Background
Deep learning (DL) have been reported feasible in breast MRI. However, the effectiveness of DL method in mpMRI combinations for breast cancer detection has not been well investigated.
...Purpose
To implement a DL method for breast cancer classification and detection using feature extraction and combination from multiple sequences.
Study Type
Retrospective.
Population
A total of 569 local cases as internal cohort (50.2 ± 11.2 years; 100% female), divided among training (218), validation (73) and testing (278); 125 cases from a public dataset as the external cohort (53.6 ± 11.5 years; 100% female).
Field Strength/Sequence
T1‐weighted imaging and dynamic contrast‐enhanced MRI (DCE‐MRI) with gradient echo sequences, T2‐weighted imaging (T2WI) with spin‐echo sequences, diffusion‐weighted imaging with single‐shot echo‐planar sequence and at 1.5‐T.
Assessment
A convolutional neural network and long short‐term memory cascaded network was implemented for lesion classification with histopathology as the ground truth for malignant and benign categories and contralateral breasts as healthy category in internal/external cohorts. BI‐RADS categories were assessed by three independent radiologists as comparison, and class activation map was employed for lesion localization in internal cohort. The classification and localization performances were assessed with DCE‐MRI and non‐DCE sequences, respectively.
Statistical Tests
Sensitivity, specificity, area under the curve (AUC), DeLong test, and Cohen's kappa for lesion classification. Sensitivity and mean squared error for localization. A P‐value <0.05 was considered statistically significant.
Results
With the optimized mpMRI combinations, the lesion classification achieved an AUC = 0.98/0.91, sensitivity = 0.96/0.83 in the internal/external cohorts, respectively. Without DCE‐MRI, the DL‐based method was superior to radiologists' readings (AUC 0.96 vs. 0.90). The lesion localization achieved sensitivities of 0.97/0.93 with DCE‐MRI/T2WI alone, respectively.
Data Conclusion
The DL method achieved high accuracy for lesion detection in the internal/external cohorts. The classification performance with a contrast agent‐free combination is comparable to DCE‐MRI alone and the radiologists' reading in AUC and sensitivity.
Evidence Level
3.
Technical Efficacy
Stage 2.
Full text
Available for:
BFBNIB, FZAB, GIS, IJS, KILJ, NLZOH, NUK, OILJ, SAZU, SBCE, SBMB, UL, UM, UPUK
Dilated cardiomyopathy (DCM) is an important cause of heart failure and the leading indication for heart transplantation. Many rare genetic variants have been associated with DCM, but common variant ...studies of the disease have yielded few associated loci. As structural changes in the heart are a defining feature of DCM, we report a genome-wide association study of cardiac magnetic resonance imaging (MRI)-derived left ventricular measurements in 36,041 UK Biobank participants, with replication in 2184 participants from the Multi-Ethnic Study of Atherosclerosis. We identify 45 previously unreported loci associated with cardiac structure and function, many near well-established genes for Mendelian cardiomyopathies. A polygenic score of MRI-derived left ventricular end systolic volume strongly associates with incident DCM in the general population. Even among carriers of TTN truncating mutations, this polygenic score influences the size and function of the human heart. These results further implicate common genetic polymorphisms in the pathogenesis of DCM.
The objective of this study was to investigate the relationship between baseline resting heart rate and incidence of heart failure (HF) and global and regional left ventricular (LV) dysfunction.
The ...association of resting heart rate to HF and LV function has not been well described in an asymptomatic multi-ethnic population.
Resting heart rate was measured in participants in the MESA (Multi-Ethnic Study of Atherosclerosis) trial at inclusion. Incident HF was registered (n = 176) during follow-up (median 7 years) in those who underwent cardiac magnetic resonance imaging (n = 5,000). Changes in ejection fraction (ΔEF) and peak circumferential strain (Δεcc) were measured as markers of developing global and regional LV dysfunction in 1,056 participants imaged at baseline and 5 years later. Time to HF (Cox model) and Δεcc and ΔEF (multiple linear regression models) were adjusted for demographics, traditional cardiovascular risk factors, calcium score, LV end-diastolic volume, and mass in addition to resting heart rate.
Cox analysis demonstrated that for 1 beat/min increase in resting heart rate, there was a 4% greater adjusted relative risk for incident HF (hazard ratio: 1.04; 95% CI: 1.02 to 1.06; p < 0.001). Adjusted multiple regression models demonstrated that resting heart rate was positively associated with deteriorating εcc and decrease in EF, even when all coronary heart disease events were excluded from the model.
Elevated resting heart rate was associated with increased risk for incident HF in asymptomatic participants in the MESA trial. Higher heart rate was related to development of regional and global LV dysfunction independent of subclinical atherosclerosis and coronary heart disease. (Multi-Ethnic Study of Atherosclerosis MESA; NCT00005487).
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Background
It is unclear whether thoracic aortic volume (TAV) is useful for cardiovascular (CV) disease prognosis and risk assessment.
Purpose
This study evaluated cross‐sectional associations of TAV ...with CV risk factors, and longitudinal association with incident CV events in the multiethnic study of atherosclerosis.
Study Type
Retrospective cohort analysis of prospective data.
Population
1182 participants (69 ± 9 years, 54% female, 37% Caucasian, 18% Chinese, 31% African American, 14% Hispanic, 60% hypertensive, and 20% diabetic) without prior CV disease.
Field Strength and sequences
Axial black‐blood turbo spin echo or bright blood steady‐state free precession images on 1.5T scanners.
Assessment
TAV was calculated using Simpson's method from axial images, and included the ascending arch and descending segments. Traditional CV risk factors were assessed at the time of MRI. CV outcomes over a 9‐year follow‐up period were recorded and represented a composite of stroke, stroke death, coronary heart disease (CHD), CHD death, atherosclerotic death, and CVD death.
Statistical Tests
Multivariable linear regression models adjusted for height and weight were used to determine the relationship (β coefficient) between TAV and CV risk factors. Cox regression models assessed the association of TAV and incident CV events. A P‐value of <0.05 was deemed statistically significant.
Results
Mean TAV was = 139 ± 41 mL. In multivariable regression, TAV was directly associated with age (β = 1.6), male gender (β = 23.9), systolic blood pressure (β = 0.1), and hypertension medication use (β = 7.9); and inversely associated with lipid medication use (β = −5.3) and treated diabetes (β = −8.9). Compared to Caucasians, Chinese Americans had higher TAV (β = 11.4), while African Americans had lower TAV (β = −7.0). Higher TAV was independently associated with incident CV events (HR: 1.057 per 10 mL).
Conclusion
Greater TAV is associated with incident CV events, increased age, and hypertension in a large multiethnic population while treated diabetes and lipid medication use were associated with lower TAV.
Level of Evidence
2
Technical Efficacy
Stage 2
Full text
Available for:
BFBNIB, FZAB, GIS, IJS, KILJ, NLZOH, NUK, OILJ, SAZU, SBCE, SBMB, UL, UM, UPUK
The association of longitudinal changes in left ventricular (LV) structure and function with myocardial fibrosis is unclear. We relate temporal changes in body size-indexed LV mass (LVMi) and ...end-diastolic volume indexed to body surface area, LV mass-to-volume ratio, and LV ejection fraction (LVEF) from cine cardiac magnetic resonance for 10 years, with replacement scar assessed from late gadolinium enhancement, and lower postcontrast T1 times reflecting greater diffuse myocardial fibrosis measured at the end of the follow-up period. All participants (n=1813) who underwent cardiac magnetic resonance twice as part of the Multi-Ethnic Study of Atherosclerosis 10 years apart were included. Multivariable logistic and linear regression models adjusted for cardiovascular risk factors measured the association of 10-year changes in LV structure and function, with fibrosis measured at follow-up. The presence of LV scar at year 10 was cross-sectionally associated with higher LVMi (≈10 g/m(2)), higher mass-to-volume ratio (0.1-0.2 g/mL), but lower LVEF (≈4%) and longitudinally with 3% decrease in LVEF and 0.7% greater end-diastolic volume indexed to body surface area in men for 10 years. Lower postcontrast T1 times at year 10 were associated cross-sectionally with lower LVMi (r=0.33), end-diastolic volume indexed to body surface area (r=0.25), and LVEF (in men only: r=0.14) and longitudinally with a decrease in LVMi (r=0.20) and reduction in LVEF (in men only: r=0.15). Sustained hypertension for 10 years was associated with increased LVMi and higher diffuse and replacement fibrosis at follow-up. During a 10-year period, increased concentric hypertrophy in women and LV dilatation in men were associated with replacement fibrosis, whereas decreasing LVMi was associated with diffuse fibrosis. Hypertension-induced remodeling was related to enhanced replacement and diffuse fibrosis, as well as hypertrophy.
Cardiovascular magnetic resonance (CMR) enables assessment and quantification of morphological and functional parameters of the heart, including chamber size and function, diameters of the aorta and ...pulmonary arteries, flow and myocardial relaxation times. Knowledge of reference ranges ("normal values") for quantitative CMR is crucial to interpretation of results and to distinguish normal from disease. Compared to the previous version of this review published in 2015, we present updated and expanded reference values for morphological and functional CMR parameters of the cardiovascular system based on the peer-reviewed literature and current CMR techniques. Further, databases and references for deep learning methods are included.
Full text
Available for:
DOBA, GEOZS, IJS, IMTLJ, IZUM, KILJ, KISLJ, NLZOH, NUK, OILJ, PILJ, PNG, SAZU, SBCE, SBJE, UILJ, UKNU, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Abnormal P-terminal force in lead V1 (PTFV1) is associated with an increased risk of heart failure, stroke, atrial fibrillation, and death.
Our goal was to explore associations of left ventricular ...(LV) diffuse fibrosis with left atrial (LA) function and electrocardiographic (ECG) measures of LA electrical activity.
Patients without atrial fibrillation (n = 91; mean age 59.5 years; 61.5% men; 65.9% white) with structural heart disease (spatial QRS-T angle ≥105° and/or Selvester QRS score ≥5 on ECG) but LV ejection fraction >35% underwent clinical evaluation, cardiac magnetic resonance, and resting ECG. LA function indices were obtained by multimodality tissue tracking using 2- and 4-chamber long-axis images. T1 mapping and late gadolinium enhancement were used to assess diffuse LV fibrosis and presence of scar. P-prime in V1 amplitude (PPaV1) and duration (PPdV1), averaged P-wave-duration, PR interval, and P-wave axis were automatically measured using 12 SLTM algorithm. PTFV1 was calculated as a product of PPaV1 and PPdV1.
In linear regression after adjustment for demographic characteristics, body mass index, maximum LA volume index, presence of scar, and LV mass index, each decile increase in LV interstitial fibrosis was associated with 0.76 mV*ms increase in negative abnormal PTFV1 (95% confidence interval CI -1.42 to -0.09; P = .025), 15.3 ms prolongation of PPdV1 (95% CI 6.9 to 23.8; P = .001) and 5.4 ms prolongation of averaged P-duration (95% CI 0.9-10.0; P = .020). LV fibrosis did not affect LA function. PPaV1 and PTFV1 were associated with an increase in LA volumes and decrease in LA emptying fraction and LA reservoir function.
LV interstitial fibrosis is associated with abnormal PTFV1, prolonged PPdV1, and P-duration, but does not affect LA function.
Background
Patients with cardiac sarcoidosis (CS) may present with arrhythmic events (AE): atrioventricular block (AVB) and/ or ventricular arrhythmias (VA). We sought to: (a) use regional analysis ...of cardiac magnetic resonance imaging (CMR) to describe anatomic and functional phenotypes of patients with CS and AE; (b) Assess the association of regional CMR abnormalities with the combined endpoint of death, heart transplantation (HT) and AE; and (c) use machine learning (ML) to predict the combined endpoint based on CMR features.
Methods
we included 76 patients with CS and CMR. We analyzed cine images to determine regional longitudinal (LS) and radial strain (RS); and late gadolinium enhancement imaging to determine regional scar burden (%scar).
Results
Patients with AVB (n = 7), compared with those without, had higher %scar in the anterior (21.8 ± 27.4 vs 5.1 ± 8.9; P = 0.0005) and anteroseptal (19.3 ± 24.5 vs 3.5 ± 5.5; P < .0001) walls. Patients with VA (n = 12), compared with those without, had higher %scar in the basal inferoseptum (20.4 ± 30.8 vs 8.3 ± 13.4; P = .03). During mean follow‐up of 4.4 ± 3.3 years, four patients died or underwent HT; eight had VA; and zero developed AVB. Multiple regional abnormalities were associated with the combined endpoint, including scar in the anteroseptal wall (HR 1.06 1.02‐1.09 per 1%scar increase, P = .002). The ML algorithm predicted the combined endpoint with a C‐statistic of 0.91.
Conclusion
Regional CMR abnormalities are associated with AE in patients with CS.
Full text
Available for:
BFBNIB, DOBA, FZAB, GIS, IJS, IZUM, KILJ, NLZOH, NUK, OILJ, PILJ, PNG, SAZU, SBCE, SBMB, SIK, UILJ, UKNU, UL, UM, UPUK, VSZLJ
Understanding the relationship of cardiovascular structure and function to age is confounded by the high prevalence of traditional risk factors in the United States. The purpose of the study is to ...compare left ventricular (LV) and aortic structural, and functional parameters in individuals with and without traditional risk factors in a population-based cohort.
3015 study participants (48% men, age 55-94, mean 69.01±9.17 years) in the Multi-Ethnic Study of Atherosclerosis (MESA) underwent cardiovascular magnetic resonance (CMR) imaging from 2010-2012. Absence of cardiovascular (CV) risk factors (no hypertension, diabetes or impaired fasting glucose, obesity, smoking or hypercholesterolemia) was infrequent, occurring in just 314 (10.4%, 38% men) of 3015 participants. In multivariable analyses adjusting for age, sex and race, individuals with CV risk factors had significantly larger LV mass index (by 17%) and lower LV contractibility (circumference strain, lower by 14%). Indexed LV volumes and stroke volume were inversely associated with age, but such relationships were not statistically significant in risk-free male subjects (p>0.05). Men with CV risk factors showed positive association of CMR T1 indices of myocardial fibrosis with age. Aortic function was similar in individuals with and without risk factors; age was associated with decline of aortic function in both CV and no CV risk factor groups.
Our results support that LV structure and function are better preserved in senescent hearts in the absence of traditional cardiovascular risk factors, and such protection is more prominent in men than in women.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
PDF
