Interactive 3D medical image segmentation with energy-minimizing implicit functions

Quantitative Assessment of Variational Surface Reconstruction from Sparse Point Clouds in Freehand 3D Ultrasound Imaging during Image-Guided Tumor Ablation

“…The VSR method has another limitation concerning contradictory inputs as shown by Heckel et al [46], i.e., contours that define different surfaces, although they should be located on the same surface. This issue was demonstrated in Figure 14.…”

“…Variational interpolation is commonly used in the surface reconstruction of dense point clouds from ranger scanners [42][43][44][45], and also in the segmentation of medical data [46], but has not been used in the surface reconstruction of freehand 3D US. Although [46] was focused on the 3D segmentation of medical images, the variational interpolation technique used was the same as that in [40]. Because this paper was not dedicated to ultrasound imaging, the specific characteristics of surface reconstruction in freehand 3D US were not addressed.…”

Real-time 3D interactive segmentation of echocardiographic data through user-based deformation of B-spline explicit active surfaces

“…The most simple approaches are geometrical modeling tools which can be used to aid the manual construction of a 3D model, such as in [4,5]. More recently, Heckel et al have proposed a variational interpolation framework to implement near real-time reconstruction of a 3D model from a set of contours [2]. On cardiac segmentation, the ellipsoidal shape of the LV can be used to improve the efficiency of the generation of the 3D model, as in the guide-point modeling algorithm from Young et al [6].…”

“…The user input can be introduced at different levels of the processing pipeline, either by initializing and setting the parameters of the segmentation algorithm or by interacting with it, allowing online steering of the segmentation result. The segmentation algorithms that follow the first approach can be broadly classified as semi-automatic, where the segmentation process has a 'fire and forget' behavior [2]. On the other hand, the second approach more closely resembles a truly interactive process, where the algorithm reacts to the information introduced by the user preferably in real-time.…”

A comparative study – medical imaging techniques: gpu-based or parallelized?

“…The authors have also evaluated the performance gains of such algorithms using GPUs and presenting both sequential as well as parallel implementations of those algorithms. Heckel et al 2011 [16] have presented an interactive segmentation method for 3D medical images which is used for reconstruction of an object's surface by making use of implicit, smooth and energy-minimizing functions. Benquassmi et al 2011 [17] have presented the parallelization of Katsevich CT image reconstruction method by making use of OpenMP.…”