A State-of-the-Art Review on Segmentation Algorithms in Intravascular Ultrasound (IVUS) Images
read more
Citations
Robust Nucleus/Cell Detection and Segmentation in Digital Pathology and Microscopy Images: A Comprehensive Review
Large-scale retrieval for medical image analytics: A comprehensive review.
Standardized evaluation methodology and reference database for evaluating IVUS image segmentation
Automated localization and segmentation techniques for B-mode ultrasound images: A review.
PCA-based polling strategy in machine learning framework for coronary artery disease risk assessment in intravascular ultrasound
References
A theory for multiresolution signal decomposition: the wavelet representation
Snakes : Active Contour Models
Numerical Optimization
Discrete-Time Signal Processing
Related Papers (5)
American College of Cardiology Clinical Expert Consensus Document on Standards for Acquisition, Measurement and Reporting of Intravascular Ultrasound Studies (IVUS). A report of the American College of Cardiology Task Force on Clinical Expert Consensus Documents.
Frequently Asked Questions (11)
Q2. Why are the vessel borders not well distinguished in IVUS image?
Due to intrinsic non-vessel image features (presence of guide wire, calcified plaques, side branches, motion artifacts from the catheter and the heart) and image variability due to extrinsic parameters (system parameter specifications such as TGC and compression of the dynamic range), the vessel borders are not well distinguished in IVUS image which hinders the direct use of a classical deformable model.
Q3. What is the primary screening choice for coronary angiography?
IVUS is the primary screening choice for validation of novel endovascular coronary imaging modalities (i.e., OCT and NIR).
Q4. What is the way to perform a vascular ultrasound scan?
Acquisition of cross-sectional ultrasound images of the right coronary arteries (RCA), left anterior descending (LAD), and left circumflex (LCX) coronary arteries can be performed with a rotating single-element transducer or a phasedarray transducer.
Q5. What was the author's approach to the detection of the lumen borders?
The authors in [24] proposed a modified image cost function, combining gradient and variance of grayscale intensities, which was less sensitive to noise and employed circular dynamic programming for the detection of the MA borders.
Q6. What are the common validation datasets used in the literature?
most of the validation datasets used in the literature comprise frames from distinct parts of pullback series, which do not reflect the needs during catheterization procedures.
Q7. What was the output of the neural network used to estimate the lumen border?
The output of the neural network was used to reconstruct blood maps and then thresholded to estimate the lumen border with a parametric deformable model.
Q8. What is the definition of the vessel wall border?
The vessel wall border, also called the external elastic membrane (EEM) border, is a contour drawn at the interface between the media and the adventitia.
Q9. What is the effect of a guide wire on the ultrasound signal?
When a guide wire rail is designed along with a plastic sheath of the catheter, it obstructs the propagation of ultrasound signals, resulting in shadowing behind the guide wire, as illustrated in Fig. 5(a).
Q10. What is the main reason why the authors presented a multiscale BNR algorithm?
A multiscale BNR algorithm was also proposed in [73] as discussed in Section II-D.BPD has also been a subject of few studies where the presence of incoherent blood speckle patterns hindered the assessment of lumen size in IVUS images, especially for images acquired with recently developed ultrahigh-frequency transducers (40 MHz and above).
Q11. What is the procedure used by interventional cardiologists to trace the lumen contour on a?
Prior to tracing, they usually go back and forth among consecutive frames to be able to visually locate the lumen contour on a single frame.