-
[show abstract]
[hide abstract]
ABSTRACT: Training active shape models requires collecting manual ground-truth meshes in a large image database. While shape information can be reused across multiple imaging modalities, intensity information needs to be imaging modality and protocol specific. In this context, this study has two main purposes: (1) to test the potential of using intensity models learned from MRI simulated datasets and (2) to test the potential of including a measure of reliability during the matching process to increase robustness. We used a population of 400 virtual subjects (XCAT phantom), and two clinical populations of 40 and 45 subjects. Virtual subjects were used to generate simulated datasets (MRISIM simulator). Intensity models were trained both on simulated and real datasets. The trained models were used to segment the left ventricle (LV) and right ventricle (RV) from real datasets. Segmentations were also obtained with and without reliability information. Performance was evaluated with point-to-surface and volume errors. Simulated intensity models obtained average accuracy comparable to inter-observer variability for LV segmentation. The inclusion of reliability information reduced volume errors in hypertrophic patients (EF errors from 17 ± 57% to 10 ± 18%; LV MASS errors from -27 ± 22 g to -14 ± 25 g), and in heart failure patients (EF errors from -8 ± 42% to -5 ± 14%). The RV model of the simulated images needs further improvement to better resemble image intensities around the myocardial edges. Both for real and simulated models, reliability information increased segmentation robustness without penalizing accuracy.
Physics in Medicine and Biology 06/2012; 57(13):4155-74. · 2.83 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: In this work we describe the usage of bilinear statistical models as a means of factoring the shape variability into two components
attributed to inter-subject variation and to the intrinsic dynamics of the human heart. We show that it is feasible to reconstruct
the shape of the heart at discrete points in the cardiac cycle. Provided we are given a small number of shape instances representing
the same heart at different points in the same cycle, we can use the bilinear model to establish this.
Using a temporal and a spatial alignment step in the preprocessing of the shapes, around half of the reconstruction errors
were on the order of the axial image resolution of 2mm, and over 90% was within 3.5mm. From this, we conclude that the dynamics
were indeed separated from the inter-subject variability in our dataset.
International Journal of Computer Vision 04/2012; 85(3):237-252. · 3.74 Impact Factor
-
Mathieu De Craene, Federico M. Sukno,
Catalina Tobon-Gomez,
Constantine Butakoff,
Rosa M. Figueras i Ventura,
Corné Hoogendoorn,
Gemma Piella,
Nicolas Duchateau,
Emma Muñoz-Moreno,
Rafael Sebastian,
Oscar Camara,
Alejandro F. Frangi
[show abstract]
[hide abstract]
ABSTRACT: This paper presents a brief overview of current trends in the construction of population and multi-modal heart atlases in
our group and their application to atlas-based cardiac image analysis. The technical challenges around the construction of
these atlases are organized around two main axes: groupwise image registration of anatomical, motion and fiber images and
construction of statistical shape models. Application-wise, this paper focuses on the extraction of atlas-based biomarkers
for the detection of local shape or motion abnormalities, addressing several cardiac applications where the extracted information
is used to study and grade different pathologies. The paper is concluded with a discussion about the role of statistical atlases
in the integration of multiple information sources and the potential this can bring to in-silico simulations.
09/2010: pages 1-13;
-
Javier Ortega-Garcia,
Julian Fierrez,
Fernando Alonso-Fernandez,
Javier Galbally,
Manuel R Freire,
Joaquin Gonzalez-Rodriguez,
Carmen Garcia-Mateo,
Jose-Luis Alba-Castro,
Elisardo Gonzalez-Agulla,
Enrique Otero-Muras, [......],
Massimo Tistarelli,
Linda Brodo,
Jonas Richiardi,
Andrzej Drygajlo,
Harald Ganster, Federico M Sukno,
Sri-Kaushik Pavani,
Alejandro Frangi,
Lale Akarun,
Arman Savran
[show abstract]
[hide abstract]
ABSTRACT: A new multimodal biometric database designed and acquired within the framework of the European BioSecure Network of Excellence is presented. It is comprised of more than 600 individuals acquired simultaneously in three scenarios: 1) over the Internet, 2) in an office environment with desktop PC, and 3) in indoor/outdoor environments with mobile portable hardware. The three scenarios include a common part of audio/video data. Also, signature and fingerprint data have been acquired both with desktop PC and mobile portable hardware. Additionally, hand and iris data were acquired in the second scenario using desktop PC. Acquisition has been conducted by 11 European institutions. Additional features of the BioSecure Multimodal Database (BMDB) are: two acquisition sessions, several sensors in certain modalities, balanced gender and age distributions, multimodal realistic scenarios with simple and quick tasks per modality, cross-European diversity, availability of demographic data, and compatibility with other multimodal databases. The novel acquisition conditions of the BMDB allow us to perform new challenging research and evaluation of either monomodal or multimodal biometric systems, as in the recent BioSecure Multimodal Evaluation campaign. A description of this campaign including baseline results of individual modalities from the new database is also given. The database is expected to be available for research purposes through the BioSecure Association during 2008.
IEEE Transactions on Software Engineering 06/2010; 32(6):1097-111. · 1.98 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: We present a novel approach for automatic segmentation of the myocardium in short-axis MRI using deformable medial models with an explicit representation of thickness. Segmentation is constrained by a Markov prior on myocardial thickness. Best practices from Active Shape Modeling (global PCA shape prior, statistical appearance model, local search) are adapted to the medial model. Segmentation performance is evaluated by comparing to manual segmentation in a heterogeneous adult MRI dataset. Average boundary displacement error is under 1.4 mm for left and right ventricles, comparing favorably with published work.
Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. 01/2010; 13(Pt 1):468-75.
-
[show abstract]
[hide abstract]
ABSTRACT: One of the drawbacks of statistical shape models is their occasional failure to converge. Although visually this fact is usually easy to recognize, there is no automatic way to detect it. In this paper, we introduce a generic reliability measure for statistical shape models. It is based on a probabilistic framework and uses information extracted by the model itself during the matching process. The proposed method was validated with two variants of Active Shape Models in the context facial image analysis. Experimental results on more than 3700 facial images showed a high degree of correlation between the segmentation accuracy and the estimated reliability metric.
IEEE Transactions on Image Processing 01/2009; 17(12):2442-55. · 3.04 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: In this work we introduce the usage of bilinear models as a means of factorising the shape variation induced by subject variability and the contraction of the human heart. We show that it is feasible to reconstruct the shape of the heart at a certain point in the cardiac cycle if we are given a small number of shapes representing the same heart at different points in the same cycle, using the bilinear model. Depending on pathology and the ratios between healthy and pathological hearts in the training set, RMS reconstruction errors measured between 1.39 and 16.58 millimetres, with a median of 6.79 and 90th percentile of 9.95 millimetres.
Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on; 11/2007
-
[show abstract]
[hide abstract]
ABSTRACT: This work is framed in the field of statistical face analysis. In particular, the problem of accurate segmentation of prominent features of the face in frontal view images is addressed. We propose a method that generalizes linear Active Shape Models (ASMs), which have already been used for this task. The technique is built upon the development of a nonlinear intensity model, incorporating a reduced set of differential invariant features as local image descriptors. These features are invariant to rigid transformations, and a subset of them is chosen by Sequential Feature Selection for each landmark and resolution level. The new approach overcomes the unimodality and Gaussianity assumptions of classical ASMs regarding the distribution of the intensity values across the training set. Our methodology has demonstrated a significant improvement in segmentation precision as compared to the linear ASM and Optimal Features ASM (a nonlinear extension of the pioneer algorithm) in the tests performed on AR, XM2VTS, and EQUINOX databases.
IEEE Transactions on Pattern Analysis and Machine Intelligence 08/2007; 29(7):1105-17. · 4.91 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: One of the important obstacles in the image-based analysis of the human face is the 3D nature of the problem and the 2D nature of most imaging systems used for biometric applications. Due to this, accuracy is strongly influenced by the viewpoint of the images, being frontal views the most thoroughly studied. However, when fully automatic face analysis systems are designed, capturing frontal-view images cannot be guaranteed. Examples of this situation can be found in surveillance systems, car driver images or whenever there are architectural constraints that prevent from placing a camera frontal to the subject. Taking advantage of the fact that most facial features lie approximately on the same plane, we propose the use of projective geometry across different views. An active shape model constructed with frontal-view images can then be directly applied to the segmentation of pictures taken from other viewpoints. The proposed extension demonstrates being significantly more invariant than the standard approach. Validation of the method is presented in 360 images from the AV@CAR database, systematically divided into three different rotations (to both sides), as well as upper and lower views due to nodding. The presented tests are among the largest quantitative results reported to date in face segmentation under varying poses.
Pattern Recognition.
