ECSMIO 2010 Abstracts


Full Papers
Paper Nr: 1
Title:

MRI IMAGE ENHANCEMENT - A PDE-based Approach Integrating a Double-well Potential Function for Thin Structure Preservation

Authors:

A. Histace and M. Ménard

Abstract: Non-linear or anisotropic regularization PDE’s (Partial Differential Equation) raised a strong interest in the field of medical image processing. The benefit of PDE-based regularization methods lies in the ability to smooth data in a nonlinear way, allowing the preservation of important image features (contours, corners or other discontinuities). In this article, we propose a PDE-based method restoration approach integrating a double-well potential as diffusive function. It is shown that this particular potential leads to a particular regularization PDE which makes the integration of prior knowledge about the gradient intensity level to enhance possible. The corresponding method shows interesting properties regarding stability and preservation of fine structures. As a proof a feasibility, results of restoration are presented on natural images to show potentialities of the proposed method. We also address a particular medical application: enhancement of tagged cardiac MRI.

Paper Nr: 2
Title:

A PRELIMINARY STUDY FOR A BIOMECHANICAL MODEL OF THE RESPIRATORY SYSTEM

Authors:

Jacques Saadé, Anne-Laure Didier, Romain Buttin, Jean-Michel Moreau, Michaël Beuve, Behzad Shariat and Pierre-Frédéric Villard

Abstract: Tumour motion is an essential source of error for treatment planning in radiation therapy. This motion is mostly due to patient respiration. To account for tumour motion, we propose a solution that is based on the biomechanical modelling of the respiratory system. To compute deformations and displacements, we use continuous mechanics laws solved with the finite element method. In this paper, we propose a preliminary study of a complete model of the respiratory system including lungs, chest wall and a simple model of the diaphragm. This feasibility study is achieved by using the data of a “virtual patient”. Results are in accordance with the anatomic reality, showing the feasibility of a complete model of the respiratory system.

Paper Nr: 4
Title:

A MULTIPHASE ACTIVE CONTOUR MODEL WITH DYNAMIC MEDIAL AXIS CONSTRAINT FOR MEDICAL IMAGE SEGMENTATION

Authors:

Yan Zhang and Bogdan J. Matuszewski

Abstract: A level-set based multiphase active contour model is proposed for medical image segmentation in this paper. The proposed method allows multiple objects with very different features to be jointly segmented by simultaneously evolving multiple active contours, each responsible for the segmentation of a single object. In this model, the forces exerted on each active contour mainly consists of two components. The first component makes use of boundary as well as regional information present in the input images. The second component is used to impose the so-called medial axis constraint, which is related to the force induced by interaction of multiple active contours. Experimental results on real medical images are also presented to show that the proposed method has good performances on topology preservation of multiple contours, as well as joint segmentation of similar objects in multiple images.

Paper Nr: 5
Title:

MARKER TRACKS POST-PROCESSING FOR ACCURATE FIDUCIAL MARKER POSITION ESTIMATION IN CONE BEAM CT PROJECTION IMAGES

Authors:

Bogdan Matuszewski, Tom Marchant and Andrzej Skalski

Abstract: This paper describes details of a method for robust and accurate marker position estimation in projection CB images. The method is based on previously proposed tracking algorithms which can cope with multiple proximate markers and image clutter. The algorithm described in this paper can be seen as a post processing algorithm which uses all the calculated hypothetical marker positions, from the tracking algorithm, for all the markers and all projection images in a single combinatorial optimisation process. The algorithm has been design to estimate intra fraction motion during image guided radiation therapy. The results from the algorithm can be used in treatment planning, subsequent treatment monitoring and correction of motion artefacts in cone beam CT. The proposed post processing algorithm reduced the maximum marker position error from 5.6 pixels, using tracker alone, to 2.6 pixels after post processing. This should be compared to estimated 2.5 pixels maximum error present in the ground truth data. For the total number of 3,840 tracked markers after post processing 1.61% and 0.02% of their positional errors were respectively above three and six standard deviation of the ground truth, estimated separately for each marker and each projection image, whereas corresponding results after using tracker alone were 2.86% and 0.23%.

Paper Nr: 6
Title:

DEFORMABLE IMAGE REGISTRATION - Improved Fast Free Form Deformation

Authors:

Bartłomiej W. Papież, Tomasz P. Zieliński and Bogdan J. Matuszewski

Abstract: In this paper, we describe a class of deformable registration techniques with application to radiotherapy of prostate cancer. To solve registration problem we introduced Jacobi and successive over-relaxation methods and compared them with the Gauss-Seidel used in the variational framework previously proposed in literature. A multi-resolution scheme was used to improve speed of computation, robustness and ability to recover bigger image deformations. To investigate the properties of these algorithms they were tested using simulated data with known displacement filed and real CT images . The results show that it is possible to improve currently widely used algorithms by introducing simple modifications in the numerical solving scheme.

Paper Nr: 7
Title:

ENDOBRONCHIAL TUMOR MASS INDICATION IN VIDEOBRONCHOSCOPY - Block based Analysis

Authors:

Artur Przelaskowski, Rafal Jozwiak, Tomasz Zielinski and Mariusz Duplaga

Abstract: Computer-assisted interpretation of bronchial neoplastic lesion is an innovative but exceptionally challenging task due to highly diversified pathology appearance, video quality limitations and the role of subjective assessment of the endobronchial images. This work is focused on various manifestations of endobronchial tumors in acquired image sequences, bronchoscope navigation, artifacts, lightening and reflections, changing color dominants and unstable focus conditions. Proposed method of neoplasmatic areas indication was based on three steps of video analysis: a) informative frame selection, b) block-based unsupervised determining of enlarged textual activity, c) recognition of potentially tumor tissue, based on feature selection in different domains of transformed image and Support Vector Machine (SVM) classification. Prior to all of these procedures, wavelet-based image processing was applied to extract texture image for further analysis. Proposed method was verified with a reference image dataset containing diversified endobronchial tumor patterns. Obtained results reveal high accuracy for independent classification of individual (single video record) forms of endobronchial tumor patterns. The overall accuracy for whole dataset of 888 test blocks reached 100%. Less complex (approximately two times) procedure including initial blocks of interests selection reached accuracy of 96%.

Short Papers
Paper Nr: 3
Title:

A STATISITICAL SHAPE MODEL FOR DEFORMABLE SURFACE REGISTRATION

Authors:

Wei Quan, Bogdan J. Matuszewski and Lik-Kwan Shark

Abstract: This short paper presents a deformable surface registration scheme which is based on the statistical shape modelling technique. The method consists of two major processing stages, model building and model fitting. A statistical shape model is first built using a set of training data. Then the model is deformed and matched to the new data by a modified iterative closest point (ICP) registration process. The proposed method is tested on real 3-D facial data from BU-3DFE database. It is shown that proposed method can achieve a reasonable result on surface registration, and can be used for patient position monitoring in radiation therapy and potentially can be used for monitoring of the radiation therapy progress for head and neck patients by analysis of facial articulation.

Paper Nr: 9
Title:

ITERATIVE IMAGE RECONSTRUCTION METHODS IN CONE BEAM CT APPLIED TO PHANTOM AND CLINICAL DATA

Authors:

W. Qiu, M. Soleimani, C. N. Mitchell, Tom Marchant and Chris Moore

Abstract: Cone beam computed tomography (CBCT) enables a volumetric image reconstruction from 2D projection data. In CBCT reconstruction, iterative methods of image reconstruction offer the potential to generate high quality images and would be an advantage especially for sparse data sets. CBCT image reconstruction software has been developed based on Multi-Instrument Data Analysis System (MIDAS) tomography toolbox. In this paper, we present a comparative study of SIRT and ART algorithms, developed in MIDAS platform. The results will be shown using phantom and clinical patient data.