Cardiac atlas development and validation for automatic segmentation of cardiac substructures

Dosimetric Impact of Delineation and Motion Uncertainties on the Heart and Substructures in Lung Cancer Radiotherapy

AIMS

Delineation variations and organ motion produce difficult-to-quantify uncertainties in planned radiation doses to targets and organs at risk. Similar to manual contouring, most automatic segmentation tools generate single delineations per structure; however, this does not indicate the range of clinically acceptable delineations. This study develops a method to generate a range of automatic cardiac structure segmentations, incorporating motion and delineation uncertainty, and evaluates the dosimetric impact in lung cancer.

MATERIALS AND METHODS

Eighteen cardiac structures were delineated using a locally developed auto-segmentation tool. It was applied to lung cancer planning CTs for 27 curative (planned dose ≥50 Gy) cases, and delineation variations were estimated by using ten mapping-atlases to provide separate substructure segmentations. Motion-related cardiac segmentation variations were estimated by auto-contouring structures on ten respiratory phases for 9/27 cases that had 4D-planning CTs. Dose volume histograms (DVHs) incorporating these variations were generated for comparison.

RESULTS

Variations in mean doses (Dmean), defined as the range in values across ten feasible auto-segmentations, were calculated for each cardiac substructure. Over the study cohort the median variations for delineation uncertainty and motion were 2.20-11.09 Gy and 0.72-4.06 Gy, respectively. As relative values, variations in Dmean were between 18.7%-65.3% and 7.8%-32.5% for delineation uncertainty and motion, respectively. Doses vary depending on the individual planned dose distribution, not simply on segmentation differences, with larger dose variations to cardiac structures lying within areas of steep dose gradient.

CONCLUSION

Radiotherapy dose uncertainties from delineation variations and respiratory-related heart motion were quantified using a cardiac substructure automatic segmentation tool. This predicts the 'dose range' where doses to structures are most likely to fall, rather than single DVH curves. This enables consideration of these uncertainties in cardiotoxicity research and for future plan optimisation. The tool was designed for cardiac structures, but similar methods are potentially applicable to other OARs.

Cardiac substructure delineation in radiation therapy - A state-of-the-art review

Delineation of cardiac substructures is crucial for a better understanding of radiation-related cardiotoxicities and to facilitate accurate and precise cardiac dose calculation for developing and applying risk models. This review examines recent advancements in cardiac substructure delineation in the radiation therapy (RT) context, aiming to provide a comprehensive overview of the current level of knowledge, challenges and future directions in this evolving field. Imaging used for RT planning presents challenges in reliably visualising cardiac anatomy. Although cardiac atlases and contouring guidelines aid in standardisation and reduction of variability, significant uncertainties remain in defining cardiac anatomy. Coupled with the inherent complexity of the heart, this necessitates auto-contouring for consistent large-scale data analysis and improved efficiency in prospective applications. Auto-contouring models, developed primarily for breast and lung cancer RT, have demonstrated performance comparable to manual contouring, marking a significant milestone in the evolution of cardiac delineation practices. Nevertheless, several key concerns require further investigation. There is an unmet need for expanding cardiac auto-contouring models to encompass a broader range of cancer sites. A shift in focus is needed from ensuring accuracy to enhancing the robustness and accessibility of auto-contouring models. Addressing these challenges is paramount for the integration of cardiac substructure delineation and associated risk models into routine clinical practice, thereby improving the safety of RT for future cancer patients.

A prior-information-based automatic segmentation method for the clinical target volume in adaptive radiotherapy of cervical cancer

OBJECTIVE

Adaptive planning to accommodate anatomic changes during treatment often requires repeated segmentation. In this study, prior patient-specific data was integrateda into a registration-guided multi-channel multi-path (Rg-MCMP) segmentation framework to improve the accuracy of repeated clinical target volume (CTV) segmentation.

METHODS

This study was based on CT image datasets for a total of 90 cervical cancer patients who received two courses of radiotherapy. A total of 15 patients were selected randomly as the test set. In the Rg-MCMP segmentation framework, the first-course CT images (CT1) were registered to second-course CT images (CT2) to yield aligned CT images (aCT1), and the CTV in the first course (CTV1) was propagated to yield aligned CTV contours (aCTV1). Then, aCT1, aCTV1, and CT2 were combined as the inputs for 3D U-Net consisting of a channel-based multi-path feature extraction network. The performance of the Rg-MCMP segmentation framework was evaluated and compared with the single-channel single-path model (SCSP), the standalone registration methods, and the registration-guided multi-channel single-path (Rg-MCSP) model. The Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), and average surface distance (ASD) were used as the metrics.

RESULTS

The average DSC of CTV for the deformable image DIR-MCMP model was found to be 0.892, greater than that of the standalone DIR (0.856), SCSP (0.837), and DIR-MCSP (0.877), which were improvements of 4.2%, 6.6%, and 1.7%, respectively. Similarly, the rigid body DIR-MCMP model yielded an average DSC of 0.875, which exceeded standalone RB (0.787), SCSP (0.837), and registration-guided multi-channel single-path (0.848), which were improvements of 11.2%, 4.5%, and 3.2%, respectively. These improvements in DSC were statistically significant (p < 0.05).

CONCLUSION

The proposed Rg-MCMP framework achieved excellent accuracy in CTV segmentation as part of the adaptive radiotherapy workflow.

Deep learning-based automatic segmentation of cardiac substructures for lung cancers

PURPOSE

Accurate and comprehensive segmentation of cardiac substructures is crucial for minimizing the risk of radiation-induced heart disease in lung cancer radiotherapy. We sought to develop and validate deep learning-based auto-segmentation models for cardiac substructures.

MATERIALS AND METHODS

Nineteen cardiac substructures (whole heart, 4 heart chambers, 6 great vessels, 4 valves, and 4 coronary arteries) in 100 patients treated for non-small cell lung cancer were manually delineated by two radiation oncologists. The valves and coronary arteries were delineated as planning risk volumes. An nnU-Net auto-segmentation model was trained, validated, and tested on this dataset with a split ratio of 75:5:20. The auto-segmented contours were evaluated by comparing them with manually drawn contours in terms of Dice similarity coefficient (DSC) and dose metrics extracted from clinical plans. An independent dataset of 42 patients was used for subjective evaluation of the auto-segmentation model by 4 physicians.

RESULTS

The average DSCs were 0.95 (+/- 0.01) for the whole heart, 0.91 (+/- 0.02) for 4 chambers, 0.86 (+/- 0.09) for 6 great vessels, 0.81 (+/- 0.09) for 4 valves, and 0.60 (+/- 0.14) for 4 coronary arteries. The average absolute errors in mean/max doses to all substructures were 1.04 (+/- 1.99) Gy and 2.20 (+/- 4.37) Gy. The subjective evaluation revealed that 94% of the auto-segmented contours were clinically acceptable.

CONCLUSION

We demonstrated the effectiveness of our nnU-Net model for delineating cardiac substructures, including coronary arteries. Our results indicate that this model has promise for studies regarding radiation dose to cardiac substructures.

An open source auto-segmentation algorithm for delineating heart and substructures - Development and validation within a multicenter lung cancer cohort

BACKGROUND AND PURPOSE

Irradiation of the heart in thoracic cancers raises toxicity concerns. For accurate dose estimation, automated heart and substructure segmentation is potentially useful. In this study, a hybrid automatic segmentation is developed. The accuracy of delineation and dose predictions were evaluated, testing the method's potential within heart toxicity studies.

MATERIALS AND METHODS

The hybrid segmentation method delineated the heart, four chambers, three large vessels, and the coronary arteries. The method consisted of a nnU-net heart segmentation and partly atlas- and model-based segmentation of the substructures. The nnU-net training and atlas segmentation was based on lung cancer patients and was validated against a national consensus dataset of 12 patients with breast cancer. The accuracy of dose predictions between manual and auto-segmented heart and substructures was evaluated by transferring the dose distribution of 240 previously treated lung cancer patients to the consensus data set.

RESULTS

The hybrid auto-segmentation method performed well with a heart dice similarity coefficient (DSC) of 0.95, with no statistically significant difference between the automatic and manual delineations. The DSC for the chambers varied from 0.78-0.86 for the automatic segmentation and was comparable with the inter-observer variability. Most importantly, the automatic segmentation was as precise as the clinical experts in predicting the dose distribution to the heart and all substructures.

CONCLUSION

The hybrid segmentation method performed well in delineating the heart and substructures. The prediction of dose by the automatic segmentation was aligned with the manual delineations, enabling measurement of heart and substructure dose in large cohorts. The delineation algorithm will be available for download.

Assessment of heart-substructures auto-contouring accuracy for application in heart-sparing radiotherapy for lung cancer

Objectives

We validated an auto-contouring algorithm for heart substructures in lung cancer patients, aiming to establish its accuracy and reliability for radiotherapy (RT) planning. We focus on contouring an amalgamated set of subregions in the base of the heart considered to be a new organ at risk, the cardiac avoidance area (CAA), to enable maximum dose limit implementation in lung RT planning.

Methods

The study validates a deep-learning model specifically adapted for auto-contouring the CAA (which includes the right atrium, aortic valve root, and proximal segments of the left and right coronary arteries). Geometric, dosimetric, quantitative, and qualitative validation measures are reported. Comparison with manual contours, including assessment of interobserver variability, and robustness testing over 198 cases are also conducted.

Results

Geometric validation shows that auto-contouring performance lies within the expected range of manual observer variability despite being slightly poorer than the average of manual observers (mean surface distance for CAA of 1.6 vs 1.2 mm, dice similarity coefficient of 0.86 vs 0.88). Dosimetric validation demonstrates consistency between plans optimized using auto-contours and manual contours. Robustness testing confirms acceptable contours in all cases, with 80% rated as "Good" and the remaining 20% as "Useful."

Conclusions

The auto-contouring algorithm for heart substructures in lung cancer patients demonstrates acceptable and comparable performance to human observers.

Advances in knowledge

Accurate and reliable auto-contouring results for the CAA facilitate the implementation of a maximum dose limit to this region in lung RT planning, which has now been introduced in the routine setting at our institution.

Identifying the optimal deep learning architecture and parameters for automatic beam aperture definition in 3D radiotherapy

PURPOSE

Two-dimensional radiotherapy is often used to treat cervical cancer in low- and middle-income countries, but treatment planning can be challenging and time-consuming. Neural networks offer the potential to greatly decrease planning time through automation, but the impact of the wide range of hyperparameters to be set during training on model accuracy has not been exhaustively investigated. In the current study, we evaluated the effect of several convolutional neural network architectures and hyperparameters on 2D radiotherapy treatment field delineation.

METHODS

Six commonly used deep learning architectures were trained to delineate four-field box apertures on digitally reconstructed radiographs for cervical cancer radiotherapy. A comprehensive search of optimal hyperparameters for all models was conducted by varying the initial learning rate, image normalization methods, and (when appropriate) convolutional kernel size, the number of learnable parameters via network depth and the number of feature maps per convolution, and nonlinear activation functions. This yielded over 1700 unique models, which were all trained until performance converged and then tested on a separate dataset.

RESULTS

Of all hyperparameters, the choice of initial learning rate was most consistently significant for improved performance on the test set, with all top-performing models using learning rates of 0.0001. The optimal image normalization was not consistent across architectures. High overlap (mean Dice similarity coefficient = 0.98) and surface distance agreement (mean surface distance < 2 mm) were achieved between the treatment field apertures for all architectures using the identified best hyperparameters. Overlap Dice similarity coefficient (DSC) and distance metrics (mean surface distance and Hausdorff distance) indicated that DeepLabv3+ and D-LinkNet architectures were least sensitive to initial hyperparameter selection.

CONCLUSION

DeepLabv3+ and D-LinkNet are most robust to initial hyperparameter selection. Learning rate, nonlinear activation function, and kernel size are also important hyperparameters for improving performance.

Artificial intelligence in cardiac computed tomography

Artificial Intelligence (AI) is a broad discipline of computer science and engineering. Modern application of AI encompasses intelligent models and algorithms for automated data analysis and processing, data generation, and prediction with applications in visual perception, speech understanding, and language translation. AI in healthcare uses machine learning (ML) and other predictive analytical techniques to help sort through vast amounts of data and generate outputs that aid in diagnosis, clinical decision support, workflow automation, and prognostication. Coronary computed tomography angiography (CCTA) is an ideal union for these applications due to vast amounts of data generation and analysis during cardiac segmentation, coronary calcium scoring, plaque quantification, adipose tissue quantification, peri-operative planning, fractional flow reserve quantification, and cardiac event prediction. In the past 5 years, there has been an exponential increase in the number of studies exploring the use of AI for cardiac computed tomography (CT) image acquisition, de-noising, analysis, and prognosis. Beyond image processing, AI has also been applied to improve the imaging workflow in areas such as patient scheduling, urgent result notification, report generation, and report communication. In this review, we discuss algorithms applicable to AI and radiomic analysis; we then present a summary of current and emerging clinical applications of AI in cardiac CT. We conclude with AI's advantages and limitations in this new field.

Development of a comprehensive cardiac atlas on a 1.5 Tesla Magnetic Resonance Linear Accelerator

Background and purpose

The 1.5 Tesla (T) Magnetic Resonance Linear Accelerator (MRL) provides an innovative modality for improved cardiac imaging when planning radiation treatment. No MRL based cardiac atlases currently exist, thus, we sought to comprehensively characterize cardiac substructures, including the conduction system, from cardiac images acquired using a 1.5 T MRL and provide contouring guidelines.

Materials and methods

Five volunteers were enrolled in a prospective protocol (NCT03500081) and were imaged on the 1.5 T MRL with Half Fourier Single-Shot Turbo Spin-Echo (HASTE) and 3D Balanced Steady-State Free Precession (bSSFP) sequences in axial, short axis, and vertical long axis. Cardiac anatomy was contoured by (AS) and confirmed by a board certified cardiologist (JR) with expertise in cardiac MR imaging.

Results

A total of five volunteers had images acquired with the HASTE sequence, with 21 contours created on each image. One of these volunteers had additional images obtained with 3D bSSFP sequences in the axial plane and additional images obtained with HASTE sequences in the key cardiac planes. Contouring guidelines were created and outlined. 15-16 contours were made for the short axis and vertical long axis. The cardiac conduction system was demonstrated with eleven representative contours. There was reasonable variation of contour volume across volunteers, with structures more clearly delineated on the 3D bSSFP sequence.

Conclusions

We present a comprehensive cardiac atlas using novel images acquired prospectively on a 1.5 T MRL. This cardiac atlas provides a novel resource for radiation oncologists in delineating cardiac structures for treatment with radiotherapy, with special focus on the cardiac conduction system.

Patient-Specific Auto-segmentation on Daily kVCT Images for Adaptive Radiation Therapy

PURPOSE

This study explored deep-learning-based patient-specific auto-segmentation using transfer learning on daily RefleXion kilovoltage computed tomography (kVCT) images to facilitate adaptive radiation therapy, based on data from the first group of patients treated with the innovative RefleXion system.

METHODS AND MATERIALS

For head and neck (HaN) and pelvic cancers, a deep convolutional segmentation network was initially trained on a population data set that contained 67 and 56 patient cases, respectively. Then the pretrained population network was adapted to the specific RefleXion patient by fine-tuning the network weights with a transfer learning method. For each of the 6 collected RefleXion HaN cases and 4 pelvic cases, initial planning computed tomography (CT) scans and 5 to 26 sets of daily kVCT images were used for the patient-specific learning and evaluation separately. The performance of the patient-specific network was compared with the population network and the clinical rigid registration method and evaluated by the Dice similarity coefficient (DSC) with manual contours being the reference. The corresponding dosimetric effects resulting from different auto-segmentation and registration methods were also investigated.

RESULTS

The proposed patient-specific network achieved mean DSC results of 0.88 for 3 HaN organs at risk (OARs) of interest and 0.90 for 8 pelvic target and OARs, outperforming the population network (0.70 and 0.63) and the registration method (0.72 and 0.72). The DSC of the patient-specific network gradually increased with the increment of longitudinal training cases and approached saturation with more than 6 training cases. Compared with using the registration contour, the target and OAR mean doses and dose-volume histograms obtained using the patient-specific auto-segmentation were closer to the results using the manual contour.

CONCLUSIONS

Auto-segmentation of RefleXion kVCT images based on the patient-specific transfer learning could achieve higher accuracy, outperforming a common population network and clinical registration-based method. This approach shows promise in improving dose evaluation accuracy in RefleXion adaptive radiation therapy.

A real-time contouring feedback tool for consensus-based contour training

Purpose

Variability in contouring structures of interest for radiotherapy continues to be challenging. Although training can reduce such variability, having radiation oncologists provide feedback can be impractical. We developed a contour training tool to provide real-time feedback to trainees, thereby reducing variability in contouring.

Methods

We developed a novel metric termed localized signed square distance (LSSD) to provide feedback to the trainee on how their contour compares with a reference contour, which is generated real-time by combining trainee contour and multiple expert radiation oncologist contours. Nine trainees performed contour training by using six randomly assigned training cases that included one test case of the heart and left ventricle (LV). The test case was repeated 30 days later to assess retention. The distribution of LSSD maps of the initial contour for the training cases was combined and compared with the distribution of LSSD maps of the final contours for all training cases. The difference in standard deviations from the initial to final LSSD maps, ΔLSSD, was computed both on a per-case basis and for the entire group.

Results

For every training case, statistically significant ΔLSSD were observed for both the heart and LV. When all initial and final LSSD maps were aggregated for the training cases, before training, the mean LSSD ([range], standard deviation) was -0.8 mm ([-37.9, 34.9], 4.2) and 0.3 mm ([-25.1, 32.7], 4.8) for heart and LV, respectively. These were reduced to -0.1 mm ([-16.2, 7.3], 0.8) and 0.1 mm ([-6.6, 8.3], 0.7) for the final LSSD maps during the contour training sessions. For the retention case, the initial and final LSSD maps of the retention case were aggregated and were -1.5 mm ([-22.9, 19.9], 3.4) and -0.2 mm ([-4.5, 1.5], 0.7) for the heart and 1.8 mm ([-16.7, 34.5], 5.1) and 0.2 mm ([-3.9, 1.6],0.7) for the LV.

Conclusions

A tool that uses real-time contouring feedback was developed and successfully used for contour training of nine trainees. In all cases, the utility was able to guide the trainee and ultimately reduce the variability of the trainee's contouring.

ASSET: Auto-Segmentation of the Seventeen SEgments for Ventricular Tachycardia Ablation in Radiation Therapy

There has been a recent effort to treat high-risk ventricular tachycardia (VT) patients through radio-ablation. However, manual segmentation of the VT target is complex and time-consuming. This work introduces ASSET, or Auto-segmentation of the Seventeen SEgments for Tachycardia ablation, to aid in radiation therapy (RT) planning. ASSET was retrospectively applied to CTs for 26 thoracic RT patients (13 undergoing VT ablation). The physician-defined parasternal long-axis of the left ventricle (LV) and the axes generated from principal component analysis (PCA) were compared using mean distance to agreement (MDA) and angle of separation. The manually selected right ventricle insertion point and LVs were used to apply the ASSET model to automatically generate the 17 segments of the LV myocardium (LVM). Physician-defined parasternal long-axis differed from PCA by 1.2 ± 0.3 mm MDA and 6.9 ± 0.7 degrees. Segments differed by 0.69 ± 0.29 mm MDA and 0.89 ± 0.03 Dice similarity coefficient. Running ASSET takes <5 min where manual segmentation took >2 h/patient. Agreement between ASSET and expert contours was comparable to inter-observer variability. Qualitative scoring conducted by three experts revealed automatically generated segmentations were clinically useable as-is. ASSET offers efficient and reliable automatic segmentations for the 17 segments of the LVM for target generation in RT planning.

Evaluation of the cardiac subvolume dose and myocardial perfusion in left breast cancer patients with postoperative radiotherapy: a prospective study

Adjuvant breast radiotherapy could reduce the risk of local recurrence. However, the radiation dose received by the heart also increases the risk of cardiotoxicity and causes consequential heart diseases. This prospective study aimed to evaluate more precisely cardiac subvolume doses and corresponding myocardial perfusion defects according to the American Heart Association (AHA)'s 20-segment model for single photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) interpretation for breast cancer after radiotherapy. The 61 female patients who underwent adjuvant radiotherapy following breast cancer surgery for left breast cancer were enrolled. SPECT MPI were performed before radiotherapy for baseline study, and 12 months after for follow-up. Enrolled patients were divided into two groups, new perfusion defect (NPD) and non new perfusion defect found (non-NPD) according to myocardial perfusion scale score. CT simulation data, radiation treatment planning, and SPECT MPI images were fused and registered. The left ventricle was divided into four rings, three territories, and 20 segments according to the AHA's 20-segment model of the LV. The doses between NPD and non-NPD groups were compared by the Mann-Whitney test. The patients were divided into two groups: NPD group (n = 28) and non-NPD group (n = 33). The mean heart dose was 3.14 Gy in the NPD group and 3.08 Gy in the non-NPD group. Mean LV doses were 4.84 Gy and 4.71 Gy, respectively. The radiation dose of the NPD group was higher than the non-NPD group in the 20 segments of LV. There was significant difference in segment 3 (p = 0.03). The study indicated that the radiation doses to 20 segments of LV in NPD were higher than those in non-NPD significantly at segment 3, and higher in other segments in general. In the bull's eye plot combining radiation dose and NPD area, we found that the new cardiac perfusion decline may exist even in the low radiation dose region.Trial registration: FEMH-IRB-101085-F. Registered 01/01/2013, https://clinicaltrials.gov/ct2/show/NCT01758419?cond=NCT01758419&draw=2&rank=1 .

Validation of a Fully Automated Hybrid Deep Learning Cardiac Substructure Segmentation Tool for Contouring and Dose Evaluation in Lung Cancer Radiotherapy

BACKGROUND AND PURPOSE

Accurate and consistent delineation of cardiac substructures is challenging. The aim of this work was to validate a novel segmentation tool for automatic delineation of cardiac structures and subsequent dose evaluation, with potential application in clinical settings and large-scale radiation-related cardiotoxicity studies.

MATERIALS AND METHODS

A recently developed hybrid method for automatic segmentation of 18 cardiac structures, combining deep learning, multi-atlas mapping and geometric segmentation of small challenging substructures, was independently validated on 30 lung cancer cases. These included anatomical and imaging variations, such as tumour abutting heart, lung collapse and metal artefacts. Automatic segmentations were compared with manual contours of the 18 structures using quantitative metrics, including Dice similarity coefficient (DSC), mean distance to agreement (MDA) and dose comparisons.

RESULTS

A comparison of manual and automatic contours across all cases showed a median DSC of 0.75-0.93 and a median MDA of 2.09-3.34 mm for whole heart and chambers. The median MDA for great vessels, coronary arteries, cardiac valves, sinoatrial and atrioventricular conduction nodes was 3.01-8.54 mm. For the 27 cases treated with curative intent (planned target volume dose ≥50 Gy), the median dose difference was -1.12 to 0.57 Gy (absolute difference of 1.13-3.25%) for the mean dose to heart and chambers; and -2.25 to 4.45 Gy (absolute difference of 0.94-6.79%) for the mean dose to substructures.

CONCLUSION

The novel hybrid automatic segmentation tool reported high accuracy and consistency over a validation set with challenging anatomical and imaging variations. This has promising applications in substructure dose calculations of large-scale datasets and for future studies on long-term cardiac toxicity.

Open-source, fully-automated hybrid cardiac substructure segmentation: development and optimisation

Radiotherapy for thoracic and breast tumours is associated with a range of cardiotoxicities. Emerging evidence suggests cardiac substructure doses may be more predictive of specific outcomes, however, quantitative data necessary to develop clinical planning constraints is lacking. Retrospective analysis of patient data is required, which relies on accurate segmentation of cardiac substructures. In this study, a novel model was designed to deliver reliable, accurate, and anatomically consistent segmentation of 18 cardiac substructures on computed tomography (CT) scans. Thirty manually contoured CT scans were included. The proposed multi-stage method leverages deep learning (DL), multi-atlas mapping, and geometric modelling to automatically segment the whole heart, cardiac chambers, great vessels, heart valves, coronary arteries, and conduction nodes. Segmentation performance was evaluated using the Dice similarity coefficient (DSC), mean distance to agreement (MDA), Hausdorff distance (HD), and volume ratio. Performance was reliable, with no errors observed and acceptable variation in accuracy between cases, including in challenging cases with imaging artefacts and atypical patient anatomy. The median DSC range was 0.81-0.93 for whole heart and cardiac chambers, 0.43-0.76 for great vessels and conduction nodes, and 0.22-0.53 for heart valves. For all structures the median MDA was below 6 mm, median HD ranged 7.7-19.7 mm, and median volume ratio was close to one (0.95-1.49) for all structures except the left main coronary artery (2.07). The fully automatic algorithm takes between 9 and 23 min per case. The proposed fully-automatic method accurately delineates cardiac substructures on radiotherapy planning CT scans. Robust and anatomically consistent segmentations, particularly for smaller structures, represents a major advantage of the proposed segmentation approach. The open-source software will facilitate more precise evaluation of cardiac doses and risks from available clinical datasets.

Multicenter comparison of measures for quantitative evaluation of contouring in radiotherapy

•

There is variation in contour measurement definitions used between institutions.

•

Differences in implementation can result in large discrepancies in reported results.

•

Many in-house implementations were found to have bugs in at least one measure.

•

Extreme care should be taken comparing results from different studies.

•

A dataset with known ground truth values would assist in validation of such tools.

Background and Purpose

A wide range of quantitative measures are available to facilitate clinical implementation of auto-contouring software, on-going Quality Assurance (QA) and interobserver contouring variation studies. This study aimed to assess the variation in output when applying different implementations of the measures to the same data in order to investigate how consistently such measures are defined and implemented in radiation oncology.

Materials and Methods

A survey was conducted to assess if there were any differences in definitions of contouring measures or their implementations that would lead to variation in reported results between institutions. This took two forms: a set of computed tomography (CT) image data with “Test” and “Reference” contours was distributed for participants to process using their preferred tools and report results, and a questionnaire regarding the definition of measures and their implementation was completed by the participants.

Results

Thirteen participants completed the survey and submitted results, with one commercial and twelve in-house solutions represented. Excluding outliers, variations of up to 50% in Dice Similarity Coefficient (DSC), 50% in 3D Hausdorff Distance (HD), and 200% in Average Distance (AD) were observed between the participant submitted results. Collaborative investigation with participants revealed a large number of bugs in implementation, confounding the understanding of intentional implementation choices.

Conclusion

Care must be taken when comparing quantitative results between different studies. There is a need for a dataset with clearly defined measures and ground truth for validation of such tools prior to their use.

Role of Real-World Data in Assessing Cardiac Toxicity After Lung Cancer Radiotherapy

Radiation-induced heart disease (RIHD) is a recent concern in patients with lung cancer after being treated with radiotherapy. Most of information we have in the field of cardiac toxicity comes from studies utilizing real-world data (RWD) as randomized controlled trials (RCTs) are generally not practical in this field. This article is a narrative review of the literature using RWD to study RIHD in patients with lung cancer following radiotherapy, summarizing heart dosimetric factors associated with outcome, strength, and limitations of the RWD studies, and how RWD can be used to assess a change to cardiac dose constraints.

Validation of an established deep learning auto-segmentation tool for cardiac substructures in 4D radiotherapy planning scans

•

Cardiotoxicity is a common complication of lung cancer radiotherapy.

•

Segmentation of cardiac substructures is time-consuming and challenging.

•

Deep learning segmentation tools can perform this task in 3D and 4D scans.

•

Performance is high when assessed geometrically, dosimetrically and clinically.

•

Auto-segmentation tools may accelerate clinical workflows and enable research.

Background

Emerging data suggest that dose-sparing several key cardiac regions is prognostically beneficial in lung cancer radiotherapy. The cardiac substructures are challenging to contour due to their complex geometry, poor soft tissue definition on computed tomography (CT) and cardiorespiratory motion artefact. A neural network was previously trained to generate the cardiac substructures using three-dimensional radiotherapy planning CT scans (3D-CT). In this study, the performance of that tool on the average intensity projection from four-dimensional (4D) CT scans (4D-AVE), now commonly used in lung radiotherapy, was evaluated.

Materials and Methods

The 4D-AVE of n=20 patients completing radiotherapy for lung cancer 2015–2020 underwent manual and automated cardiac substructure segmentation. Manual and automated substructures were compared geometrically and dosimetrically. Two senior clinicians also qualitatively assessed the auto-segmentation tool’s output.

Results

Geometric comparison of the automated and manual segmentations exhibited high levels of similarity across parameters, including volume difference (11.8% overall) and Dice similarity coefficient (0.85 overall), and were consistent with 3D-CT performance. Differences in mean (median 0.2 Gy, range −1.6–0.3 Gy) and maximum (median 0.4 Gy, range −2.2–0.9 Gy) doses to substructures were generally small. Nearly all structures (99.5 %) were deemed to be appropriate for clinical use without further editing.

Conclusions

Cardiac substructure auto-segmentation using a deep learning-based tool trained on a 3D-CT dataset was feasible on the 4D-AVE scan, meaning this tool is suitable for use on 4D-CT radiotherapy planning scans. Application of this tool would increase the practicality of routine clinical cardiac substructure delineation, and enable further cardiac radiation effects research.

Radiation-Induced Cardiac Dysfunction: Optimizing Radiation Delivery and Postradiation Care

Radiation therapy (RT) is part of standard-of-care treatment of many thoracic cancers. More than 60% of patients receiving thoracic RT may eventually develop radiation-induced cardiac dysfunction (RICD) secondary to collateral heart dose. This article reviews factors contributing to a thoracic cancer patient's risk for RICD, including RT dose to the heart and/or cardiac substructures, other anticancer treatments, and a patient's cardiometabolic health. It is also discussed how automated tracking of these factors within electronic medical record environments may aid radiation oncologists and other treating physicians in their ability to prevent, detect, and/or treat RICD in this expanding patient population.

Mutual enhancing learning-based automatic segmentation of CT cardiac substructure

Objective. Current segmentation practice for thoracic cancer RT considers the whole heart as a single organ despite increased risks of cardiac toxicities from irradiation of specific cardiac substructures. Segmenting up to 15 different cardiac substructures can be a very time-intensive process, especially due to their different volume sizes and anatomical variations amongst different patients. In this work, a new deep learning (DL)-based mutual enhancing strategy is introduced for accurate and automatic segmentation, especially of smaller substructures such as coronary arteries. Approach. Our proposed method consists of three subnetworks: retina U-net, classification module, and segmentation module. Retina U-net is used as a backbone network architecture that aims to learn deep features from the whole heart. Whole heart feature maps from retina U-net are then transferred to four different sets of classification modules to generate classification localization maps of coronary arteries, great vessels, chambers of the heart, and valves of the heart. Each classification module is in sync with its corresponding subsequent segmentation module in a bootstrapping manner, allowing them to share their encoding paths to generate a mutual enhancing strategy. We evaluated our method on three different datasets: institutional CT datasets (55 subjects) 2) publicly available Multi-Modality Whole Heart Segmentation (MM-WHS) challenge datasets (120 subjects), and Automated Cardiac Diagnosis Challenge (ACDC) datasets (100 subjects). For institutional datasets, we performed five-fold cross-validation on training data (45 subjects) and performed inference on separate hold-out data (10 subjects). For each subject, 15 cardiac substructures were manually contoured by a resident physician and evaluated by an attending radiation oncologist. For the MM-WHS dataset, we trained the network on 100 datasets and performed an inference on a separate hold-out dataset with 20 subjects, each with 7 cardiac substructures. For ACDC datasets, we performed five-fold cross-validation on 100 datasets, each with 3 cardiac substructures. We compared the proposed method against four different network architectures: 3D U-net, mask R-CNN, mask scoring R-CNN, and proposed network without classification module. Segmentation accuracies were statistically compared through dice similarity coefficient, Jaccard, 95% Hausdorff distance, mean surface distance, root mean square distance, center of mass distance, and volume difference. Main results. The proposed method generated cardiac substructure segmentations with significantly higher accuracy (P < 0.05) for small substructures, especially for coronary arteries such as left anterior descending artery (CA-LADA) and right coronary artery (CA-RCA) in comparison to four competing methods. For large substructures (i.e. chambers of the heart), our method yielded comparable results to mask scoring R-CNN method, resulting in significantly (P < 0.05) improved segmentation accuracy in comparison to 3D U-net and mask R-CNN. Significance. A new DL-based mutual enhancing strategy was introduced for automatic segmentation of cardiac substructures. Overall results of this work demonstrate the ability of the proposed method to improve segmentation accuracies of smaller substructures such as coronary arteries without largely compromising the segmentation accuracies of larger substructures. Fast and accurate segmentations of up to 15 substructures can possibly be used as a tool to rapidly generate substructure segmentations followed by physicians’ reviews to improve clinical workflow.

Unmet needs in the management of unresectable stage III non-small cell lung cancer: a review after the 'Radio Talk' webinars

INTRODUCTION

Stage III non-small cell lung cancer (NSCLC) is a variable entity, encompassing bulky primary tumors, nodal involvement or both. Multidisciplinary evaluation is essential to discuss multiple treatment options, to outline optimal management and to examine the main debated topics and critical issues not addressed by current trials and guidelines that influence daily clinical practice.

AREAS COVERED

From March to May 2021, 5 meetings were scheduled in a webinar format titled 'Radio Talk' due to the COVID-19 pandemic; the faculty was composed of 6 radiation oncologists from 6 different Institutions of Italy, all of them were the referring radiation oncologist for lung cancer treatment at their respective departments and were or had been members of AIRO (Italian Association of Radiation Oncology) Thoracic Oncology Study Group. The topics covered included: pulmonary toxicity, cardiac toxicity, radiotherapy dose, fractionation and volumes, unfit/elderly patients, multidisciplinary management.

EXPERT OPINION

The debate was focused on the unmet needs triggered by case reports, personal experiences and questions; the answers were often not univocal, however, the exchange of opinion and the contribution of different centers confirmed the role of multidisciplinary management and the necessity that the most critical issues should be investigated in clinical trials.

Validation of a Whole Heart Segmentation from Computed Tomography Imaging Using a Deep-Learning Approach

The aim of this study is to develop an automated deep-learning-based whole heart segmentation of ECG-gated computed tomography data. After 21 exclusions, CT acquired before transcatheter aortic valve implantation in 71 patients were reviewed and randomly split in a training (n = 55 patients), validation (n = 8 patients), and a test set (n = 8 patients). A fully automatic deep-learning method combining two convolutional neural networks performed segmentation of 10 cardiovascular structures, which was compared with the manually segmented reference by the Dice index. Correlations and agreement between myocardial volumes and mass were assessed. The algorithm demonstrated high accuracy (Dice score = 0.920; interquartile range: 0.906-0.925) and a low computing time (13.4 s, range 11.9-14.9). Correlations and agreement of volumes and mass were satisfactory for most structures. Six of ten structures were well segmented. Deep-learning-based method allowed automated WHS from ECG-gated CT data with a high accuracy. Challenges remain to improve right-sided structures segmentation and achieve daily clinical application.

The Impact of Radiation Dose to Heart Substructures on Major Coronary Events and Patient Survival after Chemoradiation Therapy for Esophageal Cancer

Background: There is a paucity of data regarding the association between radiation exposure of heart substructures and the incidence of major coronary events (MCEs) in patients with esophageal cancer (ESOC) undergoing chemoradiation therapy. We studied radiation dosimetric determinants of MCE risk and measured their impact on patient prognosis using a cohort of ESOC patients treated at a single institution. Methods: Between March 2005 and October 2015, 355 ESOC patients treated with concurrent chemoradiotherapy were identified from a prospectively maintained and institutional-regulatory-board-approved clinical database. Dose-distribution parameters of the whole heart, the atria, the ventricles, the left main coronary artery, and three main coronary arteries were extracted for analysis. Results: Within a median follow-up time of 67 months, 14 patients experienced MCEs at a median of 16 months. The incidence of MCEs was significantly associated with the left anterior descending coronary artery (LAD) receiving ≥30 Gy (V30Gy) (p = 0.048). Patients receiving LAD V30Gy ≥ 10% of volume experienced a higher incidence of MCEs versus the LAD V30Gy < 10% group (p = 0.044). The relative rate of death increased with the left main coronary artery (LMA) mean dose (Gy) (p = 0.002). Furthermore, a mutual promotion effect of hyperlipidemia and RT on MCEs was observed. Conclusion: Radiation dose to coronary substructures is associated with MCEs and overall survival in patients with ESOC. In this study, the doses to these substructures appeared to be better predictors of toxicity outcomes than mean heart dose (MHD) or whole-heart V30Gy. These findings have implications for reducing coronary events through radiation therapy planning.

Atlas-based auto-segmentation for delineating the heart and cardiac substructures in breast cancer radiation therapy

BACKGROUND

This study aimed to develop and validate an automatic multi-atlas segmentation method for delineating the heart and substructures in breast cancer radiation therapy (RT).

MATERIAL AND METHODS

The atlas database consisted of non-contrast-enhanced planning CT scans from 42 breast cancer patients, each with one manual delineation of the heart and 22 cardiac substructures. Half of the patients were scanned during free-breathing, the rest were scanned during a deep inspiration breath-hold. The auto-segmentation was developed in the MIM software system and validated geometrically and dosimetrically in two steps: The first validation in a small dataset to ensure consistency of the atlas. This was succeeded by a final test where multiple manual delineations in CT scans of 12 breast cancer patients were compared to the auto-segmentation. For geometric evaluation, the dice similarity coefficient (DSC) and the mean surface distance (MSD) were used. For dosimetric evaluation, the RT doses to each substructure in the manual and the automatic delineations were compared.

RESULTS

In the first validation, a high geometric and dosimetric performance between the automatic and manual delineations was observed for all substructures. The final test confirmed a high agreement between the automatic and manual delineations for the heart (DSC = 0.94) and the cardiac chambers (DSC: 0.75-0.86). The difference in MSD between the automatic and manual delineations was low (<4 mm) in all structures. Finally, a high correlation between mean RT doses for the automatic and the manual delineations was observed for the heart and substructures.

CONCLUSIONS

An automatic segmentation tool for delineation of the heart and substructures in breast cancer RT was developed and validated with a high correlation between the automatic and manual delineations. The atlas is pivotal for large-scale evaluations of radiation-associated heart disease.

Deep learning for automatic target volume segmentation in radiation therapy: a review

Deep learning, a new branch of machine learning algorithm, has emerged as a fast growing trend in medical imaging and become the state-of-the-art method in various clinical applications such as Radiology, Histo-pathology and Radiation Oncology. Specifically in radiation oncology, deep learning has shown its power in performing automatic segmentation tasks in radiation therapy for Organs-At-Risks (OAR), given its potential in improving the efficiency of OAR contouring and reducing the inter- and intra-observer variabilities. The similar interests were shared for target volume segmentation, an essential step of radiation therapy treatment planning, where the gross tumor volume is defined and microscopic spread is encompassed. The deep learning-based automatic segmentation method has recently been expanded into target volume automatic segmentation. In this paper, the authors summarized the major deep learning architectures of supervised learning fashion related to target volume segmentation, reviewed the mechanism of each infrastructure, surveyed the use of these models in various imaging domains (including Computational Tomography with and without contrast, Magnetic Resonant Imaging and Positron Emission Tomography) and multiple clinical sites, and compared the performance of different models using standard geometric evaluation metrics. The paper concluded with a discussion of open challenges and potential paths of future research in target volume automatic segmentation and how it may benefit the clinical practice.

Robustness of deep learning segmentation of cardiac substructures in noncontrast computed tomography for breast cancer radiotherapy

PURPOSE

To develop and evaluate deep learning-based autosegmentation of cardiac substructures from noncontrast planning computed tomography (CT) images in patients undergoing breast cancer radiotherapy and to investigate the algorithm sensitivity to out-of-distribution data such as CT image artifacts.

METHODS

Nine substructures including aortic valve (AV), left anterior descending (LAD), tricuspid valve (TV), mitral valve (MV), pulmonic valve (PV), right atrium (RA), right ventricle (RV), left atrium (LA), and left ventricle (LV) were manually delineated by a radiation oncologist on noncontrast CT images of 129 patients with breast cancer; among them 90 were considered in-distribution data, also named as "clean" data. The image/label pairs of 60 subjects were used to train a 3D deep neural network while the remaining 30 were used for testing. The rest of the 39 patients were considered out-of-distribution ("outlier") data, which were used to test robustness. Random rigid transformations were used to augment the dataset during training. We investigated multiple loss functions, including Dice similarity coefficient (DSC), cross-entropy (CE), Euclidean loss as well as the variation and combinations of these, data augmentation, and network size on overall performance and sensitivity to image artifacts due to infrequent events such as the presence of implanted devices. The predicted label maps were compared to the ground-truth labels via DSC and mean and 90th percentile symmetric surface distance (90th-SSD).

RESULTS

When modified Dice combined with cross-entropy (MD-CE) was used as the loss function, the algorithm achieved a mean DSC = 0.79 ± 0.07 for chambers and  0.39 ± 0.10 for smaller substructures (valves and LAD). The mean and 90th-SSD were 2.7 ± 1.4 and 6.5 ± 2.8 mm for chambers and 4.1 ± 1.7 and 8.6 ± 3.2 mm for smaller substructures. Models with MD-CE, Dice-CE, MD, and weighted CE loss had highest performance, and were statistically similar. Data augmentation did not affect model performances on both clean and outlier data and model robustness was susceptible to network size. For a certain type of outlier data, robustness can be improved via incorporating them into the training process. The execution time for segmenting each patient was on an average 2.1 s.

CONCLUSIONS

A deep neural network provides a fast and accurate segmentation of large cardiac substructures in noncontrast CT images. Model robustness of two types of clinically common outlier data were investigated and potential approaches to improve them were explored. Evaluation of clinical acceptability and integration into clinical workflow are pending.

Application of an automatic segmentation method for evaluating cardiac structure doses received by breast radiotherapy patients

•

Atlas-based method for contouring heart substructures on breast radiotherapy CT.

•

Excellent agreement between automatic and manual contours for most patients.

•

Dice similarity coefficient for LAD was low (0.06) because a narrow, long structure.

•

Doses derived from automatic and manual contours agree within observer variability.

•

For left breast treatment, right ventricle and LAD dose most senstive to contour shift.

Background and purpose

Quantifying radiation dose to cardiac substructures is important for research on the etiology and prevention of complications following radiotherapy; however, segmentation of substructures is challenging. In this study we demonstrate the application of our atlas-based automatic segmentation method to breast cancer radiotherapy plans for generating radiation doses in support of late effects research.

Material and methods

We applied our segmentation method to contour heart substructures on the computed tomography (CT) images of 70 breast cancer patients who received external photon radiotherapy. Two cardiologists provided manual segmentation of the whole heart (WH), left/right atria, left/right ventricles, and left anterior descending artery (LAD). The automatically contours were compared with manual delineations to evaluate similarity in terms of geometry and dose.

Results

The mean Dice similarity coefficient between manual and automatic segmentations was 0.96 for the WH, 0.65 to 0.82 for the atria and ventricles, and 0.06 for the LAD. The mean average surface distance was 1.2 mm for the WH, 3.4 to 4.1 mm for the atria and ventricles, and 6.4 mm for the LAD. We found the dose to the cardiac substructures based on our automatic segmentation agrees with manual segmentation within expected observer variability. For left breast patients, the mean absolute difference in mean dose was 0.1 Gy for the WH, 0.2 to 0.7 Gy for the atria and ventricles, and 1.8 Gy for the LAD. For right breast patients, these values were 0.0 Gy, 0.1 to 0.4 Gy, and 0.4 Gy, respectively.

Conclusion

Our automatic segmentation method will facilitate the development of radiotherapy prescriptive criteria for mitigating cardiovascular complications.

Cardiac substructure exposure in breast radiotherapy: a comparison between intensity modulated proton therapy and volumetric modulated arc therapy

INTRODUCTION

Proton therapy for breast cancer treatment reduces cardiac radiation exposure. Left-sided breast cancer patients with indication for internal mammary chain (IMC) irradiation are most at risk of radiation-induced cardiotoxicity. This study aims to evaluate in this situation the potential dosimetric benefit of intensity modulated proton therapy (IMPT) over volumetric modulated arc therapy (VMAT) at the cardiac substructure level.

MATERIALS AND METHODS

Cardiac substructures were retrospectively delineated according to ESTRO guidelines on the simulation CT scans of fourteen left-sided breast cancer patients having undergone conserving surgery and adjuvant locoregional free-breathing (FB-) or deep inspiration breath-hold (DIBH-) VMAT with internal mammary chain irradiation. IMPT treatment was re-planned on the simulation CT scans. Mean doses to cardiac substructures were retrieved and compared between VMAT treatment plans and IMPT simulation plans. Pearson correlation coefficients were calculated between mean doses delivered to cardiac substructures using these two techniques.

RESULTS

Mean doses to all cardiac substructures were significantly lower with IMPT than with VMAT. Regardless of the irradiation technique, the most exposed cardiac substructure was the mid segment of the left anterior descending coronary artery (LADCA). Pearson correlation coefficients between mean doses to cardiac substructures were usually weak and statistically non-significant for IMPT; mean heart dose (MHD) only correlated with mean doses delivered to the right ventricle, to the mid segment of the right coronary artery (RCA) and, to a lesser extent, to the LADCA.

CONCLUSION

The dosimetric benefit of IMPT over conformal photon therapy was consistently observed for all cardiac substructures. MHD may not be a reliable dosimetric parameter for precise cardiac exposure evaluation when planning IMPT.

Validation of separate multi-atlases for auto segmentation of cardiac substructures in CT-scans acquired in deep inspiration breath hold and free breathing

BACKGROUND AND PURPOSE

Developing NTCP-models for cardiac complications after breast cancer (BC) radiotherapy requires cardiac dose-volume parameters for many patients. These can be obtained by using multi-atlas based automatic segmentation (MABAS) of cardiac structures in planning CT scans. We investigated the relevance of separate multi-atlases for deep inspiration breath hold (DIBH) and free breathing (FB) CT scans.

MATERIALS AND METHODS

BC patients scanned in DIBH (n = 10) and in FB (n = 20) were selected to create separate multi-atlases consisting of expert panel delineations of the whole heart, atria and ventricles. The accuracy of atlas-generated contours was validated with expert delineations in independent datasets (n = 10 for DIBH and FB) and reported as Dice coefficients, contour distances and dose-volume differences in relation to interobserver variability of manual contours. Dependency of MABAS contouring accuracy on breathing technique was assessed by validation of a FB atlas in DIBH patients and vice versa (cross-validation).

RESULTS

For all structures the FB and DIBH atlases resulted in Dice coefficients with their respective reference contours ≥ 0.8 and average contour distances ≤ 2 mm smaller than slice thickness of (CTs). No significant differences were found for dose-volume parameters in volumes receiving relevant dose levels (WH, LV and RV). Accuracy of the DIBH atlas was at least similar to, and for the ventricles better than, the interobserver variation in manual delineation. Cross-validation between breathing techniques showed a reduced MABAS performance.

CONCLUSION

Multi-atlas accuracy was at least similar to interobserver delineation variation. Separate atlases for scans made in DIBH and FB could benefit atlas performance because accuracy depends on breathing technique.

Training deep-learning segmentation models from severely limited data

PURPOSE

To enable generation of high-quality deep learning segmentation models from severely limited contoured cases (e.g., ~10 cases).

METHODS

Thirty head and neck computed tomography (CT) scans with well-defined contours were deformably registered to 200 CT scans of the same anatomic site without contours. Acquired deformation vector fields were used to train a principal component analysis (PCA) model for each of the 30 contoured CT scans by capturing the mean deformation and most prominent variations. Each PCA model can produce an infinite number of synthetic CT scans and corresponding contours by applying random deformations. We used 300, 600, 1000, and 2000 synthetic CT scans and contours generated from one PCA model to train V-Net, a 3D convolutional neural network architecture, to segment parotid and submandibular glands. We repeated the training using same numbers of training cases generated from 7, 10, 20, and 30 PCA models, with the data distributed evenly between each PCA model. Performance of the segmentation models was evaluated with Dice similarity coefficients between auto-generated contours and physician-drawn contours on 162 test CT scans for parotid glands and another 21 test CT scans for submandibular glands.

RESULTS

Dice values varied with the number of synthetic CT scans and the number of PCA models used to train the network. By using 2000 synthetic CT scans generated from 10 PCA models, we achieved Dice values of 82.8% ± 6.8% for right parotid, 82.0% ± 6.9% for left parotid, and 74.2% ± 6.8% for submandibular glands. These results are comparable with those obtained from state-of-the-art auto-contouring approaches, including a deep learning network trained from more than 1000 contoured patients and a multi-atlas algorithm from 12 well-contoured atlases. Improvement was marginal when >10 PCA models or >2000 synthetic CT scans were used.

CONCLUSIONS

We demonstrated an effective data augmentation approach to train high-quality deep learning segmentation models from a limited number of well-contoured patient cases.

Impact of slice thickness, pixel size, and CT dose on the performance of automatic contouring algorithms

Purpose

To investigate the impact of computed tomography (CT) image acquisition and reconstruction parameters, including slice thickness, pixel size, and dose, on automatic contouring algorithms.

Methods

Eleven scans from patients with head‐and‐neck cancer were reconstructed with varying slice thicknesses and pixel sizes. CT dose was varied by adding noise using low‐dose simulation software. The impact of these imaging parameters on two in‐house auto‐contouring algorithms, one convolutional neural network (CNN)‐based and one multiatlas‐based system (MACS) was investigated for 183 reconstructed scans. For each algorithm, auto‐contours for organs‐at‐risk were compared with auto‐contours from scans with 3 mm slice thickness, 0.977 mm pixel size, and 100% CT dose using Dice similarity coefficient (DSC), Hausdorff distance (HD), and mean surface distance (MSD).

Results

Increasing the slice thickness from baseline value of 3 mm gave a progressive reduction in DSC and an increase in HD and MSD on average for all structures. Reducing the CT dose only had a relatively minimal effect on DSC and HD. The rate of change with respect to dose for both auto‐contouring methods is approximately 0. Changes in pixel size had a small effect on DSC and HD for CNN‐based auto‐contouring with differences in DSC being within 0.07. Small structures had larger deviations from the baseline values than large structures for DSC. The relative differences in HD and MSD between the large and small structures were small.

Conclusions

Auto‐contours can deviate substantially with changes in CT acquisition and reconstruction parameters, especially slice thickness and pixel size. The CNN was less sensitive to changes in pixel size, and dose levels than the MACS. The results contraindicated more restrictive values for the parameters should be used than a typical imaging protocol for head‐and‐neck.

Autosegmentation of cardiac substructures in respiratory-gated, non-contrasted computed tomography images

BACKGROUND

Radiation dose to specific cardiac substructures can have a significant on treatment related morbidity and mortality, yet definition of these structures is labor intensive and not standard. Autosegmentation software may potentially address these issues, however it is unclear whether this approach can be broadly applied across different treatment planning conditions. We investigated the feasibility of autosegmentation of the cardiac substructures in four-dimensional (4D) computed tomography (CT), respiratory-gated, non-contrasted imaging.

AIM

To determine whether autosegmentation can be successfully employed on 4DCT respiratory-gated, non-contrasted imaging.

METHODS

We included patients who underwent stereotactic body radiation therapy for inoperable, early-stage non-small cell lung cancer from 2007 to 2019. All patients were simulated via 4DCT imaging with respiratory gating without intravenous contrast. Generated structure quality was evaluated by degree of required manual edits and volume discrepancy between the autocontoured structures and its edited sister structure.

RESULTS

Initial 17-structure cardiac atlas was generated with 20 patients followed by three successive iterations of 10 patients using MIM software. The great vessels and heart chambers were reliably autosegmented with most edits considered minor. In contrast, coronary arteries either failed to be autosegmented or the generated structures required major alterations necessitating deletion and manual definition. Similarly, the generated mitral and tricuspid valves were poor whereas the aortic and pulmonary valves required at least minor and moderate changes respectively. For the majority of subsites, the additional samples did not appear to substantially impact the quality of generated structures. Volumetric analysis between autosegmented and its manually edited sister structure yielded comparable findings to the physician-based assessment of structure quality.

CONCLUSION

The use of MIM software with 30-sample subject library was found to be useful in delineating many of the heart substructures with acceptable clinical accuracy on respiratory-gated 4DCT imaging. Small volume structures, such as the coronary arteries were poorly autosegmented and require manual definition.

Use of Multi-Site Radiation Therapy for Systemic Disease Control

Metastatic cancer is a heterogeneous entity, some of which could benefit from local consolidative radiation therapy (RT). Although randomized evidence is growing in support of using RT for oligometastatic disease, a highly active area of investigation relates to whether RT could benefit patients with polymetastatic disease. This article highlights the preclinical and clinical rationale for using RT for polymetastatic disease, proposes an exploratory framework for selecting patients best suited for these types of treatments, and briefly reviews potential challenges. The goal of this hypothesis-generating review is to address personalized multimodality systemic treatment for patients with metastatic cancer. The rationale for using high-dose RT is primarily for local control and immune activation in either oligometastatic or polymetastatic disease. However, the primary application of low-dose RT is to activate distinct antitumor immune pathways and modulate the tumor stroma in efforts to better facilitate T cell infiltration. We explore clinical cases involving high- and low-dose RT to demonstrate the potential efficacy of such treatment. We then group patients by extent of disease burden to implement high- and/or low-dose RT. Patients with low-volume disease may receive high-dose RT to all sites as part of an oligometastatic paradigm. Subjects with high-volume disease (for whom standard of care remains palliative RT only) could be treated with a combination of high-dose RT to a few sites for immune activation, while receiving low-dose RT to several remaining lesions to enhance systemic responses from high-dose RT and immunotherapy. We further discuss how emerging but speculative concepts such as immune function may be integrated into this approach and examine therapies currently under investigation that may help address immune deficiencies. The review concludes by addressing challenges in using RT for polymetastatic disease, such as concerns about treatment planning workflows, treatment times, dose constraints for multiple-isocenter treatments, and economic considerations.

Validation of a new open-source method for automatic delineation and dose assessment of the heart and LADCA in breast radiotherapy with simultaneous uncertainty estimation

Radiotherapy has been shown to increase risks of cardiotoxicities for breast cancer patients. Automated delineation approaches are necessary for consistent and efficient assessment of cardiac doses in large, retrospective datasets, while patient-specific estimation of the uncertainty in these doses provides valuable additional data for modelling and understanding risks. In this work, we aim to validate the consistency of our previously described open-source software model for automatic cardiac delineation in the context of dose assessment, relative to manual contouring. We also extend our software to introduce a novel method to automatically quantify the uncertainty in cardiac doses based on expected inter-observer variability (IOV) in contouring. This method was applied to a cohort of 15 left-sided breast cancer patients treated in Denmark using modern tangential radiotherapy techniques. On each image set, the whole heart and left anterior descending coronary artery (LADCA) were contoured by nine independent experts; the range of doses to these nine volumes provided a reference for the dose uncertainties generated from the automatic method. Local and external atlas sets were used to test the method. Results give confidence in the consistency of automatic segmentations, with mean whole heart dose differences for local and external atlas sets of -0.20 ± 0.17 and -0.10 ± 0.14 Gy, respectively. Automatic estimates of uncertainties in doses are similar to those from IOV for both the whole heart and LADCA. Overall, this study confirms that our automated approach can be used to accurately assess cardiac doses, and the proposed method can provide a useful tool in estimating dose uncertainties.

Feasibility of using a novel automatic cardiac segmentation algorithm in the clinical routine of lung cancer patients

Incidental radiation exposure to the heart during lung cancer radiotherapy is associated with radiation-induced heart disease and increased rates of mortality. By considering the respiratory-induced motion of the heart it is possible to create a radiotherapy plan that results in a lower overall cardiac dose. This approach is challenging using current clinical practices: manual contouring of the heart is time consuming, and subject to inter- and intra-observer variability. In this work, we investigate the feasibility of our previously developed, atlas-based, automatic heart segmentation tool to delineate the heart in four-dimensional x-ray computed tomography (4D-CT) images. We used a dataset comprising 19 patients receiving radiotherapy for lung cancer, with 4D-CT imaging acquired at 10 respiratory phases and with a maximum intensity projection image generated from these. For each patient, one of four experienced radiation oncologists contoured the heart on each respiratory phase image and the maximum intensity image. Automatic segmentation of the heart on these same patient image sets was achieved using a leave-one-out approach, where for each patient the remaining 18 were used as an atlas set. The consistency of the automatic segmentation relative to manual contouring was evaluated using the Dice similarity coefficient (DSC) and mean absolute surface-to-surface distance (MASD). The DSC and MASD are comparable to inter-observer variability in clinically acceptable whole heart delineations (average DSC > 0.93 and average MASD < 2.0 mm in all the respiratory phases). The comparison between automatic and manual delineations on the maximum intensity images produced an overall mean DSC of 0.929 and a mean MASD of 2.07 mm. The automatic, atlas-based segmentation tool produces clinically consistent and robust heart delineations and is easy to implement in the routine care of lung cancer patients.

Tissue-specific deformable image registration using a spatial-contextual filter

Intensity-based deformable registration with spatial-invariant regularization generally fails when distinct motion exists across different types of tissues. The purpose of this work was to develop and validate a new regularization approach for deformable image registration that is tissue-specific and able to handle motion discontinuities. Our approach was built upon a Demons registration framework, and used the image context supplementing the original spatial constraint to regularize displacement vector fields in iterative image registration process. The new regularization was implemented as a spatial-contextual filter, which favors the motion vectors within the same tissue type but penalizes the motion vectors from different tissues. This approach was validated using five public lung cancer patients, each with 300 landmark pairs identified by a thoracic radiation oncologist. The mean and standard deviation of the landmark registration errors were 1.3 ± 0.8 mm, compared with those of 2.3 ± 2.9 mm using the original Demons algorithm. Particularly, for the case with the largest initial landmark displacement of 15 ± 9 mm, the modified Demons algorithm had a registration error of 1.3 ± 1.1 mm, while the original Demons algorithm had a registration error of 3.6 ± 5.9 mm. We also qualitatively evaluated the modified Demons algorithm using two difficult cases in our routine clinic: one lung case with large sliding motion and one head and neck case with large anatomical changes in air cavity. Visual evaluation on the deformed image created by the deformable image registration showed that the modified Demons algorithm achieved reasonable registration accuracy, but the original Demons algorithm produced distinct registration errors.

Proton versus Photon Breath-Hold Radiation for Left-Sided Breast Cancer after Breast-Conserving Surgery: A Dosimetric Comparison

PURPOSE

Radiation to breast, chest wall, and/or regional nodes is an integral component of breast cancer management in many situations. Irradiating left-sided breast and/or regional nodes may be technically challenging because of cardiac tolerance and subsequent risk of long-term cardiac complications. Deep inspiratory breath-hold (DIBH) technique physically separates cardiac structures away from radiation target volume, thus reducing cardiac dose with either photon (Ph) or proton beam therapy (PBT). The utility of combining PBT with DIBH is less well understood.

METHODS AND MATERIALS

We compared photon-DIBH (Ph-DIBH) versus proton DIBH (Pr-DIBH) for different planning parameters, including target coverage and organ at risk (OAR) sparing. Necessary ethical permission was obtained from the institutional review board. Ten previous patients with irradiated, intact, left-sided breast and Ph-DIBH were replanned with PBT for dosimetric comparison. Clinically relevant normal OARs were contoured, and Ph plans were generated with parallel, opposed tangent beams and direct fields for supraclavicular and/or axillae whenever required. For proton planning, all targets were delineated individually and best possible coverage of planning target volume was achieved. Dose-volume histogram was analyzed to determine the difference in doses received by different OARs. Minimum and maximum dose (Dmin and Dmax ) as well as dose received by a specific volume of OAR were compared. Each patient's initial plan (Ph-DIBH) was used as a control for comparing newly devised PBT plan (Pr-DIBH). Matched, paired t tests were applied to determine any significant differences between the 2 plans.

RESULTS

Both the plans were adequate in target coverage. Dose to cardiac structure subunits and ipsilateral lung were significantly reduced with the proton breath-hold technique. Significant dose reduction with Pr-DIBH was observed in comparison to Ph-DIBH for mean dose (D mean) to the heart (0.23 Gy versus 1.19 Gy; P < .001); D mean to the left ventricle (0.25 Gy versus 1.7 Gy; P < .001); D mean, D max, and the half-maximal dose to the left anterior descending artery (1.15 Gy versus 5.54 Gy; P < .003; 7.7 Gy versus 22.15 Gy; P < .007; 1.61 Gy versus 4.42 Gy, P < .049); D max of the left circumflex coronary artery (0.13 Gy versus 1.35 Gy; P < .001) and D mean, the volume to the ipsilateral lung receiving 20 Gy and 5 Gy (2.28 Gy versus 8.04 Gy; P < .001; 2.36 Gy versus 15.54 Gy, P < .001; 13.9 Gy versus 30.28 Gy; P = .002). However, skin dose and contralateral breast dose were not significantly improved with proton.

CONCLUSION

This comparative dosimetric study showed significant benefit of Pr-DIBH technique compared with Ph-DIBH in terms of cardiopulmonary sparing and may be the area of future clinical research.

Evaluation of a delineation software for cardiac atlas-based autosegmentation: An example of the use of artificial intelligence in modern radiotherapy

PURPOSE

The primary objective of this work was to implement and evaluate a cardiac atlas-based autosegmentation technique based on the "Workflow Box" software (Mirada Medical, Oxford UK), in order to delineate cardiac substructures according to European Society of Therapeutic Radiation Oncology (ESTRO) guidelines; review and comparison with other cardiac atlas-based autosegmentation algorithms published to date.

MATERIALS AND METHODS

Of an atlas of data set from 20 breast cancer patients' CT scans with recontoured cardiac substructures creation according to the ESTRO guidelines. Performance evaluation on a validation data set consisting of 20 others CT scans acquired in the same treatment position: cardiac substructure were automatically contoured by the Mirada system, using the implemented cardiac atlas, and simultaneously manually contoured by a radiation oncologist. The Dice similarity coefficient was used to evaluate the concordance level between the manual and the automatic segmentations.

RESULTS

Dice similarity coefficient value was 0.95 for the whole heart and 0.80 for the four cardiac chambers. Average Dice similarity coefficient value for the left ventricle walls was 0.50, ranging between 0.34 for the apical wall and 0.70 for the lateral wall. Compared to manual contours, autosegmented substructure volumes were significantly smaller, with the exception of the left ventricle. Coronary artery segmentation was unsuccessful. Performances were overall similar to other published cardiac atlas-based autosegmentation algorithms.

CONCLUSION

The evaluated cardiac atlas-based autosegmentation technique, using the Mirada software, demonstrated acceptable performance for cardiac cavities delineation. However, algorithm improvement is still needed in order to develop efficient and trusted cardiac autosegmentation working tools for daily practice.

Dose-sparing effect of deep inspiration breath hold technique on coronary artery and left ventricle segments in treatment of breast cancer

BACKGROUND AND PURPOSE

The risk of radiation-induced cardiac injury remains a challenging problem in the treatment of breast cancer. Certain cardiac structures receive higher doses than others, which results in variable frequencies of radiation-induced injuries across these structures. Radiation dose can be reduced using the deep inspiration breath hold (DIBH) technique. We aimed to investigate the dose reductions from DIBH in individual cardiac segments.

MATERIALS AND METHODS

A dosimetric analysis was performed on left-sided breast cancer patients who underwent breast-conserving surgery and whole breast irradiation. Radiation doses to the cardiac structures were compared between the DIBH and free-breathing (FB) techniques and the dose reductions with DIBH were correlated to the lung expansion.

RESULTS

For the 75 patients included in our study, DIBH effectively reduced doses to the heart, left lung, left anterior descending coronary artery (LAD) and left ventricle (LV), but the degree of dose reductions was variable across different structures. The absolute dose reductions were greatest in the distal LAD (14.4 Gy) and apical LV (12.1 Gy) segments, compared with the other LAD (middle 9.7 Gy, proximal 1.6 Gy) and LV (anterior 5.3 Gy, lateral 2.9 Gy, septal 2.0 Gy, inferior 0.2 Gy) segments. Left lung expansion was significantly correlated with the dose reductions in the LAD (Spearman's rank correlation coefficient, ρ, 0.304) and LV (ρ, 0.420) segments.

CONCLUSIONS

Our study demonstrates the dose-sparing effects of DIBH in various cardiac structures, especially the distal LAD and apical LV segments. The large dose reductions seen in the distal LAD and apical LV segments could potentially translate into clinical benefit of reduced cardiac toxicity, as these structures have been previously shown to receive the highest doses and are associated with radiation-induced injury.

Automated Radiation Treatment Planning for Cervical Cancer

The radiation treatment-planning process includes contouring, planning, and reviewing the final plan, and each component requires substantial time and effort from multiple experts. Automation of treatment planning can save time and reduce the cost of radiation treatment, and potentially provides more consistent and better quality plans. With the recent breakthroughs in computer hardware and artificial intelligence technology, automation methods for radiation treatment planning have achieved a clinically acceptable level of performance in general. At the same time, the automation process should be developed and evaluated independently for different disease sites and treatment techniques as they are unique from each other. In this article, we will discuss the current status of automated radiation treatment planning for cervical cancer for simple and complex plans and corresponding automated quality assurance methods. Furthermore, we will introduce Radiation Planning Assistant, a web-based system designed to fully automate treatment planning for cervical cancer and other treatment sites.

Fully Automatic Treatment Planning for External-Beam Radiation Therapy of Locally Advanced Cervical Cancer: A Tool for Low-Resource Clinics

Purpose

The purpose of this study was to validate a fully automatic treatment planning system for conventional radiotherapy of cervical cancer. This system was developed to mitigate staff shortages in low-resource clinics.

Methods

In collaboration with hospitals in South Africa and the United States, we have developed the Radiation Planning Assistant (RPA), which includes algorithms for automating every step of planning: delineating the body contour, detecting the marked isocenter, designing the treatment-beam apertures, and optimizing the beam weights to minimize dose heterogeneity. First, we validated the RPA retrospectively on 150 planning computed tomography (CT) scans. We then tested it remotely on 14 planning CT scans at two South African hospitals. Finally, automatically planned treatment beams were clinically deployed at our institution.

Results

The automatically and manually delineated body contours agreed well (median mean surface distance, 0.6 mm; range, 0.4 to 1.9 mm). The automatically and manually detected marked isocenters agreed well (mean difference, 1.1 mm; range, 0.1 to 2.9 mm). In validating the automatically designed beam apertures, two physicians, one from our institution and one from a South African partner institution, rated 91% and 88% of plans acceptable for treatment, respectively. The use of automatically optimized beam weights reduced the maximum dose significantly (median, −1.9%; P < .001). Of the 14 plans from South Africa, 100% were rated clinically acceptable. Automatically planned treatment beams have been used for 24 patients with cervical cancer by physicians at our institution, with edits as needed, and its use is ongoing.

Conclusion

We found that fully automatic treatment planning is effective for cervical cancer radiotherapy and may provide a reliable option for low-resource clinics. Prospective studies are ongoing in the United States and are planned with partner clinics.

Novel Methodology to Investigate the Effect of Radiation Dose to Heart Substructures on Overall Survival

PURPOSE

For patients with lung cancer treated with radiation therapy, a dose to the heart is associated with excess mortality; however, it is often not feasible to spare the whole heart. Our aim is to define cardiac substructures and dose thresholds that optimally reduce early mortality.

METHODS AND MATERIALS

Fourteen cardiac substructures were delineated on 5 template patients with representative anatomies. One thousand one hundred sixty-one patients with non-small cell lung cancer were registered nonrigidly to these 5 template anatomies, and their radiation therapy doses were mapped. Mean and maximum dose to each substructure were extracted, and the means were evaluated as input to prediction models. The cohort was bootstrapped into 2 variable reduction techniques: elastic net least absolute shrinkage and selection operator and the random survival forest model. Each method was optimized to extract variables contributing most to overall survival, and model coefficients were evaluated to select these substructures. The most important variables common to both models were selected and evaluated in multivariable Cox-proportional hazard models. A threshold dose was defined, and Kaplan-Meier survival curves plotted.

RESULTS

Nine hundred seventy-eight patients remained after visual quality assurance of the registration. Ranking the model coefficients across the bootstraps selected the maximum dose to the right atrium, right coronary artery, and ascending aorta as the most important factors associated with survival. The maximum dose to the combined cardiac region showed significance in the multivariable model, a hazard ratio of 1.01/Gy, and P = .03 after accounting for tumor volume (P < .001), N stage (P < .01), and performance status (P = .01). The optimal threshold for the maximum dose, equivalent dose in 2-Gy fractions, was 23 Gy. Kaplan-Meier survival curves showed a significant split (log-rank P = .008).

CONCLUSIONS

The maximum dose to the combined cardiac region encompassing the right atrium, right coronary artery, and ascending aorta was found to have the greatest effect on patient survival. A maximum equivalent dose in 2-Gy fractions of 23 Gy was identified for consideration as a dose limit in future studies.

Cardio-pulmonary substructure segmentation of radiotherapy computed tomography images using convolutional neural networks for clinical outcomes analysis

Background and purpose

Radiation dose to the cardio-pulmonary system is critical for radiotherapy-induced mortality in non-small cell lung cancer. Our goal was to automatically segment substructures of the cardio-pulmonary system for use in outcomes analyses for thoracic cancers. We built and validated a multi-label Deep Learning Segmentation (DLS) model for accurate auto-segmentation of twelve cardio-pulmonary substructures.

Materials and methods

The DLS model utilized a convolutional neural network for segmenting substructures from 217 thoracic radiotherapy Computed Tomography (CT) scans. The model was built in the presence of variable image characteristics such as the absence/presence of contrast. We quantitatively evaluated the final model against expert contours for a hold-out dataset of 24 CT scans using Dice Similarity Coefficient (DSC), 95th Percentile of Hausdorff Distance and Dose-volume Histograms (DVH). DLS contours of an additional 25 scans were qualitatively evaluated by a radiation oncologist to determine their clinical acceptability.

Results

The DLS model reduced segmentation time per patient from about one hour to 10 s. Quantitatively, the highest accuracy was observed for the Heart (median DSC = (0.96 (0.95–0.97)). The median DSC for the remaining structures was between 0.81 and 0.93. No statistically significant difference was found between DVH metrics of the auto-generated and manual contours (p-value ⩾ 0.69). The expert judged that, on average, 85% of contours were qualitatively equivalent to state-of-the-art manual contouring.

Conclusion

The cardio-pulmonary DLS model performed well both quantitatively and qualitatively for all structures. This model has been incorporated into an open-source tool for the community to use for treatment planning and clinical outcomes analysis.

CT images with expert manual contours of thoracic cancer for benchmarking auto-segmentation accuracy

PURPOSE

Automatic segmentation offers many benefits for radiotherapy treatment planning; however, the lack of publicly available benchmark datasets limits the clinical use of automatic segmentation. In this work, we present a well-curated computed tomography (CT) dataset of high-quality manually drawn contours from patients with thoracic cancer that can be used to evaluate the accuracy of thoracic normal tissue auto-segmentation systems.

ACQUISITION AND VALIDATION METHODS

Computed tomography scans of 60 patients undergoing treatment simulation for thoracic radiotherapy were acquired from three institutions: MD Anderson Cancer Center, Memorial Sloan Kettering Cancer Center, and the MAASTRO clinic. Each institution provided CT scans from 20 patients, including mean intensity projection four-dimensional CT (4D CT), exhale phase (4D CT), or free-breathing CT scans depending on their clinical practice. All CT scans covered the entire thoracic region with a 50-cm field of view and slice spacing of 1, 2.5, or 3 mm. Manual contours of left/right lungs, esophagus, heart, and spinal cord were retrieved from the clinical treatment plans. These contours were checked for quality and edited if necessary to ensure adherence to RTOG 1106 contouring guidelines.

DATA FORMAT AND USAGE NOTES

The CT images and RTSTRUCT files are available in DICOM format. The regions of interest were named according to the nomenclature recommended by American Association of Physicists in Medicine Task Group 263 as Lung_L, Lung_R, Esophagus, Heart, and SpinalCord. This dataset is available on The Cancer Imaging Archive (funded by the National Cancer Institute) under Lung CT Segmentation Challenge 2017 (http://doi.org/10.7937/K9/TCIA.2017.3r3fvz08).

POTENTIAL APPLICATIONS

This dataset provides CT scans with well-delineated manually drawn contours from patients with thoracic cancer that can be used to evaluate auto-segmentation systems. Additional anatomies could be supplied in the future to enhance the existing library of contours.