Automatic quantification of calcifications in the coronary arteries and thoracic aorta on radiotherapy planning CT scans of Western and Asian breast cancer patients

Gernaat, Sofie A M; Velzen, Sanne G. M. van; Koh, Vivien; Emaus, Marleen J.; Išgum, Ivana; Leßmann, Nikolas; Moes, Shinta; Jacobson, Anouk; Tan, Poh Wee; Grobbee, Diederick E.; Bongard, H. J. G. D. van den; Tang, Johann I.; Verkooijen, Helena M.

doi:10.1016/j.radonc.2018.04.011

Cited by 33 publications

(27 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, the algorithm has been modified to be able to measure calcifications on RT planning CT scans of patients with breast cancer. This procedure has been described in detail elsewhere 17. The first results show that automatic calcification quantification is possible on RT planning CT scans of patients with breast cancer.…”

Section: Methods and Analysismentioning

confidence: 99%

“…The first results show that automatic calcification quantification is possible on RT planning CT scans of patients with breast cancer. Reproducibility of automatically versus manually measured calcium scores was high with linearly weighted kappa values ≥0.84 and intraclass correlation coefficients ≥0.94 17. For the current project, we will further develop the method to ensure its robustness with respect to image acquisition parameters and thereby enable its applicability in multicentre settings.…”

Section: Methods and Analysismentioning

confidence: 99%

See 1 more Smart Citation

Bragatston study protocol: a multicentre cohort study on automated quantification of cardiovascular calcifications on radiotherapy planning CT scans for cardiovascular risk prediction in patients with breast cancer

et al. 2019

Self Cite

View full text Add to dashboard Cite

IntroductionCardiovascular disease (CVD) is an important cause of death in breast cancer survivors. Some breast cancer treatments including anthracyclines, trastuzumab and radiotherapy can increase the risk of CVD, especially for patients with pre-existing CVD risk factors. Early identification of patients at increased CVD risk may allow switching to less cardiotoxic treatments, active surveillance or treatment of CVD risk factors. One of the strongest independent CVD risk factors is the presence and extent of coronary artery calcifications (CAC). In clinical practice, CAC are generally quantified on ECG-triggered cardiac CT scans. Patients with breast cancer treated with radiotherapy routinely undergo radiotherapy planning CT scans of the chest, and those scans could provide the opportunity to routinely assess CAC before a potentially cardiotoxic treatment. The Bragatston study aims to investigate the association between calcifications in the coronary arteries, aorta and heart valves (hereinafter called ‘cardiovascular calcifications’) measured automatically on planning CT scans of patients with breast cancer and CVD risk.Methods and analysisIn a first step, we will optimise and validate a deep learning algorithm for automated quantification of cardiovascular calcifications on planning CT scans of patients with breast cancer. Then, in a multicentre cohort study (University Medical Center Utrecht, Utrecht, Erasmus MC Cancer Institute, Rotterdam and Radboudumc, Nijmegen, The Netherlands), the association between cardiovascular calcifications measured on planning CT scans of patients with breast cancer (n≈16 000) and incident (non-)fatal CVD events will be evaluated. To assess the added predictive value of these calcifications over traditional CVD risk factors and treatment characteristics, a case-cohort analysis will be performed among all cohort members diagnosed with a CVD event during follow-up (n≈200) and a random sample of the baseline cohort (n≈600).Ethics and disseminationThe Institutional Review Boards of the participating hospitals decided that the Medical Research Involving Human Subjects Act does not apply. Findings will be published in peer-reviewed journals and presented at conferences.Trial registration numberNCT03206333.

show abstract

Section: Methods and Analysismentioning

confidence: 99%

Section: Methods and Analysismentioning

confidence: 99%

Bragatston study protocol: a multicentre cohort study on automated quantification of cardiovascular calcifications on radiotherapy planning CT scans for cardiovascular risk prediction in patients with breast cancer

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…We included six existing datasets with 7240 subjects who received a non-contrast CT exam visualizing the heart (Table 2.1). These were 902 consecutive ECG-triggered cardiac CTs for calcium scoring (CAC-CT) 28 used in clinical practice, 399 cardiac PET attenuation correction (AC PET ) CTs from the MYOMARKER study 40 acquired in rest condition during radionuclide myocardial perfusion imaging, 1409 consecutive radiotherapy treatment planning (RadTherapy) CTs of breast cancer patients from the UMBRELLA cohort, 33 screening CTs from the Jackson Heart Study (JHS) 41,42 and 1181 lung screening low-dose chest CTs from the National Lung Screening Trial (NLST). 43 The AC PET , JHS, RadTherapy and NLST examinations were acquired as part of Ethics Committee approved studies where informed consent was obtained from all subjects.…”

Section: Image Datasetsmentioning

confidence: 99%

“…The CAC-CT and diagnostic chest CT exams originate from the University Medical Center Utrecht and were retrospectively and anonymously collected, the need for informed consent was therefore waived by our institutional review board. 135 (37) Women (%) 402 (40) 130 (35) 82 (46) 75 (47) 528 (100) 226 (63) Age (years) 114 (67) 31 (62) 12 (60) 15 (75) 0 (0) 20 (54) Women (%) 55 (33) 19 (38) 8 (40) 5 (25) 39 (100) 17 (46) Age (years) 893 (36) Women (%)…”

Section: Image Datasetsmentioning

confidence: 99%

“…23 CAC scoring is performed using non-contrast enhanced ECG-synchronized cardiac CT, but, multiple reports indicate that application of coronary calcium scoring in CT scans made with non-dedicated protocols, allows CVD risk prediction. 24 Accordingly, in addition to automatic methods for calcium scoring in non-contrast enhanced ECG-synchronized cardiac CT, [25][26][27][28] methods were also developed for automatic scoring in low-dose chest CT for lung cancer screening, [29][30][31][32] radiotherapy treatment planning CT 12,33 and PET attenuation correction CT. 34 These CT exams all include the heart; however vary widely in resolution, field of view, reconstruction kernels, noise characteristics and the presence of ECG-synchronization (Figure 2.1). Moreover, calcifications in the thoracic aorta (TAC) are predictors of CVD 35 and hence, several methods for automatic quantification of TAC in CT have been developed, 32,36 as well.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

AI-based Analysis of Cardiovascular Disease Risk in CT of Breast Cancer Patients

Velzen¹

View full text Add to dashboard Cite

Rising incidence of breast cancer, early diagnosis due to screening and advances in treatment have led to an increasing number of breast cancer survivors. Accordingly, awareness regarding importance of quality of life after breast cancer is increasing. Cardiovascular disease (CVD) is common in cancer survivors 1,2 and in older women diagnosed with breast cancer it is the primary cause of death. 3 In relation to this, the risk of CVD events is increased by breast cancer treatments. For instance, patients that received treatment with anthracyclines have a five time higher risk of chroninc heart failure than breast cancer patients that were treated with chemotherapy without anthracyclines. 4 Patients that received radiotherapy are at increased risk of CVD events compared with patients that did not receive radiotherapy. 5,6 Moreover, patients with pre-existing CVD risk factors have the highest risk of cardiotoxicity due to breast cancer treatment. 7 Therefore, identification of patients at increased risk may provide options for cardio-prevention, such as lifestyle intervention, pharmaco-prevention or opting for less cardiotoxic treatment.A frequent underlying cause of CVD is atherosclerosis. 8 Atherosclerosis is the process of thickening of the innermost layer of the artery wall. This thickening consists of fat build-up in the artery wall and an accompanying inflammation reaction. In this process fatty plaques are formed that, in a later stadium, are tranformed into fibrotic tissue and calcium deposits, i.e. calcifications. Subclinical atherosclerosis can smolder for years, without symptoms. However, plaques can become unstable, rupture and induce thrombosis, which can cause life-threatening events, such as heart attack and stroke. 8,9 CVD risk is determined based on the presence of traditional risk factors. For instance, several large studies carried out in the general population showed that based on age, blood pressure, cholesterol levels, presence of diabetes and smoking history, a risk profile can be determined. 10,11 The risk profile is directly linked to the risk of experiencing a CVD event within the next 10 year. However, one in three breast cancer patients with subclinical atherosclerosis does not have any traditional risk factor and wouldn't be identified as high risk according to these criteria. 12 Therefore, identification of patients at increased risk of developing CVD events, may be done more accurately by detecting (subclinical) atherosclerosis. Imaging with computed tomography (CT) provides an opportunity for precise identification of patients at risk, because it visualizes calcified atherosclerotic plaque. Visualization and quantification of atherosclerosisCT images visualize calcifications in the arteries and can be used to identify patients at risk. Quantification of calcifications in the arteries is also known as calcium scoring. Of all aterial calcifications throughout the body, calcification in the coronary arteries (CAC) (a) Right-sided radiotherapy (b) Left-sided radiotherapy Figure 1.2: Examp...

show abstract

Identification of Risk of Cardiovascular Disease by Automatic Quantification of Coronary Artery Calcifications on Radiotherapy Planning CT Scans in Patients With Breast Cancer

et al. 2021

Self Cite

View full text Add to dashboard Cite

IMPORTANCE Cardiovascular disease (CVD) is common in patients treated for breast cancer, especially in patients treated with systemic treatment and radiotherapy and in those with preexisting CVD risk factors. Coronary artery calcium (CAC), a strong independent CVD risk factor, can be automatically quantified on radiotherapy planning computed tomography (CT) scans and may help identify patients at increased CVD risk.OBJECTIVE To evaluate the association of CAC with CVD and coronary artery disease (CAD) in patients with breast cancer. DESIGN, SETTING, AND PARTICIPANTSIn this multicenter cohort study of 15 915 patients with breast cancer receiving radiotherapy between 2005 and 2016 who were followed until December 31, 2018, age, calendar year, and treatment-adjusted Cox proportional hazard models were used to evaluate the association of CAC with CVD and CAD.EXPOSURES Overall CAC scores were automatically extracted from planning CT scans using a deep learning algorithm. Patients were classified into Agatston risk categories (0, 1-10, 11-100, 101-399, >400 units). MAIN OUTCOMES AND MEASURESOccurrence of fatal and nonfatal CVD and CAD were obtained from national registries. RESULTSOf the 15 915 participants included in this study, the mean (SD) age at CT scan was 59.0 (11.2; range, 22-95) years, and 15 879 (99.8%) were women. Seventy percent (n = 11 179) had no CAC. Coronary artery calcium scores of 1 to 10, 11 to 100, 101 to 400, and greater than 400 were present in 10.0% (n = 1584), 11.5% (n = 1825), 5.2% (n = 830), and 3.1% (n = 497) respectively. After a median follow-up of 51.2 months, CVD risks increased from 5.2% in patients with no CAC to 28.2% in patients with CAC scores higher than 400. After adjustment, CVD risk increased with higher CAC score (hazard ratio [HR] CAC = 1-10 = 1.1; 95% CI, 0.9-1.4; HR CAC = 11-100 = 1.8; 95% CI, 1.5-2.1; HR CAC = 101-400 = 2.1; 95% CI, 1.7-2.6; and HR CAC>400 = 3.4; 95% CI, 2.8-4.2). Coronary artery calcium was particularly strongly associated with CAD (HR CAC>400 = 7.8; 95% CI, 5.5-11.2). The association between CAC and CVD was strongest in patients treated with anthracyclines (HR CAC>400 = 5.8; 95% CI, 3.0-11.4) and patients who received a radiation boost (HR CAC>400 = 6.1; 95% CI, 3.8-9.7).CONCLUSIONS AND RELEVANCE This cohort study found that coronary artery calcium on breast cancer radiotherapy planning CT scan results was associated with CVD, especially CAD. Automated CAC scoring on radiotherapy planning CT scans may be used as a fast and low-cost tool to identify patients with breast cancer at increased risk of CVD, allowing implementing CVD risk-mitigating strategies with the aim to reduce the risk of CVD burden after breast cancer.

show abstract

Automatic quantification of calcifications in the coronary arteries and thoracic aorta on radiotherapy planning CT scans of Western and Asian breast cancer patients

Cited by 33 publications

References 44 publications

Bragatston study protocol: a multicentre cohort study on automated quantification of cardiovascular calcifications on radiotherapy planning CT scans for cardiovascular risk prediction in patients with breast cancer

Bragatston study protocol: a multicentre cohort study on automated quantification of cardiovascular calcifications on radiotherapy planning CT scans for cardiovascular risk prediction in patients with breast cancer

AI-based Analysis of Cardiovascular Disease Risk in CT of Breast Cancer Patients

Identification of Risk of Cardiovascular Disease by Automatic Quantification of Coronary Artery Calcifications on Radiotherapy Planning CT Scans in Patients With Breast Cancer

Contact Info

Product

Resources

About