Thomas Deschamps

Fast extraction of minimal paths in 3D images and applications to virtual endoscopy.

The aim of this article is to build trajectories for virtual endoscopy inside 3D medical images, using the most automatic way. Usually the construction of this trajectory is left to the clinician who must define some points on the path manually using three orthogonal views. But for a complex structure such as the colon, those views give little information on the shape of the object of interest. The path construction in 3D images becomes a very tedious task and precise a priori knowledge of the structure is needed to determine a suitable trajectory. We propose a more automatic path tracking method to overcome those drawbacks: we are able to build a path, given only one or two end points and the 3D image as inputs. This work is based on previous work by Cohen and Kimmel [Int. J. Comp. Vis. 24 (1) (1997) 57] for extracting paths in 2D images using Fast Marching algorithm. Our original contribution is twofold. On the first hand, we present a general technical contribution which extends minimal paths to 3D images and gives new improvements of the approach that are relevant in 2D as well as in 3D to extract linear structures in images. It includes techniques to make the path extraction scheme faster and easier, by reducing the user interaction. We also develop a new method to extract a centered path in tubular structures. Synthetic and real medical images are used to illustrate each contribution. On the other hand, we show that our method can be efficiently applied to the problem of finding a centered path in tubular anatomical structures with minimum interactivity, and that this path can be used for virtual endoscopy. Results are shown in various anatomical regions (colon, brain vessels, arteries) with different 3D imaging protocols (CT, MR).

Simultaneous segmentation and tree reconstruction of the airways for virtual bronchoscopy

During the last couple of years virtual endoscopic systems (VES) have emerged as standard tools that are nowadays close to be utilized in daily clinical practice. Such tools render hollow human structures, allowing a clinician to visualize their inside in an endoscopic-like paradigm. It is common practice that the camera of a virtual endoscope is attached to the centerline of the structure of interest, to facilitate navigation. This centerline has to be determined manually or automatically, prior to an investigation. While there exist techniques that can straightforwardly handle simple tube-like structures (e.g. colon, aorta), structures like the tracheobronchial tree still represent a challenge due to their complex branching. In these cases it is necessary to determine all branching points within the tree which is - because of the complexity - impractical to be accomplished in a manual manner. This paper presents a simultaneous segmentation/skeletonization algorithm that extracts all major airway branches and large parts of the minor distal branches (up to 7th order) using a front propagation approach. During the segmentation the algorithm keeps track of the centerline of the segmented structure and detects all branching points. This in turn allows the full reconstruction of the tracheobronchial tree.

Segmentation of 3D tubular objects with adaptive front propagation and minimal tree extraction for 3D medical imaging

We present a new fast approach for segmentation of thin branching structures, like vascular trees, based on Fast-Marching (FM) and Level Set (LS) methods. FM allows segmentation of tubular structures by inflating a “long balloon” from a user given single point. However, when the tubular shape is rather long, the front propagation may blow up through the boundary of the desired shape close to the starting point. Our contribution is focused on a method to propagate only the useful part of the front while freezing the rest of it. We demonstrate its ability to segment quickly and accurately tubular and tree-like structures. We also develop a useful stopping criterion for the causal front propagation. We finally derive an efficient algorithm for extracting an underlying 1D skeleton of the branching objects, with minimal path techniques. Each branch being represented by its centerline, we automatically detect the bifurcations, leading to the “Minimal Tree” representation. This so-called “Minimal Tree” is very useful for visualization and quantification of the pathologies in our anatomical data sets. We illustrate our algorithms by applying it to several arteries datasets.

Minimal Paths in 3D Images and Application to Virtual Endoscopy

This paper presents a new method to find minimal paths in 3D images, giving as initial data one or two endpoints. This is based on previous work [1] for extracting paths in 2D images using Fast Marching [4]. Our original contribution is to extend this technique to 3D, and give new improvements of the approach that are relevant in 2D as well as in 3D. We also introduce several methods to reduce the computation cost and the user interaction. This work finds its motivation in the particular case of 3D medical images. We show that this technique can be efficiently applied to the problem of finding a centered path in tubular anatomical structures with minimum interactivity, and we apply it to path construction for virtual endoscopy. Synthetic and real medical images are used to illustrate each contribution.

Grouping Connected Components using Minimal Path Techniques

We address the problem of finding a set of contour curves in a 2D or 3D image. We consider the problem of perceptual grouping and contour completion, where the data is an unstructured set of regions in the image. A new method to find complete curves from a set of edge points is presented. Contours are found as minimal paths between connected components, using the fast marching algorithm. We find the minimal paths between each of these components, until the complete set of these “regions” is connected. The paths are obtained using backpropagation from the saddle points to both components.

Real-Time Interactive Path Extraction with on-the-Fly Adaptation of the External Forces

The aim of this work is to propose an adaptation of optimal path based interactive tools for image segmentation (related to Live-Wire [12] and Intelligent Scissors [18] approaches). We efficiently use both discrete [10] and continuous [6] path search approaches. The segmentation relies on the notion of energy function and we introduce the possibility of complete on-the-fly adaptation of each individual energy term, as well as of their relative weights. Non-specialist users have then a full control of the drawing process which automatically selects the most relevant set of features to steer the path extraction. Tests have been performed on a large variety of medical images.

Clinical Evaluation of an Automatic Path Tracker for Virtual Colonoscopy

Virtual colonoscopy is a minimally invasive technique allowing early detection of colorectal polyps. A path or centerline through the colon can be very useful to perform virtual endoscopy. Manual path tracking is a very time-consuming task and the resulting path depends a lot on the experience of the operator. This severely limits the applicability of the path-based visualization and inspection methods.An automatic path tracker for virtual endoscopy was introduced in [3], based on previous work on minimal path extraction ([1]). First, we briefly recall the theory of the automatic path tracker, detailing how we adapt this method for virtual colonoscopy. We show the speed and robustness of this automatic path tracker by means of a multi-user study where we measured the total user time and the difference in results between users on 29 clinical cases.

Scalable compression of 3D medical datasets using a (2D+T) wavelet video coding scheme

Nowadays the all-digital solution in hospitals is becoming widespread. The formidable increase of medical data to be processed, transmitted and stored, requires some efficient compression systems and innovative tools to improve data access, while ensuring a sufficient visualization quality for diagnosis. Medical image sequences can benefit from advanced video coding techniques when adapted to their specific constraints. Scalability, or the capability to partly decode a video bitstream and to get a reconstruction quality proportional to the decoded amount of information, is a key functionality. We have developed a video codec based on a 3D motion-compensated subband decomposition, which provides a combination of temporal, spatial and SNR scalabilities together with a very competitive compression ratio. We show that, when applied to medical sequences, it outperforms JPEG-2000 on coding efficiency aspects and offers new functionalities.

Efficacy of automatic path tracking in virtual colonoscopy

Abstract Virtual colonoscopy is a minimally invasive technique allowing early detection of colorectal polyps. Several visualization techniques exist to inspect this large amount of data on the presence of lesions. The most common ones are slice-by-slice viewing, multiplanar reformatting and perspective volume rendering of the inner colon wall (virtual endoscopy). A path or centerline through the colon can be very useful to perform virtual endoscopy. Frequently, this path has to be tracked manually. Unfortunately, manual path tracking is a very time-consuming task and the resulting path depends a lot on the experience of the operator. This severely limits the applicability of the path-based visualization and inspection methods. We have developed an automatic path tracker for virtual endoscopy based on the minimal cost path algorithm described in Deschamps and Cohen [1] . In this paper, we briefly summarize the minimal cost path method and its implementation into an automatic path tracker tool. We also describe the results of a multiuser study, where we measured the speed and operator dependence of the automated path tracker.