B-spline methods for interactive segmentation and modeling of lumen and vessel surfaces in three-dimensional intravascular ultrasound

Using Deep Learning and B-Splines to Model Blood Vessel Lumen from 3D Images

Accurate geometric modeling of blood vessel lumen from 3D images is crucial for vessel quantification as part of the diagnosis, treatment, and monitoring of vascular diseases. Our method, unlike other approaches which assume a circular or elliptical vessel cross-section, employs parametric B-splines combined with image formation system equations to accurately localize the highly curved lumen boundaries. This approach avoids the need for image segmentation, which may reduce the localization accuracy due to spatial discretization. We demonstrate that the model parameters can be reliably identified by a feedforward neural network which, driven by the cross-section images, predicts the parameter values many times faster than a reference least-squares (LS) model fitting algorithm. We present and discuss two example applications, modeling the lower extremities of artery-vein complexes visualized in steady-state contrast-enhanced magnetic resonance images (MRI) and the coronary arteries pictured in computed tomography angiograms (CTA). Beyond applications in medical diagnosis, blood-flow simulation and vessel-phantom design, the method can serve as a tool for automated annotation of image datasets to train machine-learning algorithms.

Automatic detection of basal cell carcinoma using telangiectasia analysis in dermoscopy skin lesion images

BACKGROUND

Telangiectasia, dilated blood vessels near the surface of the skin of small, varying diameter, are critical dermoscopy structures used in the detection of basal cell carcinoma (BCC). Distinguishing these vessels from other telangiectasia, that are commonly found in sun-damaged skin, is challenging.

METHODS

Image analysis techniques are investigated to find vessels structures in BCC automatically. The primary screen for vessels uses an optimized local color drop technique. A noise filter is developed to eliminate false-positive structures, primarily bubbles, hair, and blotch and ulcer edges. From the telangiectasia mask containing candidate vessel-like structures, shape, size and normalized count features are computed to facilitate the discrimination of benign skin lesions from BCCs with telangiectasia.

RESULTS

Experimental results yielded a diagnostic accuracy as high as 96.7% using a neural network classifier for a data set of 59 BCCs and 152 benign lesions for skin lesion discrimination based on features computed from the telangiectasia masks.

CONCLUSION

In current clinical practice, it is possible to find smaller BCCs by dermoscopy than by clinical inspection. Although almost all of these small BCCs have telangiectasia, they can be short and thin. Normalization of lengths and areas helps to detect these smaller BCCs.

Cell-competition algorithm: a new segmentation algorithm for multiple objects with irregular boundaries in ultrasound images

Segmentation of multiple objects with irregular contours and surrounding sporadic spots is a common practice in ultrasound image analysis. A new region-based approach, called cell-competition algorithm, is proposed for simultaneous segmentation of multiple objects in a sonogram. The algorithm is composed of two essential ideas. One is simultaneous cell-based deformation of regions and the other is cell competition. The cells are generated by two-pass watershed transformations. The cell-competition algorithm has been validated with 13 synthetic images of different contrast-to-noise ratios and 71 breast sonograms. Three assessments have been carried out and the results show that the boundaries derived by the cell-competition algorithm are reasonably comparable to those delineated manually. Moreover, the cell-competition algorithm is robust to the variation of regions-of-interest and a range of thresholds required for the second-pass watershed transformation. The proposed algorithm is also shown to be superior to the region-competition algorithm for both types of images.

Real time computation and temporal coherence of opacity transfer functions for direct volume rendering of ultrasound data

Opacity transfer function (OTF) generation for direct volume rendering of medical image data is an intensely discussed subject. Several automatic methods exist for CT and MRI data, which are not apt for ultrasound data, mainly due to its low signal-to-noise ratio. Furthermore, ultrasound (US) imaging is able to produce time-varying 3D datasets in real time thus opening the door to 4D visualization. However, OTF design for 4D datasets has not been exhaustively discussed until now. We present an efficient solution to generate an optimized OTF for a given 3DUS dataset in real time. Our method results in excellent visualization which we demonstrate using 3D fetus datasets. Finally, we discuss the applicability of our method to 4DUS visualization.

Peripheral application of intravascular ultrasound virtual histology

Intravascular ultrasound (IVUS) provides direct depiction of coronary artery anatomy. Traditional use of this tomographic imaging modality has been in determination of geometric measurements of an artery, such as lumen or plaque size. However, by analyzing the backscattered or radiofrequency (RF) data it is possible to glean information on the composition of plaques. This chapter describes the theory of spectral analysis and its application clinical practice.

The internet and medical collaboration using virtual reality

Computed Tomography (CT) provides a large amount of data but the presentation of the data to a physician can be less than satisfactory. Ideally, the image data should be available to physicians in interactive 3D to allow for improved visualization, planning and diagnosis. A virtual reality representation that not only allows for the manipulation of the image but also allows for the user to, in effect, move inside the image remotely would be ideal. In this paper the research associated with virtual reality is discussed. A formalism is then presented to create, from the CT data, the virtual reality world in the Virtual Reality Modeling Language. An implementation is described of this formalism that uses the Internet to allow for users in remote locations to view and manipulate the virtual worlds.