| |
Records |
Links |
|
Author |
Joan M. Nuñez |
|
| |
Title |
Computer vision techniques for characterization of finger joints in X-ray image |
Type |
Report |
| |
Year |
2011 |
Publication |
CVC Technical Report |
Abbreviated Journal |
|
|
| |
Volume |
165 |
Issue |
|
Pages |
|
|
| |
Keywords |
Rheumatoid arthritis, X-ray, Sharp Van der Heijde, joint characterization, sclerosis detection, bone detection, edge, ridge |
|
| |
Abstract  |
Rheumatoid arthritis (RA) is an autoimmune inflammatory type of arthritis which mainly affects hands on its first stages. Though it is a chronic disease and there is no cure for it, treatments require an accurate assessment of illness evolution. Such assessment is based on evaluation of hand X-ray images by using one of the several available semi-quantitative methods. This task requires highly trained medical personnel. That is why the automation of the assessment would allow professionals to save time and effort. Two stages are involved in this task. Firstly, the joint detection, afterwards, the joint characterization. Unlike the little existing previous work, this contribution clearly separates those two stages and sets the foundations of a modular assessment system focusing on the characterization stage. A hand joint dataset is created and an accurate data analysis is achieved in order to identify relevant features. Since the sclerosis and the lower bone were decided to be the most important features, different computer vision techniques were used in order to develop a detector system for both of them. Joint space width measures are provided and their correlation with Sharp-Van der Heijde is verified |
|
| |
Address |
Bellaterra (Barcelona) |
|
| |
Corporate Author |
Computer Vision Center |
Thesis |
Master's thesis |
|
| |
Publisher |
|
Place of Publication |
|
Editor |
Dr. Fernando Vilariño and Dra. Debora Gil |
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
|
|
| |
Notes |
MV;IAM; |
Approved |
no |
|
| |
Call Number |
IAM @ iam @ Nuñ2011 |
Serial |
1795 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Sergio Vera |
|
| |
Title |
Finger joint modelling from hand X-ray images for assessing rheumatoid arthritis |
Type |
Report |
| |
Year |
2010 |
Publication |
CVC Technical Report |
Abbreviated Journal |
|
|
| |
Volume |
164 |
Issue |
|
Pages |
|
|
| |
Keywords |
Rheumatoid arthritis; joint detection; X-ray; Van der Heijde score |
|
| |
Abstract |
Rheumatoid arthritis is an autoimmune, systemic, inflammatory disorder that mainly af- fects bone joints. While there is no cure for this disease, continuous advances on palliative treatments require frequent verification of patient’s illness evolution. Such evolution is mea- sured through several available semi-quantitative methods that require evaluation of hand and foot X-ray images. Accurate assessment is a time consuming task that requires highly trained personnel. This hinders a generalized use in clinical practice for early diagnose and disease follow-up. In the context of the automatization of such evaluation methods we present a method for detection and characterization of finger joints in hand radiography images. Several measures for assessing the reduction of joint space width are proposed. We compare for the first time such measures to the Van der Heijde score, the gold standard method for rheumatoid arthritis assessment. The proposed method outperforms existing strategies with a detection rate above 95%. Our comparison to Van der Heijde index shows a promising correlation that encourages further research. |
|
| |
Address |
|
|
| |
Corporate Author |
|
Thesis |
Master's thesis |
|
| |
Publisher |
|
Place of Publication |
Bellaterra 01893, Barcelona, Spain |
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
|
|
| |
Notes |
IAM |
Approved |
no |
|
| |
Call Number |
IAM @ iam @ Ver2010 |
Serial |
1661 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Albert Andaluz |
|
| |
Title |
LV Contour Segmentation in TMR images using Semantic Description of Tissue and Prior Knowledge Correction |
Type |
Report |
| |
Year |
2009 |
Publication |
CVC Technical Report |
Abbreviated Journal |
|
|
| |
Volume |
142 |
Issue |
|
Pages |
|
|
| |
Keywords |
Active Contour Models; Snakes; Active Shape Models; Deformable Templates; Left Ventricle Segmentation; Generalized Orthogonal Procrustes Analysis; Harmonic Phase Flow; Principal Component Analysis; Tagged Magnetic Resonance |
|
| |
Abstract |
The Diagnosis of Left Ventricle (LV) pathologies is related to regional wall motion analysis. Health indicator scores such as the rotation and the torsion are useful for the diagnose of the Left Ventricle (LV) function. However, this requires proper identification of LV segments. On one hand, manual segmentation is robust, but it is slow and requires medical expertise. On the other hand, the tag pattern in Tagged Magnetic Resonance (TMR) sequences is a problem for the automatic segmentation of the LV boundaries. Consequently, we propose a method based in the classical formulation of parametric Snakes, combined with Active Shape models. Our semantic definition of the LV is tagged tissue that experiences motion in the systolic cycle. This defines two energy potentials for the Snake convergence. Additionally, the mean shape corrects excessive deviation from the anatomical shape. We have validated our approach in 15 healthy volunteers and two short axis cuts. In this way, we have compared the automatic segmentations to manual shapes outlined by medical experts. Also, we have explored the accuracy of clinical scores computed using automatic contours. The results show minor divergence in the approximation and the manual segmentations as well as robust computation of clinical scores in all cases. From this we conclude that the proposed method is a promising support tool for clinical analysis. |
|
| |
Address |
|
|
| |
Corporate Author |
|
Thesis |
Master's thesis |
|
| |
Publisher |
|
Place of Publication |
Bellaterra 08193, Barcelona, Spain |
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
|
|
| |
Notes |
IAM; |
Approved |
no |
|
| |
Call Number |
IAM @ iam @ And2009 |
Serial |
1667 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Cristhian A. Aguilera-Carrasco |
|
| |
Title |
Evaluation of feature detectors and descriptors in VISIBLE-LWIR cross-spectral imaging |
Type |
Report |
| |
Year |
2014 |
Publication |
CVC Technical Report |
Abbreviated Journal |
|
|
| |
Volume |
177 |
Issue |
|
Pages |
|
|
| |
Keywords |
Multi-spectral; Cross-spectral; Visible-LWIR imaging; Multimodal. |
|
| |
Abstract |
This thesis evaluates the performance of different state-of-art feature detectors and descriptors algorithms in the Visible-LWIR cross-spectral scenario. The focus is to determine if current detector and descriptor algorithms can be used to match features between the LWIR spectrum and the visible spectrum in applications such as, visual odometry, object recognition, image registration and stereo vision. An outdoor cross-spectral dataset was created to evaluate the suitability of the different algorithms. The results
show that the tested algorithms are not suitable to the task of matching features across different spectra. The repeatability ratio was smaller than the 30 percent in the best case and in general matched features were not accurate located. Additionally, these results also suggest that is necessary to create new algorithms that take into account the nature of the different spectra, describing characteristics that exist in both spectra such as discontinuities. |
|
| |
Address |
|
|
| |
Corporate Author |
|
Thesis |
Master's thesis |
|
| |
Publisher |
|
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
|
|
| |
Notes |
ADAS; 600.076 |
Approved |
no |
|
| |
Call Number |
Admin @ si @Agu2014 |
Serial |
2526 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Antonio Esteban Lansaque |
|
| |
Title |
3D reconstruction and recognition using structured ligth |
Type |
Report |
| |
Year |
2014 |
Publication |
CVC Technical Report |
Abbreviated Journal |
|
|
| |
Volume |
179 |
Issue |
|
Pages |
|
|
| |
Keywords |
|
|
| |
Abstract |
This work covers the problem of 3D reconstruction, recognition and 6DOF pose estimation. The goal of this project is to reconstruct a 3D scene and to align an object model of the industrial pieces onto the reconstructed scene. The reconstruction algorithm is based on stereo techniques and the recognition algorithm is based on SHOT descriptors computed on a set of uniform keypoints. Correspondences are used to estimate a first 6DOF transformation that maps the model onto the scene and then ICP algorithm is used to refine the transformation. In order to check the effectiveness of the proposed algorithm, several experiments were performed. These experiments were conducted on a lab environment in order to get results under the same conditions in all of them. Although obtained results are not real time results, the proposed algorithm ends up with high rates of object recognition. |
|
| |
Address |
UAB; September 2014 |
|
| |
Corporate Author |
|
Thesis |
Master's thesis |
|
| |
Publisher |
|
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
|
|
| |
Notes |
IAM; 600.075 |
Approved |
no |
|
| |
Call Number |
Admin @ si @ Est2014 |
Serial |
2578 |
|
| Permanent link to this record |
| |
|
| |
|
Author |
Petia Radeva; Amir Amini; Jintao Huang; Enric Marti |
|
| |
Title |
Deformable B-Solids: application for localization and tracking of MRI-SPAMM data |
Type |
Report |
| |
Year |
1996 |
Publication |
CVC Technical Report |
Abbreviated Journal |
|
|
| |
Volume |
|
Issue |
8 |
Pages |
|
|
| |
Keywords |
|
|
| |
Abstract |
To date, MRI-SPAMM data from different image slices have been analyzed independently. In this paper, we propose an approach for 3D tag localization and tracking of SPAMM data by a novel deformable B-solid. The solid is defined in terms of a 3D tensor product B-spline. The isoparametric curves of the B-spline solid have special importance. These are termed implicit snakes as they deform under image forces from tag lines in different image slices. The localization and tracking of tag lines is performed under constraints of continuity and smoothness of the B-solid. The framework unifies the problems of localization, and displacement fitting and interpolation into the same procedure utilizing B-spline bases for interpolation. To track motion from boundaries and restrict image forces to the myocardium, a volumetric model is employed as a pair of coupled endocardial and epicardial B-spline surfaces. To recover deformations in the LV an energy-minimization problem is posed where both tag and ... |
|
| |
Address |
|
|
| |
Corporate Author |
|
Thesis |
|
|
| |
Publisher |
CVC (UAB) |
Place of Publication |
|
Editor |
|
|
| |
Language |
|
Summary Language |
|
Original Title |
|
|
| |
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
|
| |
Series Volume |
|
Series Issue |
|
Edition |
|
|
| |
ISSN |
|
ISBN |
|
Medium |
|
|
| |
Area |
|
Expedition |
|
Conference |
|
|
| |
Notes |
MILAB;IAM |
Approved |
no |
|
| |
Call Number |
IAM @ iam @ RHM1996 |
Serial |
1631 |
|
| Permanent link to this record |
