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

Investigation of cardiac substructure automatic segmentation methods on synthetically generated 4D cone-beam CT images

BACKGROUND

STereotactic Arrhythmia Radioablation (STAR) is a novel noninvasive method for treating arrythmias in which external beam radiation is directed towards subregions of the heart. Challenges for accurate STAR targeting include small target volumes and relatively large patient motion, which can lead to radiation related patient toxicities. 4D Cone-beam CT (CBCT) images are used for stereotactic lung treatments to account for respiration-related patient motion. 4D-CBCT imaging could similarly be used to account for respiration-related patient motion in STAR; however, the poor contrast of heart tissue in CBCT makes identifying cardiac substructures in 4D-CBCT images challenging. If cardiac structures can be identified in pre-treatment 4D-CBCT images, then the location of the target volume can be more accurately identified for different phases of the respiration cycle, leading to more accurate targeting and a reduction in patient toxicities.

PURPOSE

The aim of this simulation study is to investigate the accuracy of different cardiac substructure segmentation methods for 4D-CBCT images.

METHODS

Repeat 4D-CT scans from 13 lung cancer patients were obtained from The Cancer Imaging Archive. Synthetic 4D-CBCT images for each patient were simulated by forward projecting and reconstructing each respiration phase of a chosen "testing" 4D-CT scan. Eighteen cardiac structures were segmented from each respiration phase image in the testing 4D-CT using the previously validated platipy toolkit. The platipy segmentations from the testing 4D-CT were defined as the ground truth segmentations for the synthetic 4D-CBCT images. Five different 4D-CBCT cardiac segmentation methods were investigated: 3D Rigid Alignment, 4D Rigid Alignment, Direct CBCT Segmentation, Contour Transformation, and Synthetic CT Segmentation methods. For all methods except the Direct CBCT segmentation method, a separate 4D-CT (Planning CT) was used to assist in generating 4D-CBCT segmentations. Segmentation performance was measured using the Dice similarity coefficient (DSC), Hausdorff distance (HD), mean surface distance (MSD), and volume ratio (VR) metrics.

RESULTS

The mean ± standard deviation DSC for all cardiac substructures for the 3D Rigid Alignment, 4D Rigid Alignment, Direct CBCT Segmentation, Contour Transformation, and Synthetic CT Segmentation methods were 0.48 ± 0.29, 0.52 ± 0.29, 0.37 ± 0.32, 0.53 ± 0.29, 0.57 ± 0.28, respectively. Similarly, the HD values were 10.9 ± 3.6 , 9.9 ± 2.6 , 17.3 ± 5.3 , 9.9 ± 2.8 , 9.3 ± 3.0 mm, the MSD values were 2.9 ± 0.6 , 2.9 ± 0.6 , 6.3 ± 2.5 , 2.5 ± 0.6 , 2.4 ± 0.8 mm, and the VR Values were 0.81 ± 0.12, 0.78 ± 0.14, 1.10 ± 0.47, 0.72 ± 0.15, 0.98 ± 0.44, respectively. Of the five methods investigated the Synthetic CT segmentation method generated the most accurate segmentations for all calculated segmentation metrics.

CONCLUSION

This simulation study investigates the accuracy of different cardiac substructure segmentation methods for 4D-CBCT images. Accurate 4D-CBCT cardiac segmentation will provide more accurate information on the location of cardiac anatomy during STAR treatments which can lead to safer and more effective STAR. As the data and segmentation methods used in this study are all open source, this study provides a useful benchmarking tool to evaluate other CBCT cardiac segmentation methods.

Auto-contouring of cardiac substructures for Stereotactic arrhythmia radioablation (STAR): A STOPSTORM.eu consortium study

BACKGROUND/PURPOSE

High doses to healthy cardiac substructures (CS) in stereotactic arrhythmia radioablation (STAR) raise concerns regarding potential treatment-induced cardio-toxicity. However, CS contours are not routinely created, hindering the understanding of the CS dose-effect relationships. To address this issue, the alignment of CS contouring was initiated within the STOPSTORM consortium. In this study, we developed and evaluated auto-contouring models trained to delineate CS and major vessels in ventricular tachycardia (VT) patients.

METHODS

Eight centres provided standard treatment planning computed tomography (CT) and/or contrast-enhanced CT datasets of 55 VT patients, each including 16 CS. Auto-contouring models were trained to contour either large structures or small structures. Dice Similarity Coefficient (DSC), 95 % Hausdorff distance (HD95) and volume ratio (VR) were used to evaluate model performance versus inter-observer variation (IOV) on seven VT patient test cases. Significant differences were tested using the Mann-Whitney U test.

RESULTS

The performance on the four chambers and the major vessels (median DSC: 0.88; HD95: 5.8-19.4 mm; VR: 1.09) was similar to the IOV (median DSC: 0.89; HD95: 4.8-14.0 mm; VR: 1.20). For the valves, model performance (median DSC: 0.37; HD95: 11.6 mm; VR: 1.63) was similar to the IOV (median DSC: 0.41; HD95: 12.4 mm; VR: 3.42), but slightly worse for the coronary arteries (median DSC: 0.33 vs 0.42; HD95: 24.4 mm vs 16.9 mm; VR: 1.93 vs 3.30). The IOV for these small structures remains large despite using contouring guidelines.

CONCLUSION

CS auto-contouring models trained on VT patient data perform similarly to IOV. This allows for time-efficient evaluation of CS as possible organs-at-risk.

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.

The influence of cardiac substructure dose on survival in a large lung cancer stereotactic radiotherapy cohort using a robust personalized contour analysis

BACKGROUND/PURPOSE

Radiation-induced cardiac toxicity in lung cancer patients has received increased attention since RTOG 0617. However, large cohort studies with accurate cardiac substructure (CS) contours are lacking, limiting our understanding of the potential influence of individual CSs. Here, we analyse the correlation between CS dose and overall survival (OS) while accounting for deep learning (DL) contouring uncertainty, α / β uncertainty and different modelling approaches.

MATERIALS/METHODS

This single institution, retrospective cohort study includes 730 patients (early-stage tumours (I or II). All treated: 2009-2019), who received stereotactic body radiotherapy (≥ 5 Gy per fraction). A DL model was trained on 70 manually contoured patients to create 12 cardio-vascular structures. Structures with median dice score above 0.8 and mean surface distance (MSD) <2 mm during testing, were further analysed. Patientspecific CS dose was used to find the correlation between CS dose and OS with elastic net and random survival forest models (with and without confounding clinical factors). The influence of delineation-induced dose uncertainty on OS was investigated by expanding/contracting the DL-created contours using the MSD ± 2 standard deviations.

RESULTS

Eight CS contours met the required performance level. The left atrium (LA) mean dose was significant for OS and an LA mean dose of 3.3 Gy (in EQD2) was found as a significant dose stratum.

CONCLUSION

Explicitly accounting for input parameter uncertainty in lung cancer survival modelling was crucial in robustly identifying critical CS dose parameters. Using this robust methodology, LA mean dose was revealed as the most influential CS dose parameter.

Cardiac Substructure Dose and Survival in Stereotactic Radiotherapy for Lung Cancer: Results of the Multi-Centre SSBROC Trial

BACKGROUND AND PURPOSE

Stereotactic ablative body radiotherapy (SABR) is increasingly used for early-stage lung cancer, however the impact of dose to the heart and cardiac substructures remains largely unknown. The study investigated doses received by cardiac substructures in SABR patients and impact on survival.

MATERIALS AND METHODS

SSBROC is an Australian multi-centre phase II prospective study of SABR for stage I non-small cell lung cancer. Patients were treated between 2013 and 2019 across 9 centres. In this secondary analysis of the dataset, a previously published and locally developed open-source hybrid deep learning cardiac substructure automatic segmentation tool was deployed on the planning CTs of 117 trial patients. Physical doses to 18 cardiac structures and EQD2 converted doses (α/β = 3) were calculated. Endpoints evaluated include pericardial effusion and overall survival. Associations between cardiac doses and survival were analysed with the Kaplan-Meier method and Cox proportional hazards models.

RESULTS

Cardiac structures that received the highest physical mean doses were superior vena cava (22.5 Gy) and sinoatrial node (18.3 Gy). The highest physical maximum dose was received by the heart (51.7 Gy) and right atrium (45.3 Gy). Three patients developed grade 2, and one grade 3 pericardial effusion. The cohort receiving higher than median mean heart dose (MHD) had poorer survival compared to those who received below median MHD (p = 0.00004). On multivariable Cox analysis, male gender and maximum dose to ascending aorta were significant for worse survival.

CONCLUSIONS

Patients treated with lung SABR may receive high doses to cardiac substructures. Dichotomising the patients according to median mean heart dose showed a clear difference in survival. On multivariable analyses gender and dose to ascending aorta were significant for survival, however cardiac substructure dosimetry and outcomes should be further explored in larger studies.

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.

Automation and artificial intelligence in radiation therapy treatment planning

Automation and artificial intelligence (AI) is already possible for many radiation therapy planning and treatment processes with the aim of improving workflows and increasing efficiency in radiation oncology departments. Currently, AI technology is advancing at an exponential rate, as are its applications in radiation oncology. This commentary highlights the way AI has begun to impact radiation therapy treatment planning and looks ahead to potential future developments in this space. Historically, radiation therapist's (RT's) role has evolved alongside the adoption of new technology. In Australia, RTs have key clinical roles in both planning and treatment delivery and have been integral in the implementation of automated solutions for both areas. They will need to continue to be informed, to adapt and to transform with AI technologies implemented into clinical practice in radiation oncology departments. RTs will play an important role in how AI-based automation is implemented into practice in Australia, ensuring its application can truly enable personalised and higher-quality treatment for patients. To inform and optimise utilisation of AI, research should not only focus on clinical outcomes but also AI's impact on professional roles, responsibilities and service delivery. Increased efficiencies in the radiation therapy workflow and workforce need to maintain safe improvements in practice and should not come at the cost of creativity, innovation, oversight and safety.

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.

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.

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.