Estimation of the displacement of cardiac substructures and the motion of the coronary arteries using electrocardiographic gating

Tan, Wenyong; Xu, Liying; Wang, Xionghong; Qiu, Dasheng; Hân, Gia; Hu, Desheng

doi:10.2147/ott.s52101

Cited by 19 publications

(23 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, cardiac motion is not managed clinically due to limitations in available treatment technologies. Nevertheless, the magnitude of cardiac motion is on the order of 3-8 mm 63 suggesting internal motion may be incorporated into future margin design as has been previously proposed. 64,65 As MR-guided RT and MR-only planning become more prevalent, future work will include training an MR-only model.…”

Section: Discussionmentioning

confidence: 99%

Cardiac substructure segmentation with deep learning for improved cardiac sparing

et al. 2019

View full text Add to dashboard Cite

Purpose Radiation dose to cardiac substructures is related to radiation‐induced heart disease. However, substructures are not considered in radiation therapy planning (RTP) due to poor visualization on CT. Therefore, we developed a novel deep learning (DL) pipeline leveraging MRI’s soft tissue contrast coupled with CT for state‐of‐the‐art cardiac substructure segmentation requiring a single, non‐contrast CT input. Materials/methods Thirty‐two left‐sided whole‐breast cancer patients underwent cardiac T2 MRI and CT‐simulation. A rigid cardiac‐confined MR/CT registration enabled ground truth delineations of 12 substructures (chambers, great vessels (GVs), coronary arteries (CAs), etc.). Paired MRI/CT data (25 patients) were placed into separate image channels to train a three‐dimensional (3D) neural network using the entire 3D image. Deep supervision and a Dice‐weighted multi‐class loss function were applied. Results were assessed pre/post augmentation and post‐processing (3D conditional random field (CRF)). Results for 11 test CTs (seven unique patients) were compared to ground truth and a multi‐atlas method (MA) via Dice similarity coefficient (DSC), mean distance to agreement (MDA), and Wilcoxon signed‐ranks tests. Three physicians evaluated clinical acceptance via consensus scoring (5‐point scale). Results The model stabilized in ~19 h (200 epochs, training error <0.001). Augmentation and CRF increased DSC 5.0 ± 7.9% and 1.2 ± 2.5%, across substructures, respectively. DL provided accurate segmentations for chambers (DSC = 0.88 ± 0.03), GVs (DSC = 0.85 ± 0.03), and pulmonary veins (DSC = 0.77 ± 0.04). Combined DSC for CAs was 0.50 ± 0.14. MDA across substructures was <2.0 mm (GV MDA = 1.24 ± 0.31 mm). No substructures had statistical volume differences (P > 0.05) to ground truth. In four cases, DL yielded left main CA contours, whereas MA segmentation failed, and provided improved consensus scores in 44/60 comparisons to MA. DL provided clinically acceptable segmentations for all graded patients for 3/4 chambers. DL contour generation took ~14 s per patient. Conclusions These promising results suggest DL poses major efficiency and accuracy gains for cardiac substructure segmentation offering high potential for rapid implementation into RTP for improved cardiac sparing.

show abstract

Section: Discussionmentioning

confidence: 99%

Cardiac substructure segmentation with deep learning for improved cardiac sparing

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Heart [16,34,70] Cranial: The whole heart starts just inferior to the left pulmonary artery Caudal: The heart blends with the diaphragm If contrast is administered, the superior vena cava (SVC) can generally be separately contoured from the whole heart. In a noncontrast scan, the SVC can be included for simplification and consistency…”

Section: Definition Notementioning

confidence: 99%

“…Left main coronary artery [34,70] Defined from its origin in the aortic sinus to the first branches Originates from the left side of the ascending aorta, inferior to the right pulmonary artery…”

Section: Definition Notementioning

confidence: 99%

“…Right coronary artery [34,70] Originates from the right side of the ascending aorta Left anterior descending artery [34,70] Defined from where they branched at the left or right main coronary artery to the caudal edge of the endocardial surface of the left ventricle…”

Section: Definition Notementioning

confidence: 99%

“…Left circumflex artery [34,70] Originates from the left coronary artery and runs between the left atrium and ventricle Right marginal artery [70] -Aortic valve [34] No Found within the ascending aorta and seen in cross section on axial CT Pulmonic valve [34] No Found within the pulmonary trunk and seen in cross section on axial CT Tricuspid valve [34] No Located between the right atrium and ventricle. It is difficult to see, but it is defined as the area where the blood pool between the atrium and ventricle is shared…”

Section: Definition Notementioning

confidence: 99%

See 2 more Smart Citations

Radiation-Related Heart Disease: Up-to-Date Developments

Tan¹,

Li²,

Dai³

2017

Radiotherapy

Self Cite

View full text Add to dashboard Cite

Approximately 25-30% of patients with cancer undergo thoracic radiation therapy (RT). RT might inadvertently induce heart injury and result in various forms of radiationrelated heart disease (RRHD). The main endpoints of RRHD include cardiac death from RT, clinical heart disease (congestive heart disease, ischemic heart disease, and myocardial infarction), and subclinical heart disease (cardiac perfusion defects). Advanced RT techniques, such as breath control, intensity-modulated RT, and image-guided RT, as well as limited target volume definition might spare or avoid cardiac doses and/or volume, which may translate into decreased incidence of RRHD. The total delivered radiation dose to cardiac implantable electronic devices was strongly recommended not to exceed 2 Gy. The treatment strategies of RRHD were based on the various recommended consensus of related heart diseases in cardiology. However, the standardized definitions of the cardiac structures, dose-volume limits during radiation planning design, the optimal dose-volume parameters, and the dose-volume effects of various cardiac substructures warrant further investigation. The recognition, prediction, prevention, and management of RRHD require close collaboration between oncologists and cardiologists.

show abstract

Analysis of cardiac motion without respiratory motion for cardiac stereotactic body radiation therapy

Ouyang

Schoenhagen

Wazni

et al. 2020

J Applied Clin Med Phys

View full text Add to dashboard Cite

Purpose/objective(s) To study the heart motion using cardiac gated computed tomographies (CGCT) to provide guidance on treatment planning margins during cardiac stereotactic body radiation therapy (SBRT). Materials/methods Ten patients were selected for this study, who received CGCT scans that were acquired with intravenous contrast under a voluntary breath‐hold using a dual source CT scanner. For each patient, CGCT images were reconstructed in multiple phases (10%–90%) of the cardiac cycle and the left ventricle (LV), right ventricle (RV), ascending aorta (AAo), ostia of the right coronary artery (O‐RCA), left coronary artery (O‐LCA), and left anterior descending artery (LAD) were contoured at each phase. For these contours, the centroid displacements from their corresponding average positions were measured at each phase in the superior–inferior (SI), medial–lateral (ML), and anterior–posterior (AP). The average volumes as well as the maximum to minimum ratios were analyzed for the LV and RV. Results For the six contoured substructures, more than 90% of the measured displacements were <5 mm. For these patients, the average volumes ranged from 191.25 to 429.51 cc for LV and from 91.76 to 286.88 cc for RV. For each patient, the ratios of maximum to minimum volumes within a cardiac cycle ranged from 1.15 to 1.54 for LV and from 1.34 to 1.84 for RV. Conclusion Based on this study, cardiac motion is variable depending on the specific substructure of the heart but is mostly within 5 mm. Depending on the location (central or peripheral) of the treatment target and treatment purposes, the treatment planning margins for targets and risk volumes should be adjusted accordingly. In the future, we will further assess heart motion and its dosimetric impact.

show abstract

Estimation of the displacement of cardiac substructures and the motion of the coronary arteries using electrocardiographic gating

Cited by 19 publications

References 20 publications

Cardiac substructure segmentation with deep learning for improved cardiac sparing

Cardiac substructure segmentation with deep learning for improved cardiac sparing

Radiation-Related Heart Disease: Up-to-Date Developments

Analysis of cardiac motion without respiratory motion for cardiac stereotactic body radiation therapy

Contact Info

Product

Resources

About