Percutaneous coronary intervention is a minimally-invasive procedure to treat coronary artery disease. In such procedures, X-ray angiography, a real-time imaging technique, is commonly used for image guidance to identify lesion sites and navigate catheters and guide-wires within coronary arteries. Due to the physical nature of X-ray imaging, photon energy undergoes absorption when penetrating tissues, rendering a 2D projection image of a 3D scene, in which semi-transparent structures overlap with each other. The overlapping structures make robust information processing of X-ray images challenging. To tackle this issue, layer separation techniques for X-ray images were proposed to separate those structures into different image layers based on structure appearance or motion pattern. These techniques have been proven effective for vessel enhancement in X-ray angiograms. However, layer separation approaches still suffer either from spurious structures or non-real-time processing, which prevent their application in clinics. Purpose of this work is to investigate whether vessel layer separation from X-ray angiography images is possible via a data-driven strategy. To this end, we develop and evaluate a deep learning based method to extract the vessel layer. More specifically, U-Net, a fully convolutional network architecture, was trained to separate the vessel layer from the background. The results of our experiments show good vessel layer separation on 42 clinical sequences. Compared to the previous state-of-the-art, our proposed method has similar performance but runs much faster, which makes it a potential real-time clinical application.
Needle visibility is of crucial importance for ultrasound guided interventional procedures. However, several factors, such as shadowing by bone or gas and tissue echogenic properties similar to needles, may compromise needle visibility. Additionally, small angle between the ultrasound beam and the needle, as well as small gauged needles may reduce visibility. Variety in needle tips design may also affect needle visibility. Whereas several studies have investigated needle visibility in 2D ultrasound imaging, no data is available for 3D ultrasound imaging, a modality that has great potential for image guidance interventions1. In this study, we evaluated needle visibility using a 3D ultrasound transducer. We examined different needles in a tissue mimicking liver phantom at three angles (200, 550 and 900) and quantify their visibility. The liver phantom was made by 5% polyvinyl alcohol solution containing 1% Silica gel particles to act as ultrasound scattering particles. We used four needles; two biopsy needles (Quick core 14G and 18G), one Ablation needle (Radiofrequency Ablation 17G), and Initial puncture needle (IP needle 17G). The needle visibility was quantified by calculating contrast to noise ratio. The results showed that the visibility for all needles were almost similar at large angles. However the difference in visibility at lower angles is more prominent. Furthermore, the visibility increases with the increase in angle of ultrasound beam with needles.
Percutaneous radio frequency ablation is a method for liver tumor treatment when conventional surgery is not an option. It is a minimally invasive treatment and may be performed under CT image guidance if the tumor does not give sufficient contrast on ultrasound images. For optimal guidance, registration of the pre-operative contrast-enhanced CT image to the intra-operative CT image is hypothesized to improve guidance. This is a highly challenging registration task due to large differences in pose and image quality. In this study, we introduce a semi-automated registration algorithm to address this problem. The method is based on a conventional nonrigid intensity-based registration framework, extended with a novel point-to-surface constraint. The point-to-surface constraint serves to improve the alignment of the liver boundary, while requiring minimal user interaction during the operation. The method assumes that a liver segmentation of the pre-operative CT is available. After an initial nonrigid registration without the point-to-surface constraint, the operator clicks a few points on the liver surface at those regions where the nonrigid registration seems inaccurate. In a subsequent registration step, these points on the intra-operative image are driven towards the liver surface on the preoperative image, using a penalty term added to the registration cost function. The method is evaluated on five clinical datasets and it is shown to improve registration compared with conventional rigid and nonrigid registrations in all cases.
This paper presents a level set based method for segmenting the outer vessel wall and plaque components of the carotid
artery in CTA. The method employs a GentleBoost classification framework that classifies pixels as calcified region or
not, and inside or outside the vessel wall. The combined result of both classifications is used to construct a speed
function for level set based segmentation of the outer vessel wall; the segmented lumen is used to initialize the level set.
The method has been optimized on 20 datasets and evaluated on 80 datasets for which manually annotated data was
available as reference. The average Dice similarity of the outer vessel wall segmentation was 92%, which compares
favorably to previous methods.
We propose a minimum cost path approach to track the centerlines of the internal and external carotid arteries in
multispectral MR data. User interaction is limited to the annotation of three seed points. The cost image is based
on both a measure of vessel medialness and lumen intensity similarity in two MRA image sequences: Black Blood
MRA and Phase Contrast MRA. After intensity inhomogeneity correction and noise reduction, the two images are
aligned using affine registration. The two parameters that control the contrast of the cost image were determined
in an optimization experiment on 40 training datasets. Experiments on the training datasets also showed that a cost
image composed of a combination of gradient-based medialness and lumen intensity similarity increases the tracking
accuracy compared to using only one of the constituents. Furthermore, centerline tracking using both MRA sequences
outperformed tracking using only one of these MRA images. An independent test set of 152 images from 38 patients
served to validate the technique. The centerlines of 148 images were successfully extracted using the parameters
optimized on the training sets. The average mean distance to the reference standard, manually annotated centerlines,
was 0.98 mm, which is comparable to the in-plane resolution. This indicates that the proposed method has a high
potential to replace the manual centerline annotation.
Cardiac magnetic resonance perfusion imaging (CMR) and computed tomography angiography (CTA) are widely used to
assess heart disease. CMR is used to measure the global and regional myocardial function and to evaluate the presence of
ischemia; CTA is used for diagnosing coronary artery disease, such as coronary stenoses. Nowadays, the hemodynamic
significance of coronary artery stenoses is determined subjectively by combining information on myocardial function with
assumptions on coronary artery territories. As the anatomy of coronary arteries varies greatly between individuals, we
developed a patient-specific tool for relating CTA and perfusion CMR data. The anatomical and functional information
extracted from CTA and CMR data are combined into a single frame of reference. Our graphical user interface provides
various options for visualization. In addition to the standard perfusion Bull's Eye Plot (BEP), it is possible to overlay a 2D
projection of the coronary tree on the BEP, to add a 3D coronary tree model and to add a 3D heart model. The perfusion
BEP, the 3D-models and the CTA data are also interactively linked. Using the CMR and CTA data of 14 patients, our
tool directly established a spatial correspondence between diseased coronary artery segments and myocardial regions with
abnormal perfusion. The location of coronary stenoses and perfusion abnormalities were visualized jointly in 3D, thereby
facilitating the study of the relationship between the anatomic causes of a blocked artery and the physiological effects on
the myocardial perfusion. This tool is expected to improve diagnosis and therapy planning of early-stage coronary artery
Computed tomography angiography (CTA), a non-invasive imaging technique, is becoming increasingly popular for cardiac
examination, mainly due to its superior spatial resolution compared to MRI. This imaging modality is currently widely
used for the diagnosis of coronary artery disease (CAD) but it is not commonly used for the diagnosis of ventricular and
atrial function. In this paper, we present a fully automatic method for segmenting the whole heart (i.e. the outer surface of
the myocardium) and cardiac chambers from CTA datasets. Cardiac chamber segmentation is particularly valuable for the
extraction of ventricular and atrial functional information, such as stroke volume and ejection fraction. With our approach,
we aim to improve the diagnosis of CAD by providing functional information extracted from the same CTA data, thus not
requiring additional scanning. In addition, the whole heart segmentation method we propose can be used for visualization
of the coronary arteries and for obtaining a region of interest for subsequent segmentation of the coronaries, ventricles and
atria. Our approach is based on multi-atlas segmentation, and performed within a non-rigid registration framework. A
leave-one-out quantitative validation was carried out on 8 images. The method showed a high accuracy, which is reflected
in both a mean segmentation error of 1.05±1.30 mm and an average Dice coefficient of 0.93. The robustness of the method
is demonstrated by successfully applying the method to 243 additional datasets, without any significant failure.
In this paper we address the problem of 3D shape reconstruction from sparse X-ray projections. We present a correspondence
free method to fit a statistical shape model to two X-ray projections, and illustrate its performance in 3D shape
reconstruction of the femur. The method alternates between 2D segmentation and 3D shaoe reconstruction, where 2D
segmentation is guided by dynamic programming along the model projection on the X-ray plane. 3D reconstruction is
based on the iterative minimization of the 3D distance between a set of support points and the back-projected silhouette
with respect to the pose and model parameters. We show robustness of the reconstruction on simulated X-ray projection data of the femur, varying the field of view; and in a pilot study on cadaveric femora.
A novel 2D slice based automatic method for model based segmentation of the outer vessel wall of the common carotid artery in CTA data set is introduced. The method utilizes a lumen segmentation and AdaBoost, a fast and robust machine learning algorithm, to initially classify (mark) regions outside and inside the vessel wall using the distance from the lumen and intensity profiles sampled radially from the gravity center of the lumen. A similar method using the distance from the lumen and the image intensity as features is used to classify calcium regions. Subsequently, an ellipse shaped deformable model is fitted to the classification result. The method has achieved smaller detection error than the inter observer variability, and the method is robust against variation of the training data sets.
A method is presented to track the guide wire during endovascular interventions and to visualize it in 3D, together with the vasculature of the patient. The guide wire is represented by a 3D spline whose position is optimized using internal and external forces. For the external forces, the 3D spline is projected onto the biplane projection images that are routinely acquired. Feature images are constructed based on the enhancement of line-like structures in the projection images. A threshold is applied to this image such that if the probability of a pixel to be part of the guide wire is sufficiently high this feature image is used, whereas outside this region a distance transform is computed to improve the capture range of the method. In preliminary experiments, it is shown that some of the problems of the 2D tracking which where presented in previous work can successfully be circumvented using the 3D tracking method.
A new method has been developed that, based on tracking a guide wire
in monoplane fluoroscopic images, visualizes the approximate guide
wire position in the 3D vasculature, that is obtained prior to the
intervention with 3D rotational X-ray angiography (3DRA). The
method consists of four stages: (i) tracking of the guide wire in 2D
fluoroscopic imaging, (ii) projecting the guide wire from the 2D
fluoroscopic image back into the 3DRA image to determine possible
locations of the guide wire in 3D, (iii) determining the approximate
guide wire location in the 3DRA image based on image features, and
(iv) visualization of the vessel and guide wire location found. The
method has been evaluated using a 3DRA image of a vascular phantom
filled with contrast, and monoplane fluoroscopic images of the same
phantom without contrast and with a guide wire inserted. Evaluation
has been performed for different projection angles. Also, several
feature images for finding the optimal guide wire position have been
compared. Average localization errors for the guide wire and the
guide wire tip are in the range of a few millimetres, which shows
that 3D visualization of the guide wire with respect to
the vasculature as a navigation tool in endovascular procedures is
3D Rotational X-ray (3DRX) imaging can be used to intraoperatively
acquire 3D volumes depicting bone structures in the patient. Registration of 3DRX to MR images, containing soft tissue
information, facilitates image guided surgery on both soft tissue and
bone tissue information simultaneously. In this paper, automated noninvasive registration using maximization of mutual information is compared to conventional interactive and invasive point-based registration using the least squares fit of corresponding point sets. Both methods were evaluated on 3DRX images (with a resolution of 0.62x0.62x0.62 mm3) and MRI images (with resolutions of 2x2x2 mm3, 1.5x1.5x1.5 mm3 and 1x1x1 mm3) of seven defrosted spinal segments implanted with six or seven markers. The markers were used for the evaluation of the registration transformations found by both point- and maximization of mutual information based registration. The root-mean-squared-error on markers that were left out during registration was calculated after transforming the marker set with the computed registration transformation. The results show that the noninvasive registration method performs significantly better (p≤0.01) for all MRI resolutions than point-based registration using four or five markers, which is the number of markers conventionally used in image guided surgery systems.