Validating a Predictive Atlas of Tumor Shrinkage for Adaptive Radiotherapy of Locally Advanced Lung Cancer

Adapt-On-Demand: A Novel Strategy for Personalized Adaptive Radiation Therapy for Locally Advanced Lung Cancer

PURPOSE

Real-time adaptation of thoracic radiation plans is compelling because offline adaptive experiences show that tumor volumes and lung anatomy can change during therapy. We present and analyze a novel adaptive-on-demand (AOD) workflow combining online adaptive radiation therapy (o-ART) on the ETHOS system with image guided radiation therapy delivery on a Halcyon unit for conventional fractionated radiation therapy of locally advanced lung cancer (LALC).

METHODS AND MATERIALS

We analyzed 26 patients with LALC treated with the AOD workflow, adapting weekly. We timed segments of the workflow to evaluate efficiency in a real-world clinic. Target coverage and organ at risk (OAR) doses were compared between adaptive plans (ADP) and nonadaptive scheduled plans (SCH). Planning robustness was evaluated by the frequency of preplanning goals achieved in ADP plans, stratified by tumor volume change.

RESULTS

The AOD workflow was achievable within 30 minutes for most radiation fractions. Over the course of therapy, we observed an average 26.6% ± 23.3% reduction in internal target volume (ITV). Despite these changes, with o-ART, ITV and planning target volume (PTV) coverage (V100%) was 99.2% and 93.9% for all members of the cohort, respectively. This represented a 2.9% and 6.8% improvement over nonadaptive plans (P < .05), respectively. For tumors that grew >10%, V100% was 93.1% for o-ART and 76.4% for nonadaptive plans, representing a median 17.2% improvement in the PTV coverage (P < .05). In these plans, critical OAR constraints were met 94.1% of the time, whereas in nonadaptive plans, this figure was 81.9%. This represented reductions of 1.32 Gy, 1.34 Gy, or 1.75 Gy in the heart, esophagus, and lung, respectively. The effect was larger when tumors had shrunk more than 10%. Regardless of tumor volume alterations, the PTV/ITV coverage was achieved for all adaptive plans. Exceptional cases, where dose constraints were not met, were due to large initial tumor volumes or tumor growth.

CONCLUSIONS

The AOD workflow is efficient and robust in responding to anatomic changes in LALC patients, providing dosimetric advantages over standard therapy. Weekly adaptation was adequate to keep pace with changes. This approach is a feasible alternative to conventional offline replanning workflows for managing anatomy changes in LALC radiation therapy.

Creating patient-specific digital phantoms with a longitudinal atlas for evaluating deformable CT-CBCT registration in adaptive lung radiotherapy

BACKGROUND

Quality assurance of deformable image registration (DIR) is challenging because the ground truth is often unavailable. In addition, current approaches that rely on artificial transformations do not adequately resemble clinical scenarios encountered in adaptive radiotherapy.

PURPOSE

We developed an atlas-based method to create a variety of patient-specific serial digital phantoms with CBCT-like image quality to assess the DIR performance for longitudinal CBCT imaging data in adaptive lung radiotherapy.

METHODS

A library of deformations was created by extracting the longitudinal changes observed between a planning CT and weekly CBCT from an atlas of lung radiotherapy patients. The planning CT of an inquiry patient was first deformed by mapping the deformation pattern from a matched atlas patient, and subsequently appended with CBCT artifacts to imitate a weekly CBCT. Finally, a group of digital phantoms around an inquiry patient was produced to simulate a series of possible evolutions of tumor and adjacent normal structures. We validated the generated deformation vector fields (DVFs) to ensure numerically and physiologically realistic transformations. The proposed framework was applied to evaluate the performance of the DIR algorithm implemented in the commercial Eclipse treatment planning system in a retrospective study of eight inquiry patients.

RESULTS

The generated DVFs were inverse consistent within less than 3 mm and did not exhibit unrealistic folding. The deformation patterns adequately mimicked the observed longitudinal anatomical changes of the matched atlas patients. Worse Eclipse DVF accuracy was observed in regions of low image contrast or artifacts. The structure volumes exhibiting a DVF error magnitude of equal or more than 2 mm ranged from 24.5% (spinal cord) to 69.2% (heart) and the maximum DVF error exceeded 5 mm for all structures except the spinal cord. Contour-based evaluations showed a high degree of alignment with dice similarity coefficients above 0.8 in all cases, which underestimated the overall DVF accuracy within the structures.

CONCLUSIONS

It is feasible to create and augment digital phantoms based on a particular patient of interest using multiple series of deformation patterns from matched patients in an atlas. This can provide a semi-automated procedure to complement the quality assurance of CT-CBCT DIR and facilitate the clinical implementation of image-guided and adaptive radiotherapy that involve longitudinal CBCT imaging studies.

Artificial intelligence-based automated segmentation and radiotherapy dose mapping for thoracic normal tissues

Background and purpose

Objective assessment of delivered radiotherapy (RT) to thoracic organs requires fast and accurate deformable dose mapping. The aim of this study was to implement and evaluate an artificial intelligence (AI) deformable image registration (DIR) and organ segmentation-based AI dose mapping (AIDA) applied to the esophagus and the heart.

Materials and methods

AIDA metrics were calculated for 72 locally advanced non-small cell lung cancer patients treated with concurrent chemo-RT to 60 Gy in 2 Gy fractions in an automated pipeline. The pipeline steps were: (i) automated rigid alignment and cropping of planning CT to week 1 and week 2 cone-beam CT (CBCT) field-of-views, (ii) AI segmentation on CBCTs, and (iii) AI-DIR-based dose mapping to compute dose metrics. AIDA dose metrics were compared to the planned dose and manual contour dose mapping (manual DA).

Results

AIDA required ∼2 min/patient. Esophagus and heart segmentations were generated with a mean Dice similarity coefficient (DSC) of 0.80±0.15 and 0.94±0.05, a Hausdorff distance at 95th percentile (HD95) of 3.9±3.4 mm and 14.1±8.3 mm, respectively. AIDA heart dose was significantly lower than the planned heart dose (p = 0.04). Larger dose deviations (>=1Gy) were more frequently observed between AIDA and the planned dose (N = 26) than with manual DA (N = 6).

Conclusions

Rapid estimation of RT dose to thoracic tissues from CBCT is feasible with AIDA. AIDA-derived metrics and segmentations were similar to manual DA, thus motivating the use of AIDA for RT applications.

Can bronchoscopically implanted anchored electromagnetic transponders be used to monitor tumor position and lung inflation during deep inspiration breath-hold lung radiotherapy?

PURPOSE

To evaluate the efficacy of using bronchoscopically implanted anchored electromagnetic transponders (EMTs) as surrogates for 1) tumor position and 2) repeatability of lung inflation during deep-inspiration breath-hold (DIBH) lung radiotherapy.

METHODS

41 patients treated with either hypofractionated (HF) or conventional (CF) lung radiotherapy on an IRB approved prospective protocol using coached DIBH were evaluated for this study. Three anchored EMTs were bronchoscopically implanted into small airways near or within the tumor. DIBH treatment was gated by tracking the EMT positions. Breath-hold cone-beam-CTs (CBCTs) were acquired prior to every HF treatment or weekly for CF patients. Retrospectively, rigid registrations between each CBCT and the breath-hold planning CT were performed to match to 1) spine 2) EMTs and 3) tumor. Absolute differences in registration between EMTs and spine were analyzed to determine surrogacy of EMTs for lung inflation. Differences in registration between EMTs and tumor were analyzed to determine surrogacy of EMTs for tumor position. The stability of the EMTs was evaluated by analyzing the difference between inter-EMT displacements recorded at treatment from that of the plan for the CF patients, as well as the geometric residual (GR) recorded at the time of treatment.

RESULTS

219 CBCTs were analyzed. The average differences between EMT centroid and spine registration among all CBCTs were 0.45±0.42cm, 0.29±0.28cm, and 0.18±0.15cm in superior-inferior (SI), anterior-posterior (AP) and lateral directions, respectively. Only 59% of CBCTs had differences in registration <0.5cm for EMT centroid compared to spine, indicating that lung inflation is not reproducible from simulation to treatment. The average differences between EMT centroid and tumor registration among all CBCTs were 0.13±0.13cm, 0.14±0.13cm and 0.12±0.12cm in SI, AP and lateral directions, respectively. 95% of CBCTs resulted in <0.5cm change between EMT centroid and tumor registration, indicating that EMT positions correspond well with tumor position during treatments. Six out of the 7 recorded CF patients had average differences in inter-EMT displacements to be ≤0.26cm and average GR ≤0.22cm, indicating that the EMTs are stable throughout treatment.

CONCLUSIONS

Bronchoscopically implanted anchored EMTs are good surrogates for tumor position and are reliable for maintaining tumor position when tracked during DIBH treatment, as long as the tumor size and shape are stable. Large differences in registration between EMTs and spine for many treatments suggest that lung inflation achieved at simulation is often not reproduced. This article is protected by copyright. All rights reserved.

Adaptive Radiation Therapy in the Treatment of Lung Cancer: An Overview of the Current State of the Field

Lung cancer treatment is constantly evolving due to technological advances in the delivery of radiation therapy. Adaptive radiation therapy (ART) allows for modification of a treatment plan with the goal of improving the dose distribution to the patient due to anatomic or physiologic deviations from the initial simulation. The implementation of ART for lung cancer is widely varied with limited consensus on who to adapt, when to adapt, how to adapt, and what the actual benefits of adaptation are. ART for lung cancer presents significant challenges due to the nature of the moving target, tumor shrinkage, and complex dose accumulation because of plan adaptation. This article presents an overview of the current state of the field in ART for lung cancer, specifically, probing topics of: patient selection for the greatest benefit from adaptation, models which predict who and when to adapt plans, best timing for plan adaptation, optimized workflows for implementing ART including alternatives to re-simulation, the best radiation techniques for ART including magnetic resonance guided treatment, algorithms and quality assurance, and challenges and techniques for dose reconstruction. To date, the clinical workflow burden of ART is one of the major reasons limiting its widespread acceptance. However, the growing body of evidence demonstrates overwhelming support for reduced toxicity while improving tumor dose coverage by adapting plans mid-treatment, but this is offset by the limited knowledge about tumor control. Progress made in predictive modeling of on-treatment tumor shrinkage and toxicity, optimizing the timing of adaptation of the plan during the course of treatment, creating optimal workflows to minimize staffing burden, and utilizing deformable image registration represent ways the field is moving toward a more uniform implementation of ART.

Dynamic stochastic deep learning approaches for predicting geometric changes in head and neck cancer

Objective.Modern radiotherapy stands to benefit from the ability to efficiently adapt plans during treatment in response to setup and geometric variations such as those caused by internal organ deformation or tumor shrinkage. A promising strategy is to develop a framework, which given an initial state defined by patient-attributes, can predict future states based on pre-learned patterns from a well-defined patient population.Approach.Here, we investigate the feasibility of predicting patient anatomical changes, defined as a joint state of volume and daily setup changes, across a fractionated treatment schedule using two approaches. The first is based on a new joint framework employing quantum mechanics in combination with deep recurrent neural networks, denoted QRNN. The second approach is developed based on a classical framework, which models patient changes as a Markov process, denoted MRNN. We evaluated the performance characteristics of these two approaches on a dataset of 125 head and neck cancer patients, which was supplemented by synthetic data generated using a generative adversarial network. Model performance was evaluated using area under the receiver operating characteristic curve (AUC) scores.Main results.The MRNN framework had slightly better performance than the QRNN framework, with MRNN (QRNN) validation AUC scores of 0.742±0.021 (0.675±0.036), 0.709±0.026 (0.656±0.021), 0.724±0.036 (0.652±0.044), and 0.698±0.016 (0.605±0.035) for system state vector sizes of 4, 6, 8, and 10, respectively. Of these, only the results from the two higher order states had statistically significant differences(p<0.05).A similar trend was also observed when the models were applied to an external testing dataset of 20 patients, yielding MRNN (QRNN) AUC scores of 0.707 (0.623), 0.687 (0.608), 0.723 (0.669), and 0.697 (0.609) for states vectors sizes of 4, 6, 8, and 10, respectively.Significance.These results suggest that both stochastic models have potential value in predicting patient changes during the course of adaptive radiotherapy.

Identification of modes of tumor regression in non-small cell lung cancer patients during radiotherapy

PURPOSE

Observed gross tumor volume (GTV) shrinkage during radiotherapy (RT) raises the question of whether to adapt treatment to changes observed on the acquired images. In the literature, two modes of tumor regression have been described: elastic and non-elastic. These modes of tumor regression will affect the safety of treatment adaptation. This study applies a novel approach, using routine cone-beam computed tomography (CBCT) and deformable image registration to automatically distinguish between elastic and non-elastic tumor regression.

METHODS

In this retrospective study, 150 locally advanced non-small cell lung cancer patients treated with 55 Gray of radiotherapy were included. First, the two modes of tumor regression were simulated. For each mode of tumor regression, one timepoint was simulated. Based on the results of simulated data, the approach used for analysis in real patients was developed. CBCTs were non-rigidly registered to the baseline CBCT using a cubic B-spline algorithm, NiftyReg. Next, the Jacobian determinants were computed from the deformation vector fields. To capture local volume changes, 10 Jacobian values were sampled perpendicular to the surface of the GTV, across the lung-tumor boundary. From the simulated data, we can distinguish elastic from non-elastic tumor regression by comparing the Jacobian values samples between 5 and 12.5 mm inside and 5 and 12.5 mm outside the planning GTV. Finally, morphometric results were compared between tumors of different histologies.

RESULTS

Most patients (92.3%) in our cohort showed stable disease in the first week of treatment and non-elastic shrinkage in the later weeks of treatment. At week 2, 125 patients (88%) showed stable disease, three patients (2.1%) disease progression, and 11 patients (8%) regression. By treatment completion, 91 patients (64%) had stable disease, one patient (0.7%) progression and 46 patients (32%) regression. A slight difference in the mode of tumor change was observed between tumors of different histologies.

CONCLUSION

Our novel approach shows that it may be possible to automatically quantify and identify global changes in lung cancer patients during RT, using routine CBCT images. Our results show that different regions of the tumor change in different ways. Therefore, careful consideration should be taken when adapting RT.

CT-based radiomics signatures can predict the tumor response of non-small cell lung cancer patients treated with first-line chemotherapy and targeted therapy

OBJECTIVES

The goal of this study was to evaluate the effectiveness of radiomics signatures on pre-treatment computed tomography (CT) images of lungs to predict the tumor responses of non-small cell lung cancer (NSCLC) patients treated with first-line chemotherapy, targeted therapy, or a combination of both.

MATERIALS AND METHODS

This retrospective study included 322 NSCLC patients who were treated with first-line chemotherapy, targeted therapy, or a combination of both. Of these patients, 224 were randomly assigned to a cohort to help develop the radiomics signature. A total of 1946 radiomics features were obtained from each patient's CT scan. The top-ranked features were selected by the Minimum Redundancy Maximum Relevance (MRMR) feature-ranking method and used to build a lightweight radiomics signature with the Random Forest (RF) classifier. The independent predictive (IP) features (AUC > 0.6, p value < 0.05) were further identified from the top-ranked features and used to build a refined radiomics signature by the RF classifier. Its prediction performance was tested on the validation cohort, which consisted of the remaining 98 patients.

RESULTS

The initial lightweight radiomics signature constructed from 15 top-ranked features had an AUC of 0.721 (95% CI, 0.619-0.823). After six IP features were further identified and a refined radiomics signature was built, it had an AUC of 0.746 (95% CI, 0.646-0.846).

CONCLUSIONS

Radiomics signatures based on pre-treatment CT scans can accurately predict tumor response in NSCLC patients after first-line chemotherapy or targeted therapy treatments. Radiomics features could be used as promising prognostic imaging biomarkers in the future.

KEY POINTS

The radiomics signature extracted from baseline CT images in patients with NSCLC can predict response to first-line chemotherapy, targeted therapy, or both treatments with an AUC = 0.746 (95% CI, 0.646-0.846). The radiomics signature could be used as a new biomarker for quantitative analysis in radiology, which might provide value in decision-making and to define personalized treatments for cancer patients.

Managing tumor changes during radiotherapy using a deep learning model

PURPOSE

We propose a treatment planning framework that accounts for weekly lung tumor shrinkage using cone beam computed tomography (CBCT) images with a deep learning-based model.

METHODS

Sixteen patients with non-small-cell lung cancer (NSCLC) were selected with one planning CT and six weekly CBCTs each. A deep learning-based model was applied to predict the weekly deformation of the primary tumor based on the spatial and temporal features extracted from previous weekly CBCTs. Starting from Week 3, the tumor contour at Week N was predicted by the model based on the input from all the previous weeks (1, 2 … N - 1), and was evaluated against the manually contoured tumor using Dice coefficient (DSC), precision, average surface distance (ASD), and Hausdorff distance (HD). Information about the predicted tumor was then entered into the treatment planning system and the plan was re-optimized every week. The objectives were to maximize the dose coverage in the target region while minimizing the toxicity to the surrounding healthy tissue. Dosimetric evaluation of the target and organs at risk (heart, lung, esophagus, and spinal cord) was performed on four cases, comparing between a conventional plan (ignoring tumor shrinkage) and the shrinkage-based plan.

RESULTS

he primary tumor volumes decreased on average by 38% ± 26% during six weeks of treatment. DSCs and ASD between the predicted tumor and the actual tumor for Weeks 3, 4, 5, 6 were 0.81, 0.82, 0.79, 0.78 and 1.49, 1.59, 1.92, 2.12 mm, respectively, which were significantly superior to the score of 0.70, 0.68, 0.66, 0.63 and 2.81, 3.22, 3.69, 3.63 mm between the rigidly transferred tumors ignoring shrinkage and the actual tumor. While target coverage metrics were maintained for the re-optimized plans, lung mean dose dropped by 2.85, 0.46, 2.39, and 1.48 Gy for four sample cases when compared to the original plan. Doses in other organs such as esophagus were also reduced for some cases.

CONCLUSION

We developed a deep learning-based model for tumor shrinkage prediction. This model used CBCTs and contours from previous weeks as input and produced reasonable tumor contours with a high prediction accuracy (DSC, precision, HD, and ASD). The proposed framework maintained target coverage while reducing dose in the lungs and esophagus.

A method for predictive modeling of tumor regression for lung adaptive radiotherapy

PURPOSE

The purpose of this work is to create a decision support methodology to predict when patients undergoing radiotherapy treatment for locally advanced lung cancer would potentially benefit from adaptive radiotherapy. The proposed methodology seeks to eliminate the manual subjective review by developing an automated statistical learning model to predict when tumor regression would trigger implementation of adaptive radiotherapy based on quantified anatomic changes observed in individual patients on-treatment cone beam computed tomographies (CTs). This proposed process seeks to improve the efficacy and efficiency of both the existing manual and automated adaptive review processes for locally advanced stage III lung cancer.

METHODS

A predictive algorithm was developed as a decision support tool to determine the potential utility of mid-treatment adaptive radiotherapy based on anatomic changes observed on 1158 daily CBCT images across 43 patients. The anatomic changes on each axial slice within specified regions-of-interest were quantified into a single value utilizing imaging similarity criteria comparing the daily CBCT to the initial simulation CT. The range of the quantified metrics for each fraction across all axial slices are reduced to specified quantiles, which are used as the predictive input to train a logistic regression algorithm. A "ground-truth" of the need for adaptive radiotherapy based on tumor regression was evaluated systematically on each of the daily CBCTs and used as the classifier in the logistic regression algorithm. Accuracy of the predictive model was assessed utilizing both a tenfold cross validation and an independent validation dataset, with the sensitivity, specificity, and fractional accuracy compared to the ground-truth.

RESULTS

The sensitivity and specificity for the individual daily fractions ranged from 87.9%-94.3% and 91.9%-98.6% for a probability threshold of 0.2-0.5, respectively. The corresponding average treatment fraction difference between the model predictions and assessed ART "ground-truth" ranged from -2.25 to -0.07 fractions, with the model predictions consistently predicting the potential need for ART earlier in the treatment course. By initially utilizing a lower probability threshold, the higher sensitivity minimizes the chance of false negative by alerting the clinician to review a higher number of questionable cases.

CONCLUSIONS

The proposed methodology accurately predicted the first fraction at which individual patients may benefit from ART based on quantified anatomic changes observed in the on-treatment volumetric imaging. The generalizability of the proposed method has potential to expand to additional modes of adaptive radiotherapy for lung cancer patients with observed underlying anatomic changes.

Radiomics in predicting treatment response in non-small-cell lung cancer: current status, challenges and future perspectives

OBJECTIVES

Radiomics is the extraction of quantitative data from medical imaging, which has the potential to characterise tumour phenotype. The radiomics approach has the capacity to construct predictive models for treatment response, essential for the pursuit of personalised medicine. In this literature review, we summarise the current status and evaluate the scientific and reporting quality of radiomics research in the prediction of treatment response in non-small-cell lung cancer (NSCLC).

METHODS

A comprehensive literature search was conducted using the PubMed database. A total of 178 articles were screened for eligibility and 14 peer-reviewed articles were included. The radiomics quality score (RQS), a radiomics-specific quality metric emulating the TRIPOD guidelines, was used to assess scientific and reporting quality.

RESULTS

Included studies reported several predictive markers including first-, second- and high-order features, such as kurtosis, grey-level uniformity and wavelet HLL mean respectively, as well as PET-based metabolic parameters. Quality assessment demonstrated a low median score of + 2.5 (range - 5 to + 9), mainly reflecting a lack of reproducibility and clinical evaluation. There was extensive heterogeneity between studies due to differences in patient population, cancer stage, treatment modality, follow-up timescales and radiomics workflow methodology.

CONCLUSIONS

Radiomics research has not yet been translated into clinical use. Efforts towards standardisation and collaboration are needed to identify reproducible radiomic predictors of response. Promising radiomic models must be externally validated and their impact evaluated within the clinical pathway before they can be implemented as a clinical decision-making tool to facilitate personalised treatment for patients with NSCLC.

KEY POINTS

• The included studies reported several promising radiomic markers of treatment response in lung cancer; however, there was a lack of reproducibility between studies. • Quality assessment using the radiomics quality score (RQS) demonstrated a low median total score of + 2.5 (range - 5 to + 9). • Future radiomics research should focus on implementation of standardised radiomics features and software, together with external validation in a prospective setting.

Cone-Beam-CT Guided Adaptive Radiotherapy for Locally Advanced Non-small Cell Lung Cancer Enables Quality Assurance and Superior Sparing of Healthy Lung

Purpose

To evaluate the potential of cone-beam-CT (CB-CT) guided adaptive radiotherapy (ART) for locally advanced non-small cell lung cancer (NSCLC) for sparing of surrounding organs-at-risk (OAR).

Materials and Methods

In 10 patients with locally advanced NSCLC, daily CB-CT imaging was acquired during radio- (n = 4) or radiochemotherapy (n = 6) for simulation of ART. Patients were treated with conventionally fractionated intensity-modulated radiotherapy (IMRT) with total doses of 60–66 Gy (pPlan) (311 fraction CB-CTs). OAR were segmented on every daily CB-CT and the tumor volumes were modified weekly depending on tumor changes. Doses actually delivered were recalculated on daily images (dPlan), and voxel-wise dose accumulation was performed using a deformable registration algorithm. For simulation of ART, treatment plans were adapted using the new contours and re-optimized weekly (aPlan).

Results

CB-CT showed continuous tumor regression of 1.1 ± 0.4% per day, leading to a residual gross tumor volume (GTV) of 65.3 ± 13.4% after 6 weeks of radiotherapy (p = 0.005). Corresponding PTVs decreased to 83.7 ± 7.8% (p = 0.005). In the actually delivered plans (dPlan), both conformity (p = 0.005) and homogeneity (p = 0.059) indices were impaired compared to the initial plans (pPlan). This resulted in higher actual lung doses than planned: V_20Gy was 34.6 ± 6.8% instead of 32.8 ± 4.9% (p = 0.066), mean lung dose was 19.0 ± 3.1 Gy instead of 17.9 ± 2.5 Gy (p = 0.013). The generalized equivalent uniform dose (gEUD) of the lung was 18.9 ± 3.1 Gy instead of 17.8 ± 2.5 Gy (p = 0.013), leading to an increased lung normal tissue complication probability (NTCP) of 15.2 ± 13.9% instead of 9.6 ± 7.3% (p = 0.017). Weekly plan adaptation enabled decreased lung V_20Gy of 31.6 ± 6.2% (−3.0%, p = 0.007), decreased mean lung dose of 17.7 ± 2.9 Gy (−1.3 Gy, p = 0.005), and decreased lung gEUD of 17.6 ± 2.9 Gy (−1.3 Gy, p = 0.005). Thus, resulting lung NTCP was reduced to 10.0 ± 9.5% (−5.2%, p = 0.005). Target volume coverage represented by conformity and homogeneity indices could be improved by weekly plan adaptation (CI: p = 0.007, HI: p = 0.114) and reached levels of the initial plan (CI: p = 0.721, HI: p = 0.333).

Conclusion

IGRT with CB-CT detects continuous GTV and PTV changes. CB-CT-guided ART for locally advanced NSCLC is feasible and enables superior sparing of healthy lung at high levels of plan conformity.

Predicting spatial esophageal changes in a multimodal longitudinal imaging study via a convolutional recurrent neural network

Acute esophagitis (AE) occurs among a significant number of patients with locally advanced lung cancer treated with radiotherapy. Early prediction of AE, indicated by esophageal wall expansion, is critical, as it can facilitate the redesign of treatment plans to reduce radiation-induced esophageal toxicity in an adaptive radiotherapy (ART) workflow. We have developed a novel machine learning framework to predict the patient-specific spatial presentation of the esophagus in the weeks following treatment, using magnetic resonance imaging (MRI)/ cone-beam CT (CBCT) scans acquired earlier in the 6 week radiotherapy course. Our algorithm captures the response patterns of the esophagus to radiation on a patch level, using a convolutional neural network. A recurrence neural network then parses the evolutionary patterns of the selected features in the time series, and produces a predicted esophagus-or-not label for each individual patch over future weeks. Finally, the esophagus is reconstructed, using all the predicted labels. The algorithm is trained and validated by means of ∼ 250 000 patches taken from MRI scans acquired weekly from a variety of patients, and tested using both weekly MRI and CBCT scans under a leave-one-patient-out scheme. In addition, our approach is externally validated using a publicly available dataset (Hugo 2017). Using the first three weekly scans, the algorithm can predict the condition of the esophagus over the succeeding 3 weeks with a Dice coefficient of 0.83 ± 0.04, estimate esophagus volume highly (0.98), correlated with the actual volume, using our institutional MRI/CBCT data. When evaluated using the external weekly CBCT data, the averaged Dice coefficient is 0.89 ± 0.03. Our novel algorithm may prove useful in enabling radiation oncologists to monitor and detect AE in its early stages, and could potentially play an important role in the ART decision-making process.

LDeform: Longitudinal deformation analysis for adaptive radiotherapy of lung cancer

PURPOSE

Conventional radiotherapy for large lung tumors is given over several weeks, during which the tumor typically regresses in a highly nonuniform and variable manner. Adaptive radiotherapy would ideally follow these shape changes, but we need an accurate method to extrapolate tumor shape changes. We propose a computationally efficient algorithm to quantitate tumor surface shape changes that makes minimal assumptions, identifies fixed points, and can be used to predict future tumor geometrical response.

METHODS

A novel combination of nonrigid iterative closest point (ICP) and local shape-preserving map algorithms, LDeform, is developed to enable visualization, prediction, and categorization of both diffeomorphic and nondiffeomorphic tumor deformations during an extended course of radiotherapy.

RESULTS

We tested and validated our technique on 31 longitudinal CT/MRI subjects, with five to nine time points each. Based on this tumor deformation analysis, regions of local growth, shrinkage, and anchoring are identified and tracked across multiple time points. This categorization in turn represents a rational biomarker of local response. Results demonstrate useful predictive power, with an averaged Dice coefficient and surface mean-squared error of 0.85 and 2.8 mm, respectively, over all images.

CONCLUSIONS

We conclude that the LDeform algorithm can facilitate the adaptive decision-making process during lung cancer radiotherapy.

Toward predicting the evolution of lung tumors during radiotherapy observed on a longitudinal MR imaging study via a deep learning algorithm

PURPOSE

To predict the spatial and temporal trajectories of lung tumor during radiotherapy monitored under a longitudinal magnetic resonance imaging (MRI) study via a deep learning algorithm for facilitating adaptive radiotherapy (ART).

METHODS

We monitored 10 lung cancer patients by acquiring weekly MRI-T2w scans over a course of radiotherapy. Under an ART workflow, we developed a predictive neural network (P-net) to predict the spatial distributions of tumors in the coming weeks utilizing images acquired earlier in the course. The three-step P-net consisted of a convolutional neural network to extract relevant features of the tumor and its environment, followed by a recurrence neural network constructed with gated recurrent units to analyze trajectories of tumor evolution in response to radiotherapy, and finally an attention model to weight the importance of weekly observations and produce the predictions. The performance of P-net was measured with Dice and root mean square surface distance (RMSSD) between the algorithm-predicted and experts-contoured tumors under a leave-one-out scheme.

RESULTS

Tumor shrinkage was 60% ± 27% (mean ± standard deviation) by the end of radiotherapy across nine patients. Using images from the first three weeks, P-net predicted tumors on future weeks (4, 5, 6) with a Dice and RMSSD of (0.78 ± 0.22, 0.69 ± 0.24, 0.69 ± 0.26), and (2.1 ± 1.1 mm, 2.3 ± 0.8 mm, 2.6 ± 1.4 mm), respectively.

CONCLUSION

The proposed deep learning algorithm can capture and predict spatial and temporal patterns of tumor regression in a longitudinal imaging study. It closely follows the clinical workflow, and could facilitate the decision-making of ART. A prospective study including more patients is warranted.

Functional Adaptation in Radiation Therapy

The promise of adaptive therapy to improve outcomes in radiation oncology has been an area of interest and research in the community for many years. One of the sources of data that can be used to drive adaptive therapy is functional information about the tumor or normal tissues. This avenue of adaptation includes many potential sources of data including global markers and functional imaging. Global markers can be assessments derived from blood measurements, patient functional testing, and circulating tumor material and functional imaging data comprises spatial physiological information from various imaging studies such as positron emission tomography, magnetic resonance imaging, and single photon emission computed tomography. The goal of functional adaptation is to use these functional data to adapt radiation therapy to improve patient outcomes. While functional adaptation holds a lot of promise, there are challenges such as quantifying and minimizing uncertainties, streamlining clinical implementation, determining the ideal way to incorporate information within treatment plan optimization, and proving the clinical benefit through trials. This paper will discuss the types of functional information currently being used for adaptation, highlight several areas where functional adaptation has been studied, and introduce some of the barriers to more widespread clinical implementation.