41.6% of the patients experienced ≥ grade 2 RE. Five modeling methods were used to build NTCP models: standard Lyman–Kutcher–Burman (sLKB), generalized LKB (gLKB), multivariable logistic regression using two variable selection procedures-stepwise forward selection (Stepwise-MLR), and least absolute shrinkage and selection operator (LASSO-MLR), and support vector machines (SVM). Predictive performance was internally validated by a bootstrap approach for each modeling method. The overall performance, discriminative ability, and calibration were assessed using the Negelkerke R², area under the receiver operator curve (AUC), and Hosmer–Lemeshow test, respectively. The LASSO-MLR model showed the best discriminative ability with an AUC value of 0.799 (95% confidence interval (CI): 0.763–0.854), and the best overall performance with a Negelkerke R² value of 0.332 (95% CI: 0.266–0.486). Both of the optimism-corrected Negelkerke R² values of the SVM and sLKB models were 0.301. The optimism-corrected AUC of the gLKB model (0.796) was higher than that of the SVM model (0.784). The sLKB model had the smallest optimism in the model variation and discriminative ability. In the context of classification and probability estimation for predicting the NTCP for radiation-induced esophagitis, the MLR model developed with LASSO provided the best predictive results. The simplest LKB modeling had similar or even better predictive performance than the most complex SVM modeling, and it was least likely to overfit the training data. The advanced machine learning approach might have limited applicability in clinical settings with a relatively small amount of data.

Leveraging Blood-Based Diagnostics to Predict Tumor Biology and Extend the Application and Personalization of Radiotherapy in Liver Cancers

While the incidence of primary liver cancers has been increasing worldwide over the last few decades, the mortality has remained consistently high. Most patients present with underlying liver disease and have limited treatment options. In recent years, radiotherapy has emerged as a promising approach for some patients; however, the risk of radiation induced liver disease (RILD) remains a limiting factor for some patients. Thus, the discovery and validation of biomarkers to measure treatment response and toxicity is critical to make progress in personalizing radiotherapy for liver cancers. While tissue biomarkers are optimal, hepatocellular carcinoma (HCC) is typically diagnosed radiographically, making tumor tissue not readily available. Alternatively, blood-based diagnostics may be a more practical option as blood draws are minimally invasive, widely availability and may be performed serially during treatment. Possible blood-based diagnostics include indocyanine green test, plasma or serum levels of HGF or cytokines, circulating blood cells and genomic biomarkers. The albumin–bilirubin (ALBI) score incorporates albumin and bilirubin to subdivide patients with well-compensated underlying liver dysfunction (Child–Pugh score A) into two distinct groups. This review provides an overview of the current knowledge on circulating biomarkers and blood-based scores in patients with malignant liver disease undergoing radiotherapy and outlines potential future directions.

Predictive Modeling of Survival and Toxicity in Patients With Hepatocellular Carcinoma After Radiotherapy

PURPOSE

To stratify patients and aid clinical decision making, we developed machine learning models to predict treatment failure and radiation-induced toxicities after radiotherapy (RT) in patients with hepatocellular carcinoma across institutions.

MATERIALS AND METHODS

The models were developed using linear and nonlinear algorithms, predicting survival, nonlocal failure, radiation-induced liver disease, and lymphopenia from baseline patient and treatment parameters. The models were trained on 207 patients from Massachusetts General Hospital. Performance was quantified using Harrell's c-index, area under the curve (AUC), and accuracy in high-risk populations. Models' structures were optimized in a nested cross-validation approach to prevent overfitting. A study analysis plan was registered before external validation using 143 patients from MD Anderson Cancer Center. Clinical utility was assessed using net-benefit analysis.

RESULTS

The survival model stratified high-risk versus low-risk patients well in the external validation cohort (c-index = 0.75), better than existing risk scores. Predictions of 1-year survival and nonlocal failure were excellent (external AUC = 0.74 and 0.80, respectively), especially in the high-risk group (accuracy > 90%). Cause-of-death analysis showed differential modes of treatment failure in these cohorts and indicated that these models could be used to stratify RT patients for liver-sparing treatment regimen or combination approaches with systemic agents. Predictions of liver disease and lymphopenia were good but less robust (external AUC = 0.68 and 0.7, respectively), suggesting the need for more comprehensive consideration of dosimetry and better predictive biomarkers. The liver disease model showed excellent accuracy in the high-risk group (92%) and revealed possible interactions of platelet count with initial liver function.

CONCLUSION

Machine learning approaches can provide reliable outcome predictions in patients with hepatocellular carcinoma after RT in diverse cohorts across institutions. The excellent performance, particularly in high-risk patients, suggests novel strategies for patient stratification and treatment selection.

Potential Defects and Improvements of Equivalent Uniform Dose Prediction Model Based on the Analysis of Radiation-Induced Brain Injury

PURPOSE

To study the impact of dose distribution on volume-effect parameter and predictive ability of equivalent uniform dose (EUD) model, and to explore the improvements.

METHODS AND MATERIALS

The brains of 103 nasopharyngeal carcinoma patients treated with IMRT were segmented according to dose distribution (brain and left/right half-brain for similar distributions but different sizes; V _D with different D for different distributions). Predictive ability of EUD_{V D} (EUD of V _D ) for radiation-induced brain injury was assessed by receiver operating characteristics curve (ROC) and area under the curve (AUC). The optimal volume-effect parameter a of EUD was selected when AUC was maximal (mAUC). Correlations between mAUC, a and D were analyzed by Pearson correlation analysis. Both mAUC and a in brain and half-brain were compared by using paired samples t-tests. The optimal D _V and V _D points were selected for a simple comparison.

RESULTS

The mAUC of brain/half-brain EUD was 0.819/0.821 and the optimal a value was 21.5/22. When D increased, mAUC of EUD_{V D} increased, while a decreased. The mAUC reached the maximum value when D was 50-55 Gy, and a was always 1 when D ≥55 Gy. The difference of mAUC/a between brain and half-brain was not significant. If a was in range of 1 to 22, AUC of brain/half-brain EUD_{V55 Gy} (0.857-0.830/0.845-0.830) was always larger than that of brain/half-brain EUD (0.681-0.819/0.691-0.821). The AUCs of optimal dose/volume points were 0.801 (brain D_{2.5 cc}), 0.823 (brain V_{70 Gy}), 0.818 (half-brain D_{1 cc}), and 0.827 (half-brain V_{69 Gy}), respectively. Mean dose (equal to EUD_{V D} with a = 1) of high-dose volume (V_{50 Gy}-V_{60 Gy}) was superior to traditional EUD and dose/volume points.

CONCLUSION

Volume-effect parameter of EUD is variable and related to dose distribution. EUD with large low-dose volume may not be better than simple dose/volume points. Critical-dose-volume EUD could improve the predictive ability and has an invariant volume-effect parameter. Mean dose may be the case in which critical-dose-volume EUD has the best predictive ability.

Toward MR-integrated proton therapy: modeling the potential benefits for liver tumors

Magnetic resonance imaging (MRI)-integrated proton therapy (MRiPT) is envisioned to improve treatment quality for many cancer patients. However, given the availability of alternative image-guided strategies, its clinical need is yet to be justified. This study aims to compare the expected clinical outcomes of MRiPT with standard of practice cone-beam CT (CBCT)-guided PT, and other MR-guided methods, i.e. offline MR-guided PT and MR-linac, for treatment of liver tumors. Clinical outcomes were assessed by quantifying the dosimetric and biological impact of target margin reduction enabled by each image-guided approach. Planning target volume (PTV) margins were calculated using random and systematic setup, delineation and motion uncertainties, which were quantified by analyzing longitudinal MRI data for 10 patients with liver tumors. Proton treatment plans were created using appropriate PTV margins for each image-guided PT method. Photon plans with margins equivalent to MRiPT were generated to represent MR-linac. Normal tissue complication probabilities (NTCP) of the uninvolved liver were compared. We found that PTV margin can be reduced by 20% and 40% for offline MR-guided PT and MRiPT, respectively, compared with CBCT-guided PT. Furthermore, clinical target volume expansion could be largely alleviated when delineating on MRI rather than CT. Dosimetric implications included decreased equivalent mean dose of the uninvolved liver, i.e. up to 24.4 Gy and 27.3 Gy for offline MR-guided PT and MRiPT compared to CBCT-guided PT, respectively. Considering Child-Pugh score increase as endpoint, NTCP of the uninvolved liver was significantly decreased for MRiPT compared to CBCT-guided PT (up to 48.4%,p < 0.01), offline MR-guided PT (up to 12.9%,p < 0.01) and MR-linac (up to 30.8%,p < 0.05). Target underdose was possible in the absence of MRI-guidance (D90 reduction up to 4.2 Gy in 20% of cases). In conclusion, MRiPT has the potential to significantly reduce healthy liver toxicities in patients with liver tumors. It is superior to other image-guided techniques currently available.

Toward Personalized Medicine in Radiotherapy of Hepatocellular Carcinoma: Emerging Radiomic Biomarker Candidates of Response and Toxicity

Radiology and radiotherapy are currently undergoing radical transformation with use of biomarkers and digital technologies such as artificial intelligence. These current and upcoming changes in radiology speak of an overarching new vision for personalized medicine. This is particularly evident in the case of radiotherapy of cancers, and of liver cancer in particular. The development of modern radiotherapy with stereotactic body radiotherapy allows targeted treatments to be delivered to the tumor site, limiting the dose to surrounding healthy organs, thus becoming a new therapeutic alternative for hepatocellular carcinoma and other liver tumors. However, not all patients have the same response to radiotherapy or display the same side-effect profile. Biomarkers of response and toxicity in liver radiotherapy would facilitate the vision and practice of personalized medicine. This expert review examines the available molecular, radiomic, and radiogenomic biomarker candidates for acute liver toxicity with potential use for prediction of radiotherapy-induced liver toxicity. To this end, I highlight for oncologists and life scientists that radiomics allows diagnostic images to be analyzed using computer algorithms to extract information imperceptible to the human eye and of relevance to forecasting clinical outcomes. This article underscores particularly (1) the microRNA-based biomarker candidates as among the most promising predictors of radiation-induced liver toxicity and (2) the texture features in radiomic analyses for response prediction. Radiotherapy of hepatocellular carcinoma is edging toward personalized medicine with emerging radiomic biomarker candidates. Future large-scale biomarker studies are called for to enable personalized medicine in liver cancers.

Multi-parametric MRI (mpMRI) for treatment response assessment of radiation therapy

Magnetic resonance imaging (MRI) plays an important role in the modern radiation therapy (RT) workflow. In comparison with computed tomography (CT) imaging, which is the dominant imaging modality in RT, MRI possesses excellent soft-tissue contrast for radiographic evaluation. Based on quantitative models, MRI can be used to assess tissue functional and physiological information. With the developments of scanner design, acquisition strategy, advanced data analysis, and modeling, multiparametric MRI (mpMRI), a combination of morphologic and functional imaging modalities, has been increasingly adopted for disease detection, localization, and characterization. Integration of mpMRI techniques into RT enriches the opportunities to individualize RT. In particular, RT response assessment using mpMRI allows for accurate characterization of both tissue anatomical and biochemical changes to support decision-making in monotherapy of radiation treatment and/or systematic cancer management. In recent years, accumulating evidence have, indeed, demonstrated the potentials of mpMRI in RT response assessment regarding patient stratification, trial benchmarking, early treatment intervention, and outcome modeling. Clinical application of mpMRI for treatment response assessment in routine radiation oncology workflow, however, is more complex than implementing an additional imaging protocol; mpMRI requires additional focus on optimal study design, practice standardization, and unified statistical reporting strategy to realize its full potential in the context of RT. In this article, the mpMRI theories, including image mechanism, protocol design, and data analysis, will be reviewed with a focus on the radiation oncology field. Representative works will be discussed to demonstrate how mpMRI can be used for RT response assessment. Additionally, issues and limits of current works, as well as challenges and potential future research directions, will also be discussed.

Current Understanding of Ablative Radiation Therapy in Hepatocellular Carcinoma

The role of ablative stereotactic body radiotherapy (SBRT) in hepatocellular carcinoma (HCC) has been evolving over the last few decades. SBRT has mostly been used in early stages of HCC, including few (≤ 3 in number) tumors, small tumours (< 3 cm in size), as well as larger tumours which are ineligible for other ablative modalities, mostly without vascular invasion. In early stage HCC, SBRT is used as a definitive treatment with curative intent or with intent to bridge to liver transplant. Retrospective and prospective institutional series document a high rate of local control (68–95% at 3 years) following SBRT. This coupled with a low risk of toxicity makes this non-invasive ablative treatment an attractive option for patients who are ineligible for other ablative treatments. Small randomized studies of ablative radiation have also shown non-inferiority of radiation as compared to radiofrequency ablation (RFA). Currently, SBRT is widely available as a safe and effective liver directed therapy, although there is a need for more studies providing higher level evidence. This review gives a brief overview of SBRT and the evidence for its use in HCC patients with ablative intent.

Assessment of the confidence interval in the multivariable normal tissue complication probability model for predicting radiation-induced liver disease in primary liver cancer

We developed a confidence interval-(CI) assessing model in multivariable normal tissue complication probability (NTCP) modeling for predicting radiation-induced liver disease (RILD) in primary liver cancer patients using clinical and dosimetric data. Both the mean NTCP and difference in the mean NTCP (ΔNTCP) between two treatment plans of different radiotherapy modalities were further evaluated and their CIs were assessed. Clinical data were retrospectively reviewed in 322 patients with hepatocellular carcinoma (n = 215) and intrahepatic cholangiocarcinoma (n = 107) treated with photon therapy. Dose-volume histograms of normal liver were reduced to mean liver dose (MLD) based on the fraction size-adjusted equivalent uniform dose. The most predictive variables were used to build the model based on multivariable logistic regression analysis with bootstrapping. Internal validation was performed using the cross-validation leave-one-out method. Both the mean NTCP and the mean ΔNTCP with 95% CIs were calculated from computationally generated multivariate random sets of NTCP model parameters using variance-covariance matrix information. RILD occurred in 108/322 patients (33.5%). The NTCP model with three clinical and one dosimetric parameter (tumor type, Child-Pugh class, hepatitis infection status and MLD) was most predictive, with an area under the receiver operative characteristics curve (AUC) of 0.79 (95% CI 0.74-0.84). In eight clinical subgroups based on the three clinical parameters, both the mean NTCP and the mean ΔNTCP with 95% CIs were able to be estimated computationally. The multivariable NTCP model with the assessment of 95% CIs has potential to improve the reliability of the NTCP model-based approach to select the appropriate radiotherapy modality for each patient.

Radiomic and radiogenomic modeling for radiotherapy: strategies, pitfalls, and challenges

The power of predictive modeling for radiotherapy outcomes has historically been limited by an inability to adequately capture patient-specific variabilities; however, next-generation platforms together with imaging technologies and powerful bioinformatic tools have facilitated strategies and provided optimism. Integrating clinical, biological, imaging, and treatment-specific data for more accurate prediction of tumor control probabilities or risk of radiation-induced side effects are high-dimensional problems whose solutions could have widespread benefits to a diverse patient population-we discuss technical approaches toward this objective. Increasing interest in the above is specifically reflected by the emergence of two nascent fields, which are distinct but complementary: radiogenomics, which broadly seeks to integrate biological risk factors together with treatment and diagnostic information to generate individualized patient risk profiles, and radiomics, which further leverages large-scale imaging correlates and extracted features for the same purpose. We review classical analytical and data-driven approaches for outcomes prediction that serve as antecedents to both radiomic and radiogenomic strategies. Discussion then focuses on uses of conventional and deep machine learning in radiomics. We further consider promising strategies for the harmonization of high-dimensional, heterogeneous multiomics datasets (panomics) and techniques for nonparametric validation of best-fit models. Strategies to overcome common pitfalls that are unique to data-intensive radiomics are also discussed.

The Potential for Midtreatment Albumin-Bilirubin (ALBI) Score to Individualize Liver Stereotactic Body Radiation Therapy

PURPOSE

Our individualized functional response adaptive approach to liver stereotactic body radiation therapy (SBRT) with assessment of indocyanine green (ICG) retention at baseline and midtreatment to detect subclinical changes in liver function, permitting dose adjustment, has decreased toxicity while preserving efficacy. We hypothesized that assessment of the albumin-bilirubin (ALBI) score at baseline and midtreatment would allow for more practical identification of patients at risk for treatment-related toxicity (TRT).

METHODS AND MATERIALS

Patients with hepatocellular carcinoma were treated on 3 prospective institutional review board-approved trials using baseline and midtreatment ICG to deliver individualized functional response adaptive liver SBRT. Patients received 3 or 5 fractions, with fraction 3 followed by a 1-month treatment break. TRT was a ≥2-point rise in Child-Pugh score within 6 months of SBRT. Logistic regression was used to estimate odds ratios (ORs) and confidence intervals (CIs) for assessment of TRT. Area under the receiver operating curve was used to compare predictive ability across models.

RESULTS

In total, 151 patients underwent 166 treatments. Baseline Child-Pugh class and ALBI grade were A (66.9%), B (31.3%), or C (1.8%) and 1 (25.9%), 2 (65.7%), or 3 (8.4%), respectively. Thirty-five patients (20.3%) experienced TRT. On univariate analysis, baseline ALBI (OR, 1.8; 95% CI, 1.24-2.62; P = .02), baseline ICG (OR, 1.66; 95% CI, 1.17-2.35; P = .04), and change in ALBI (OR, 3.07; 95% CI, 1.29-7.32; P = .003) were associated with increased odds of TRT. ALBI-centric models performed similarly to ICG-centric models on multivariate analyses predicting toxicity (area under the receiver operating curve of 0.79 for both). In a model incorporating baseline and midtreatment change in ALBI and ICG, both ALBI values were statistically significantly associated with toxicity, whereas ICG values were not.

CONCLUSIONS

Incorporation of midtreatment change in ALBI in addition to baseline ALBI improves the ability to predict TRT in patients with hepatocellular carcinoma receiving SBRT. Our findings suggest that functional response adaptive treatment could be implemented in a practical manner because the ALBI score is easily obtained from standard laboratory values.

Normal tissue complication probability (NTCP) models for predicting temporal lobe injury after intensity-modulated radiotherapy in nasopharyngeal carcinoma: A large registry-based retrospective study from China

PURPOSE

To develop predictive models with dosimetric and clinical variables for temporal lobe injury (TLI) in nasopharyngeal carcinoma (NPC) after intensity-modulated radiotherapy (IMRT).

MATERIALS AND METHODS

Data of 8194 NPC patients who received IMRT-based treatment were retrospectively reviewed. TLI was diagnosed by magnetic resonance imaging. Dosimetric factors were selected by penalized regression and machine learning, with area under the receiver operating curve (AUC) calculated. Cox proportional hazards models containing the most predictive dosimetric factor with/without clinical variables were performed. A nomogram was generated as a visualization of Cox regression for predicting TLI-free survival.

RESULTS

During median follow-up of 66.8 months (interquartile range [IQR] 54.2-82.2 months), 12.1% of patients (989/8194) developed TLI. Median latency from IMRT to TLI was 36 months (IQR 28-47 months). D_0.5cc (dose delivered to 0.5-cm³ temporal-lobe volume) was the most predictive dosimetric factor (AUC: 0.799). Tolerance dose for 5% and 50% probabilities to develop TLI in 5 years were 65.06 Gy (95% confidence interval [CI]: 64.19-65.92) and 89.75 Gy (95% CI: 87.39-92.11), respectively. A nomogram comprising age, T stage, and D_0.5cc significantly outperformed the model with only D_0.5cc in predicting TLI (C-index: 0.78 vs. 0.737 in train set; 0.775 vs. 0.73 in test set; both P < 0.001). The nomogram-defined high-risk group had worse 5-year TLI-free survival.

CONCLUSIONS

D_0.5cc of 65.06 Gy was the tolerance dose of the temporal lobe. Reducing D_0.5cc decreased risk of TLI, especially in older patients with advanced T stage. The nomogram could predict TLI precisely and allow individualized follow-up management.

A Primer on Dose-Response Data Modeling in Radiation Therapy

An overview of common approaches used to assess a dose response for radiation therapy-associated endpoints is presented, using lung toxicity data sets analyzed as a part of the High Dose per Fraction, Hypofractionated Treatment Effects in the Clinic effort as an example. Each component presented (eg, data-driven analysis, dose-response analysis, and calculating uncertainties on model prediction) is addressed using established approaches. Specifically, the maximum likelihood method was used to calculate best parameter values of the commonly used logistic model, the profile-likelihood to calculate confidence intervals on model parameters, and the likelihood ratio to determine whether the observed data fit is statistically significant. The bootstrap method was used to calculate confidence intervals for model predictions. Correlated behavior of model parameters and implication for interpreting dose response are discussed.

Individualized Adaptive Radiation Therapy Allows for Safe Treatment of Hepatocellular Carcinoma in Patients With Child-Turcotte-Pugh B Liver Disease

PURPOSE

Previous reports of stereotactic body radiation therapy (SBRT) for hepatocellular carcinoma (HCC) suggest unacceptably high rates of toxicity in patients with Child-Turcotte-Pugh (CTP) B liver disease. We hypothesized that an individualized adaptive treatment approach based on midtreatment liver function would maintain good local control while limiting toxicity in this population.

METHODS AND MATERIALS

Patients with CTP-B liver disease and HCC were treated on prospective trials of individualized adaptive SBRT between 2006 and 2018. Patients underwent pre- and midtreatment liver function assessments using indocyanine green. Treatment-related toxicity was defined as a ≥2-point increase in CTP score from pretreatment within 6 months of treatment. In addition, we performed analyses with a longitudinal model to assess changes in CTP score over 12 months after SBRT.

RESULTS

Eighty patients with CTP-B (median tumor size, 2.5 cm) were treated: 37 patients were CTP-B-7, 28 were CTP-B-8, and 15 were CTP-B-9. The median treatment dose was 36 Gy in 3 fractions. One-year local control was 92%. In a multivariate model controlling for tumor size, treatment dose, and baseline CTP score, higher treatment dose was associated with improved freedom from local progression (hazard ratio: 0.97; 95% confidence interval, 0.94-1.00; P = .04). Eighteen patients (24%) had a ≥2-point increase in CTP score within 6 months of SBRT. In a longitudinal model assessing changes in CTP score over 12 months after SBRT, controlling for baseline CTP and tumor size, increasing mean liver dose was associated with larger increases in CTP score (P = .04).

CONCLUSIONS

An individualized adaptive treatment approach allows for acceptable toxicity and effective local control in patients with HCC and CTP-B liver disease. Because increasing dose may increase both local control and toxicity, further work is needed to optimize treatment in patients with compromised liver function.

Long term outcomes of stereotactic body radiation therapy for hepatocellular carcinoma without macrovascular invasion

BACKGROUND

Stereotactic Body Radiation Therapy (SBRT) is a non-invasive ablative treatment for hepatocellular carcinoma (HCC). This report aimed to address the limited availability of long-term outcomes after SBRT for HCC from North America.

METHODS

Localized HCC patients without vascular invasion, who were ineligible for other liver-directed therapies and treated with SBRT at the University of Toronto or University of Michigan, were pooled to determine overall survival (OS), cumulative recurrence rates, and ≥ grade-3 toxicity. Multivariable analysis determined factors affecting OS and local recurrence rates.

RESULTS

In 297 patients with 436 HCCs (42% > 3 cm), one-, three- and five-year OS was 77·3%, 39·0% and 24·1%, respectively. On Cox proportional hazards regression analysis, liver transplant after SBRT, Child-Pugh A liver function, alpha-fetoprotein ≤ 10 ng/ml, and Eastern Co-operative Oncology Group performance status 0 significantly improved OS (hazard ratio [HR] = 0·06, 95% confidence interval [CI- 0·02-0·25; p<0·001; HR = 0·42, 95% CI = 0·29-0·60, p<0·001; HR = 0·61, 95% CI- 0·44-0·83; p=0·002 and HR = 0·71, 95% CI = 0·51-0·97, p=0·034, respectively). Cumulative local recurrence was 6·3% (95% CI = 0.03-0.09) and 13·3% (95% CI = 0.06-0.21) at one and three years, respectively. Using Cox regression modelling, local control was significantly higher using breath-hold motion management and in HCC smaller than 3 cm (HR = 0.52, 95% CI = 0.58-0.98; p=0.042 and HR = 0.53, 95% CI = 0.26-0.98; p=0.042, respectively). Worsening of Child-Pugh score by ≥2 points three months after SBRT was seen in 15.9%.

CONCLUSIONS

SBRT confers high local control and long-term survival in a substantial proportion of HCC patients unsuitable for, or refractory to standard loco-regional treatments. Liver transplant should be considered if appropriate downsizing occurs after SBRT.

Lyman-Kutcher-Burman normal tissue complication probability modeling for radiation-induced esophagitis in non-small cell lung cancer patients receiving proton radiotherapy

PURPOSE

To develop and test an Lyman-Kutcher-Burman (LKB) normal tissue complication probability (NTCP) model to predict radiation-induced esophagitis (RE) in non-small cell lung cancer (NSCLC) patients receiving passive-scattering proton therapy (PSPT).

MATERIAL AND METHODS

We retrospectively reviewed 328 NSCLC patients receiving PSPT at our institution. Esophagitis severity was graded by physicians according to the Common Toxicity Criteria for Adverse Events version 3.0, and the primary endpoint was grade ≥2 RE within 6 months from the first treatment. LKB model parameters (n, m, and TD₅₀) were determined using maximum likelihood estimation. Overall performance of the model was quantified by Nagelkerke's R² and the scaled Brier score. Discriminative ability was evaluated using the area under the receiver operating curve (AUC), and calibration was assessed with the Hosmer-Lemeshow goodness-of-fit test. Bootstrap internal validation was performed to assess the model uncertainty and generalizability.

RESULTS

Grade 2-3 RE was observed in 136 (41.5%) patients, and no grade 4-5 RE was reported. The optimal LKB parameters were: n = 0.24, m = 0.51, and TD₅₀ = 44.83 Gy (relative biological effectiveness). The optimism-corrected AUC was 0.783, and the Hosmer-Lemeshow test showed significant agreement between predicted and observed morbidity. Bootstrap validation verified that the model was robust to similar future populations.

CONCLUSION

Our LKB NTCP model to predict grade ≥2 RE in NSCLC patients who received PSPT showed good predictive performance and robustness to similar future populations, and a smaller volume effect than the previously observed in photon-treated populations. External validation of the model is warranted.

Dosimetric Analysis and Normal-Tissue Complication Probability Modeling of Child-Pugh Score and Albumin-Bilirubin Grade Increase After Hepatic Irradiation

PURPOSE

This study aimed to develop robust normal-tissue complication probability (NTCP) models for patients with hepatocellular carcinoma treated with radiation therapy (RT) using Child-Pugh (CP) score and albumin-bilirubin (ALBI) grade increase as endpoints for hepatic toxicity.

METHODS AND MATERIALS

Data from 108 patients with hepatocellular carcinoma treated with RT between 2008 and 2017 were evaluated, of which 47 patients (44%) were treated with proton RT. Of these patients, 29 received stereotactic body RT and 79 moderately hypofractionated RT to median physical tumor doses of 43 Gy in 5 fractions and 59 Gy in 15 fractions, respectively. A generalized Lyman-Kutcher-Berman (LKB) model was used to model the NTCP using 2 clinical endpoints, both evaluated at 3 months after RT: CP score increase of ≥2 and ALBI grade increase of ≥1 from the pre-RT baseline. Confidence intervals on LKB fit parameters were determined using bootstrap resampling.

RESULTS

Compared with previous NTCP models, this study found a stronger correlation between normal liver volume receiving low doses of radiation (5-10 Gy) and a CP score or ALBI grade increase. A CP score increase exhibited a stronger correlation to normal liver volumes irradiated than an ALBI grade increase. LKB models for CP increase found values for the volume-effect parameter of a = 0.06 for all patients, and a = 0.02/0.09 when fit to photon/proton patients separately. Subset analyses for patients with superior initial liver functions showed consistent dose-volume effects (a = 0.1) and consistent dose-response relationships.

CONCLUSIONS

This study presents an update of liver NTCP models in the era of modern RT techniques using relevant endpoints of hepatic toxicity, CP score and ALBI grade increase. The results show a stronger influence of low-dose bath on hepatic toxicity than those found in previous studies, indicating that RT techniques that minimize the low-dose bath may be beneficial for patients.

A mid-treatment break and reassessment maintains tumor control and reduces toxicity in patients with hepatocellular carcinoma treated with stereotactic body radiation therapy

BACKGROUND AND PURPOSE

Patients with hepatocellular carcinoma (HCC) commonly have underlying liver dysfunction with variable tolerance to liver stereotactic body radiation therapy (SBRT). We hypothesized that insertion of a 1-month mid-treatment break would allow us to adapt treatment to the individual patient response, thereby reducing toxicity without compromising local control (LC).

MATERIALS AND METHODS

We analyzed HCC patients receiving 3-5 fraction SBRT at our institution from 2005 to 2017. Over this time, patients were offered enrollment on prospective trials assessing individualized adaptive SBRT. Based on normal tissue complication probability and modeling of changes in liver function following a 1-month treatment break between fractions 3 and 4, patients could receive a total of 3 or 5 fractions. Patients not on trial received 3 or 5 fractions without a break. Toxicity was defined as a ≥2 point rise in Child-Pugh (CP) score within 6 months of SBRT.

RESULTS

178 patients were treated with SBRT to 263 HCCs. Median follow-up was 23 months. 86 treatments had a 1-month break. 1-Year LC was 95.4%; this was not different between patients treated with or without a break (p = 0.14). Controlling for tumor size and dose a break was not associated with inferior LC (HR: 0.58, 95%CI: 0.1-3.34, p = 0.54). 54 patients experienced a ≥2 point rise in CP score. Controlling for the number of prior liver directed therapies and mean liver dose, a treatment break reduced the odds of toxicity (OR: 0.42, 95% CI: 0.17-1.03, p = 0.06).

CONCLUSION

A one-month mid-treatment break and reassessment may reduce the odds of treatment related toxicity without compromising LC.

In-vivo treatment accuracy analysis of active motion-compensated liver SBRT through registration of plan dose to post-therapeutic MRI-morphologic alterations

BACKGROUND/PURPOSE

In-vivo-accuracy analysis (IVA) of dose-delivery with active motion-management (gating/tracking) was performed based on registration of post-radiotherapeutic MRI-morphologic-alterations (MMA) to the corresponding dose-distributions of gantry-based/robotic SBRT-plans.

METHODS

Forty targets in two patient cohorts were evaluated: (1) gantry-based SBRT (deep-inspiratory breath-hold-gating; GS) and (2) robotic SBRT (online fiducial-tracking; RS). The planning-CT was deformably registered to the first post-treatment contrast-enhanced T1-weighted MRI. An isodose-structure cropped to the liver (ISL) and corresponding to the contoured MMA was created. Structure and statistical analysis regarding volumes, surface-distance, conformity metrics and center-of-mass-differences (CoMD) was performed.

RESULTS

Liver volume-reduction was -43.1 ± 148.2 cc post-RS and -55.8 ± 174.3 cc post-GS. The mean surface-distance between MMA and ISL was 2.3 ± 0.8 mm (RS) and 2.8 ± 1.1 mm (GS). ISL and MMA volumes diverged by 5.1 ± 23.3 cc (RS) and 16.5 ± 34.1 cc (GS); the median conformity index of both structures was 0.83 (RS) and 0.80 (GS). The average relative directional errors were ≤0.7 mm (RS) and ≤0.3 mm (GS); the median absolute 3D-CoMD was 3.8 mm (RS) and 4.2 mm (GS) without statistically significant differences between the two techniques. Factors influencing the IVA included GTV and PTV (p = 0.041 and p = 0.020). Four local relapses occurred without correlation to IVA.

CONCLUSIONS

For the first time a method for IVA was presented, which can serve as a benchmarking-tool for other treatment techniques. Both techniques have shown median deviations <5 mm of planned dose and MMA. However, IVA also revealed treatments with errors ≥5 mm, suggesting a necessity for patient-specific safety-margins. Nevertheless, the treatment accuracy of well-performed active motion-compensated liver SBRT seems not to be a driving factor for local treatment failure.

Radiotherapy for Hepatocellular Carcinoma

For patients with unresectable or medically inoperable hepatocellular carcinoma, there are many local and regional therapies available, including stereotactic body radiotherapy, radiofrequency ablation, and transcatheter embolic approaches. This article will describe these treatment options and review the current comparative literature, suggesting that stereotactic body radiotherapy provides similar or better tumor control and a favorable side effect profile.

Role and future of MRI in radiation oncology

Technical innovations and developments in areas such as disease localization, dose calculation algorithms, motion management and dose delivery technologies have revolutionized radiation therapy resulting in improved patient care with superior outcomes. A consequence of the ability to design and accurately deliver complex radiation fields is the need for improved target visualization through imaging. While CT imaging has been the standard of care for more than three decades, the superior soft tissue contrast afforded by MR has resulted in the adoption of this technology in radiation therapy. With the development of real time MR imaging techniques, the problem of real time motion management is enticing. Currently, the integration of an MR imaging and megavoltage radiation therapy treatment delivery system (MR-linac or MRL) is a reality that has the potential to provide improved target localization and real time motion management during treatment. Higher magnetic field strengths provide improved image quality potentially providing the backbone for future work related to image texture analysis-a field known as Radiomics-thereby providing meaningful information on the selection of future patients for radiation dose escalation, motion-managed treatment techniques and ultimately better patient care. On-going advances in MRL technologies promise improved real time soft tissue visualization, treatment margin reductions, beam optimization, inhomogeneity corrected dose calculation, fast multileaf collimators and volumetric arc radiation therapy. This review article provides rationale, advantages and disadvantages as well as ideas for future research in MRI related to radiation therapy mainly in adoption of MRL.

Abdominal DCE-MRI reconstruction with deformable motion correction for liver perfusion quantification

PURPOSE

Abdominal dynamic contrast-enhanced (DCE) MRI suffers from motion-induced artifacts that can blur images and distort contrast-agent uptake curves. For liver perfusion analysis, image reconstruction with rigid-body motion correction (RMC) can restore distorted portal-venous input functions (PVIF) to higher peak amplitudes. However, RMC cannot correct for liver deformation during breathing. We present a reconstruction algorithm with deformable motion correction (DMC) that enables correction of breathing-induced deformation in the whole abdomen.

METHODS

Raw data from a golden-angle stack-of-stars gradient-echo sequence were collected for 54 DCE-MRI examinations of 31 patients. For each examination, a respiratory motion signal was extracted from the data and used to reconstruct 21 breathing states from inhale to exhale. The states were aligned with deformable image registration to the end-exhale state. Resulting deformation fields were used to correct back-projection images before reconstruction with view sharing. Images with DMC were compared to uncorrected images and images with RMC.

RESULTS

DMC significantly increased the PVIF peak amplitude compared to uncorrected images (P << 0.01, mean increase: 8%) but not compared to RMC. The increased PVIF peak amplitude significantly decreased estimated portal-venous perfusion in the liver (P << 0.01, mean decrease: 8 ml/(100 ml·min)). DMC also removed artifacts in perfusion maps at the liver edge and reduced blurring of liver tumors for some patients.

CONCLUSIONS

DCE-MRI reconstruction with DMC can restore motion-distorted uptake curves in the abdomen and remove motion artifacts from reconstructed images and parameter maps but does not significantly improve perfusion quantification in the liver compared to RMC.