A problem of current MRA techniques is the inability to accurately depict the vascular anatomy, particularly in areas of disturbed flow. Various reasons, such as intravoxel phase dispersion, ...saturation, temporal variations, and maximum intensity projection (MIP) nonlinearity, cause a wrong delineation of vessel boundaries. A phase contrast (PC)‐based postprocessing operation, the phase derivative (PhD), is introduced to detect phase fluctuations indicating flow. Two‐dimensional and three‐dimensional angiographic reconstruction algorithms are presented. Mathematical formulas are derived to predict the effect of sampling to flow profiles and the effect on the PhD of these profiles. Numerical, phantom, and preliminary in vivo experiments demonstrate that PhD images do not suffer from phase wraps and allow a velocity dynamic range extension only limited by a differential phase change. It is also shown that PhD MIPs produce higher signal‐to‐noise ratios than conventional PC angiograms and give a better impression of the anatomy of (stenotic) vessels and of their diameters for both laminar and disturbed flow.
The geometry of a space curve is described in terms of a Euclidean invariant frame field, metric, connection, torsion and curvature. Here the torsion and curvature of the connection quantify the ...curve geometry. In order to retain a stable and reproducible description of that geometry, such that it is slightly affected by non-uniform protrusions of the curve, a linearised Euclidean shortening flow is proposed. (Semi)-discretised versions of the flow subsequently physically realise a concise and exact (semi-)discrete curve geometry. Imposing special ordering relations the torsion and curvature in the curve geometry can be retrieved on a multi-scale basis not only for simply closed planar curves but also for open, branching, intersecting and space curves of non-trivial knot type. In the context of the shortening flows we revisit the maximum principle, the semi-group property and the comparison principle normally required in scale-space theories. We show that our linearised flow satisfies an adapted maximum principle, and that its Green's functions possess a semi-group property. We argue that the comparison principle in the case of knots can obstruct topological changes being in contradiction with the required curve simplification principle. Our linearised flow paradigm is not hampered by this drawback; all non-symmetric knots tend to trivial ones being infinitely small circles in a plane. Finally, the differential and integral geometry of the multi-scale representation of the curve geometry under the flow is quantified by endowing the scale-space of curves with an appropriate connection, and calculating related torsion and curvature aspects. This multi-scale modern geometric analysis forms therewith an alternative for curve description methods based on entropy scale-space theories.PUBLICATION ABSTRACT
Primary tumors have a high likelihood of developing metastases in the liver and early detection of these metastases is crucial for patient outcome. We propose a method based on convolutional neural ...networks (CNN) to detect liver metastases. First, the liver was automatically segmented using the six phases of abdominal dynamic contrast enhanced (DCE) MR images. Next, DCE-MR and diffusion weighted (DW) MR images are used for metastases detection within the liver mask. The liver segmentations have a median Dice similarity coefficient of 0.95 compared with manual annotations. The metastases detection method has a sensitivity of 99.8% with a median of 2 false positives per image. The combination of the two MR sequences in a dual pathway network is proven valuable for the detection of liver metastases. In conclusion, a high quality liver segmentation can be obtained in which we can successfully detect liver metastases.
In patients with coronary artery stenoses of intermediate severity, the functional significance needs to be determined. Fractional flow reserve (FFR) measurement, performed during invasive coronary ...angiography (ICA), is most often used in clinical practice. To reduce the number of ICA procedures, we present a method for automatic identification of patients with functionally significant coronary artery stenoses, employing deep learning analysis of the left ventricle (LV) myocardium in rest coronary CT angiography (CCTA). The study includes consecutively acquired CCTA scans of 166 patients with FFR measurements. To identify patients with a functionally significant coronary artery stenosis, analysis is performed in several stages. First, the LV myocardium is segmented using a multiscale convolutional neural network (CNN). To characterize the segmented LV myocardium, it is subsequently encoded using unsupervised convolutional autoencoder (CAE). Thereafter, patients are classified according to the presence of functionally significant stenosis using an SVM classifier based on the extracted and clustered encodings. Quantitative evaluation of LV myocardium segmentation in 20 images resulted in an average Dice coefficient of 0.91 and an average mean absolute distance between the segmented and reference LV boundaries of 0.7 mm. Classification of patients was evaluated in the remaining 126 CCTA scans in 50 10-fold cross-validation experiments and resulted in an area under the receiver operating characteristic curve of 0.74 +- 0.02. At sensitivity levels 0.60, 0.70 and 0.80, the corresponding specificity was 0.77, 0.71 and 0.59, respectively. The results demonstrate that automatic analysis of the LV myocardium in a single CCTA scan acquired at rest, without assessment of the anatomy of the coronary arteries, can be used to identify patients with functionally significant coronary artery stenosis.
Cardiovascular disease (CVD) is a leading cause of death in the lung cancer screening population. Chest CT scans made in lung cancer screening are suitable for identification of participants at risk ...of CVD. Existing methods analyzing CT images from lung cancer screening for prediction of CVD events or mortality use engineered features extracted from the images combined with patient information. In this work we propose a method that automatically predicts 5-year cardiovascular mortality directly from chest CT scans without the need for hand-crafting image features. A set of 1,583 participants of the National Lung Screening Trial was included (1,188 survivors, 395 non-survivors). Low-dose chest CT images acquired at baseline were analyzed and the follow-up time was 5 years. To limit the analysis to the heart region, the heart was first localized by our previously developed algorithm for organ localization exploiting convolutional neural networks. Thereafter, a convolutional autoencoder was used to encode the identified heart region. Finally, based on the extracted encodings subjects were classified into survivors or non-survivors using a support vector machine classifier. The performance of the method was assessed in eight cross-validation experiments with 1,433 images used for training, 50 for validation and 100 for testing. The method achieved a performance with an area under the ROC curve of 0.72. The results demonstrate that prediction of cardiovascular mortality directly from low-dose screening chest CT scans, without hand-crafted features, is feasible, allowing identification of subjects at risk of fatal CVD events.
Objectives: Radio-guided interventional procedures are currently performed with probes or small gamma cameras. The availability of live hybrid nuclear/fluoroscopic images during interventions may ...extend the application of interventional nuclear imaging, for instance to guide radioembolization procedures. Therefore, we aim at developing a real-time, simultaneous fluoroscopic and nuclear imaging device, consisting of a c-arm with nuclear imaging capabilities. In a previous design, we located four gamma cameras with pinhole collimators at the side of the x-ray tube 1, 2. We now propose a dual layer detector, capable of acquiring real-time nuclear images that are intrinsically registered to the fluoroscopic images. This principle relies on the fact that the x-ray flat panel detector absorbs the majority of x-rays but is largely transparent to the higher energy gammas. The purpose of this study is to investigate the technical feasibility of such a dual layer detector using simulations and experiments. Methods: Simultaneous acquisition of fluoroscopic and nuclear images of the same field of view can be achieved by placing a gamma camera with a cone beam collimator focussed at the x-ray focal spot behind a dynamic x-ray flat panel detector of a mobile c-arm (figure 1). An envisioned setup would consist of a traditional gamma camera with a low-energy high-resolution (LEHR) cone beam collimator focussed at 1 m and a standard dynamic flat panel (700 μm cesium iodide) as used in radiological interventions to guarantee unhampered x-ray image quality. The sensitivity and resolution of the nuclear image of this setup were Monte Carlo simulated for a technetium-99m (99mTc, 140 keV) point source positioned at various source detector distances (range: 2-30 cm) and compared to standard nuclear images without a flat panel in place. The presence of an anti-scatter grid was also simulated. In addition to simulations, a physical prototype was built consisting of a gamma camera (Diacam, Siemens Healthcare) with a cone beam collimator focused at 56 cm (septal thickness: 0.377 mm, hole diameter: 1.94 mm, septal length: 40 mm) in combination with a wireless digital flat panel and mobile x-ray tube (DRX revolution, Carestream Health). With this prototype, sensitivity and resolution of the nuclear image were determined with a 99mTc point source of 720 kBq positioned at various source detector distances (range: 1-30 cm). In addition, hybrid images of a rotating phantom with two spheres of 17 and 37 mm diameter filled with 99mTc (4 MBq/ml) were acquired in a step-and-shoot mode, where the fluoroscopic image was taken after each 0.5 s acquisition of the nuclear image. Results: As compared to a standard gamma camera without a flat panel in place, our envisioned setup showed an attenuation of 38% of the gamma rays. Addition of an anti-scatter grid accounted for an extra reduction in sensitivity of 37%. Resolution of the nuclear images was unhampered by the setup. Experiments with the prototype were in line with the simulations and resulted in a sensitivity of 4.44asterisk10-5 to 25.0asterisk10-5 counts per decay, resolution varied between 7.4 and 43 mm. Measurements of the physical phantom showed good spatial overlap of fluoroscopic and nuclear images (figure 1). Conclusion: A dual layer detector capable of acquiring real-time fluoroscopic and nuclear images of the same field-of-view was proposed. Simulations of the ideal setup and measurements with a prototype have shown the technical feasibility of such a dual layer detector.