In this dissertation non-parametric Bayesian methods are used in the application of robotic vision. Robots make use of depth sensors that represent their environment using point clouds. Non... Show moreIn this dissertation non-parametric Bayesian methods are used in the application of robotic vision. Robots make use of depth sensors that represent their environment using point clouds. Non-parametric Bayesian methods can (1) determine how good an object is recognized, and (2) determine how many objects a particular scene contains. When there is a model available for the object to be recognized and the nature of perceptual error is known, a Bayesian method will act optimally.In this dissertation Bayesian models are developed to represent geometric objects such as lines and line segments (consisting out of points). The infinite line model and the infinite line segment model use a non-parametric Bayesian model, to be precise, a Dirichlet process, to represent the number of objects. The line or the line segment is represented by a probability distribution. The lines can be represented by conjugate distributions and then Gibbs sampling can be used. The line segments are not represented by conjugate distributions and therefore a split-merge sampler is used.A split-merge sampler fits line segments by assigning points to a hypothetical line segment. Then it proposes splits of a single line segment or merges of two line segments. A new sampler, the triadic split-merge sampler, introduces steps that involve three line segments. In this dissertation, the new sampler is compared to a conventional split-merge sampler. The triadic sampler can be applied to other problems as well, i.e., not only problems in robotic perception.The models for objects can also be learned. In the dissertation this is done for more complex objects, such as cubes, built up out of hundreds of points. An auto-encoder then learns to generate a representative object given the data. The auto-encoder uses a newly defined reconstruction distance, called the partitioning earth mover’s distance. The object that is learned by the auto-encoder is used in a triadic sampler to (1) identify the point cloud objects and to (2) establish multiple occurrences of those objects in the point cloud. Show less
Demirkiran, A.; Amier, R.P.; Hofman, M.B.M.; Geest, R.J. van der; Robbers, L.F.H.J.; Hopman, L.H.G.A.; ... ; Nijveldt, R. 2021
The pathophysiology behind thrombus formation in paroxysmal atrial fibrillation (AF) patients is very complex. This can be due to left atrial (LA) flow changes, remodeling, or both. We investigated... Show moreThe pathophysiology behind thrombus formation in paroxysmal atrial fibrillation (AF) patients is very complex. This can be due to left atrial (LA) flow changes, remodeling, or both. We investigated differences for cardiovascular magnetic resonance (CMR)-derived LA 4D flow and remodeling characteristics between paroxysmal AF patients and patients without cardiac disease. In this proof-of-concept study, the 4D flow data were acquired in 10 patients with paroxysmal AF (age=61 +/- 8 years) and 5 age/gender matched controls (age=56 +/- 1 years) during sinus rhythm. The following LA and LA appendage flow parameters were obtained: flow velocity (mean, peak), stasis defined as the relative volume with velocities<10 cm/s, and kinetic energy (KE). Furthermore, LA global strain values were derived from b-SSFP cine images using dedicated CMR feature-tracking software. Even in sinus rhythm, LA mean and peak flow velocities over the entire cardiac cycle were significantly lower in paroxysmal AF patients compared to controls [(13.12.4 cm/s vs. 16.7 +/- 2.1 cm/s, p=0.01) and (19.3 +/- 4.7 cm/s vs. 26.8 +/- 5.5 cm/s, p=0.02), respectively]. Moreover, paroxysmal AF patients expressed more stasis of blood than controls both in the LA (43.2 +/- 10.8% vs. 27.8 +/- 7.9%, p=0.01) and in the LA appendage (73.3 +/- 5.7% vs. 52.8 +/- 16.2%, p=0.04). With respect to energetics, paroxysmal AF patients demonstrated lower mean and peak KE values (indexed to maximum LA volume) than controls. No significant differences were observed for LA volume, function, and strain parameters between the groups. Global LA flow dynamics in paroxysmal AF patients appear to be impaired including mean/peak flow velocity, stasis fraction, and KE, partly independent of LA remodeling. This pathophysiological flow pattern may be of clinical value to explain the increased incidence of thromboembolic events in paroxysmal AF patients, in the absence of actual AF or LA remodeling. Show less
Amier, R.P.; Marcks, N.; Hooghiemstra, A.M.; Nijveldt, R.; Buchem, M.A. van; Roos, A. de; ... ; Heart-Brain Connection Consortium 2021
OBJECTIVES This study sought to investigate the extent of hypertensive exposure as assessed by cardiovascular magnetic resonance imaging (MRI) in relation to cerebral small vessel disease (CSVD)... Show moreOBJECTIVES This study sought to investigate the extent of hypertensive exposure as assessed by cardiovascular magnetic resonance imaging (MRI) in relation to cerebral small vessel disease (CSVD) and cognitive impairment, with the aim of understanding the role of hypertension in the early stages of deteriorating brain health.BACKGROUND Preserving brain health into advanced age is one of the great challenges of modern medicine. Hypertension is thought to induce vascular brain injury through exposure of the cerebral microcirculation to increased pressure/pulsatility. Cardiovascular MRI provides markers of (subclinical) hypertensive exposure, such as aortic stiffness by puke wave velocity (PWV), left ventricular (LV) mass index (LVMi), and concentricity by mass-to-volume ratio.METHODS A total of 559 participants from the Heart-Brain Connection Study (431 patients with manifest cardiovascular disease and 128 control participants), age 67.8 +/- 8.8 years, underwent 3.0-T heart-brain MRI and extensive neuropsychological testing. Aortic PWV, LVMi, and LV mass-to-volume ratio were evaluated in relation to presence of CSVD and cognitive impairment. Effect modification by patient group was investigated by interaction terms; results are reported pooled or stratified accordingly.RESULTS Aortic PWV (odds ratio [OR]: 1.17; 95% confidence interval [CI]: 1.05 to 1.30 in patient groups only), LVMi (in carotid occlusive disease, OR: 5.69; 95% CI: 1.63 to 19.87; in other groups, OR: 1.30; 95% CI: 1.05 to 1.62]) and LV mass-to-volume ratio (OR: 1.81; 95% CI: 1.46 to 2.24) were associated with CSVD. Aortic PWV (OR: 1.07; 95% CI: 1.02 to 1.13) and LV mass-to-volume ratio (OR: 1.27; 95% CI: 1.07 to 1.51) were also associated with cognitive impairment. Relations were independent of sociodemographic and cardiac index and mostly persisted after correction for systolic blood pressure or medical history of hypertension. Causal mediation analysis showed significant mediation by presence of CSVD in the relation between hypertensive exposure markers and cognitive impairment.CONCLUSIONS The extent of hypertensive exposure is associated with CSVD and cognitive impairment beyond clinical brood pressure or medical history. The mediating role of CSVD suggests that hypertension may lead to cognitive impairment through the occurrence of CSVD. (C) 2021 Published by Elsevier on behalf of the American College of Cardiology Foundation. Show less