Protecting the Heart: A Practical Approach to Account for the Full Extent of Heart Motion in Radiation Therapy Planning

Osorio, Eliana Vásquez; McCallum, H.; Bedair, Ahmed; Faivre-Finn, Corinne; Haughey, Aisling; Herk, Marcel van; Iqbal, Muhammad Shahid; McWilliam, A.; Price, Gareth J; Byrne, John; Cobben, D.

doi:10.1016/j.ijrobp.2020.06.068

Cited by 11 publications

(7 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multiple studies measured the magnitude of the cardio-respiratory motion of the heart and its substructures among free-breathing patients [12,13]. However, deep inhalation breath-hold (DIBH) represents one of the most well studied cardiac sparing techniques [14], and its application leads to the necessity of accurate information about the substructure motion and dose variation due to cardiac activity.…”

Section: Introductionmentioning

confidence: 99%

Dosimetric impact from cardiac motion to heart substructures in thoracic cancer patients treated with a magnetic resonance guided radiotherapy system

Yan

Chu

Gao

et al. 2021

Physics and Imaging in Radiation Oncology

View full text Add to dashboard Cite

Few studies have examined the cardiac volume and radiation dose differences among cardiac phases during radiation therapy (RT). Such information is crucial to dose reconstruction and understanding of RT related cardiac toxicity. In a cohort of nine patients, we studied the changes in the volume and doses of several cardiac substructures between the end-diastolic and end-systolic phases based on the clinical magnetic resonance-guided RT (MRgRT) treatment plans. Significant differences in the volume and dose between the two phases were observed. Onboard cardiac cine MRI holds promise for patient-specific cardiac sparing treatment designs.

show abstract

Section: Introductionmentioning

confidence: 99%

Dosimetric impact from cardiac motion to heart substructures in thoracic cancer patients treated with a magnetic resonance guided radiotherapy system

Yan

Chu

Gao

et al. 2021

Physics and Imaging in Radiation Oncology

View full text Add to dashboard Cite

show abstract

“…The main limitations of this study are the cohort size and restriction to lung cancer cases. The 4D-AVE was used rather than the MIP despite prior work demonstrating the whole heart on 4D-AVE requires larger PRV margins than on MIP [47] . However, 4D-AVE was chosen for its superior soft tissue definition suited to delineating the complex geometries of the cardiac substructures, and for its similarity to the 3D-CT scan, on which our deep learning tool was based.…”

Section: Discussionmentioning

confidence: 99%

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

Walls¹,

Giacometti²,

Apte

et al. 2022

Physics and Imaging in Radiation Oncology

View full text Add to dashboard Cite

“…However, reliance on the FBCT means that motion is ignored in the model, and this is generally a limitation of any cardiac or intracardiac contouring process unless cardiac gating is used at the time of CT simulation. Methods to account for local motion of the heart in radiation treatment planning have recently been proposed, 41 but information is lacking on motion of specific cardiac substructures. This is an area that needs further study to better inform models such as the proposed which may be used to prospectively generate radiation treatment plans.…”

Section: Discussionmentioning

confidence: 99%

Automatic delineation of cardiac substructures using a region‐based fully convolutional network

et al. 2021

View full text Add to dashboard Cite

Purpose Radiation dose to specific cardiac substructures, such as the atria and ventricles, has been linked to post‐treatment toxicity and has shown to be more predictive of these toxicities than dose to the whole heart. A deep learning‐based algorithm for automatic generation of these contours is proposed to aid in either retrospective or prospective dosimetric studies to better understand the relationship between radiation dose and toxicities. Methods The proposed method uses a mask‐scoring regional convolutional neural network (RCNN) which consists of five major subnetworks: backbone, regional proposal network (RPN), RCNN head, mask head, and mask‐scoring head. Multiscale feature maps are learned from computed tomography (CT) via the backbone network. The RPN utilizes these feature maps to detect the location and region‐of‐interest (ROI) of all substructures, and the final three subnetworks work in series to extract structural information from these ROIs. The network is trained using 55 patient CT datasets, with 22 patients having contrast scans. Threefold cross validation (CV) is used for evaluation on 45 datasets, and a separate cohort of 10 patients are used for holdout evaluation. The proposed method is compared to a 3D UNet. Results The proposed method produces contours that are qualitatively similar to the ground truth contours. Quantitatively, the proposed method achieved average Dice score coefficients (DSCs) for the whole heart, chambers, great vessels, coronary arteries, the valves of the heart of 0.96, 0.94, 0.93, 0.66, and 0.77 respectively, outperforming the 3D UNet, which achieved DSCs of 0.92, 0.87, 0.88, 0.48, and 0.59 for the corresponding substructure groups. Mean surface distances (MSDs) between substructures segmented by the proposed method and the ground truth were <2 mm except for the left anterior descending coronary artery and the mitral and tricuspid valves, and <5 mm for all substructures. When dividing results into noncontrast and contrast datasets, the model performed statistically significantly better in terms of DSC, MSD, centroid mean distance (CMD), and volume difference for the chambers and whole heart with contrast. Notably, the presence of contrast did not statistically significantly affect coronary artery segmentation DSC or MSD. After network training, all substructures and the whole heart can be segmented on new datasets in less than 5 s. Conclusions A deep learning network was trained for automatic delineation of cardiac substructures based on CT alone. The proposed method can be used as a tool to investigate the relationship between cardiac substructure dose and treatment toxicities.

show abstract

Protecting the Heart: A Practical Approach to Account for the Full Extent of Heart Motion in Radiation Therapy Planning

Cited by 11 publications

References 34 publications

Dosimetric impact from cardiac motion to heart substructures in thoracic cancer patients treated with a magnetic resonance guided radiotherapy system

Dosimetric impact from cardiac motion to heart substructures in thoracic cancer patients treated with a magnetic resonance guided radiotherapy system

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

Automatic delineation of cardiac substructures using a region‐based fully convolutional network

Contact Info

Product

Resources

About