MIMED
Etude Bibliographique
2010-2011
L'unité MIMED est évaluée par une étude bibliographique de deux articles.
Le compte rendu doit être court et synthétique (4 pages + bibliographie), écrit dans l'un des 2 objectifs suivants:
(1) Vous êtes ingénieur chez un éditeur de plateforme de traitement
d'images médicales et vous devez proposer un choix entre deux
méthodes pour son intégration dans un nouveau module dans la plateforme.
(2) Vous vous apprétez à faire une thèse en traitement d'image médicale
et vous devez établir le cadre méthodologique que vous souhaitez
poursuivre.
Le rendu de cette étude comporte:
(1) une présentation devant le groupe durant un exposé de 10 minutes et 10 minutes de question.
(2) Le compte rendu écrit remis 2 jours avant la séance de
présentation .
Liste des sujets et articles attribués :
[1-2] Nicolas Dumont + Philippe Granjal
Detection of Pathological structures in medical images
Papier #1:
Maggio, Palladini, De Marchi, Alessandrini, Speciale,
Masetti,"Predictive Deconvolution and hybrid feature selection for
computer-aided detection of prostate cancer", IEEE TMI, vol29, 2010. link
Papier #2: Ou, Shen,
Zeng, sun, Moul, Davatzikos, "Sampling the spatial patterns of cancer:
optimized biopsy procedures for estimating prostate cancer volume and
Gleason score" , Medical Image Analysis, vol 13, 2009. link
[3-4] Arnaud Le Carvennec + Nadia Othmane
Registration of brain MRI-CT data via variational approaches
Papier #1:
Guimond, Roche, Ayache, Meunier, "Three-dimentional multimodal brain
wrapping using the Demons algorithm and adaptive intensity correction",
IEEE TMI, vol20, 2001. link
Papier #2: Chen,
Varshney, "Mutual information-based CT-MR brain image registration
using generalized partial volume joint histogram estimation" , IEEE
TMI, vol 22, 2003. link
[5-6] Bertrand Saudreau + Claire Cury
Registration 2D-3D between CT and per-surgery X-ray images
Papier #1: Lyviatan, Yaniv, Joskowicz "Gradient-Based 2-D/3-D Rigid Registration of Fluoroscopic X-Ray to CT",
IEEE TMI, vol22, 2003. link
Papier #2: Russakoff, Rohlfing, Mori, Rueckert, Ho, Adler, Maurer, "Fast
Generation of Digitally Reconstructed Radiographs Using Attenuation
Fields With Application to 2D-3D Image Registration", IEEE
TMI, vol 24, 2005. link
[7] Moulay Hakim FADIL
Tracking objects in fluoroscopic images
Papier #1: Wang, Chen, Zhu, Zhang, Zhou, Comaniciu, "Robust Guidewire Tracking in Fluoroscopy",
IEEE CVPR, 2009. link
Papier #2: Baert, Viergever, Niessen, "Guide-Wire Tracking During Endovascular Interventions", IEEE
TMI, vol 22, 2003. link
[8] Rémi Mariani
Mutual information-based registration approaches
Papier #1: Knops, Maintz, Viergever, Pluim, "Normalized mutual information based registration using k-means clustering and shading correction", MediA, vol10, 2006. link
Papier #2: Loeckx, Slagmolen, Maes, Vandermeulen, Suetens "Nonrigid Image Registration Using Conditional Mutual Information", IEEE
TMI, vol 29, 2010. link
[9-10] Sylvio Rajaspera + Sten Essono
Comparison of quantification approaches in cardiac imaging
Papier #1: Mitchell, Bosch, Lelieveldt, van der Geest, Reiber, Sonka "3-D Active Appearance Models: Segmentation of Cardiac MR and Ultrasound Images", IEEE TMI, vol21, 2002 link
Papier #2: Peters, Ecabert, Meyer, Kneser, Weese, "Optimizing boundary detection via Simulated Search with applications to multi-modal heart segmentation", MediA, vol 14, 2010. link
[11] Basile Pinsard
Automated classification and learning of biomarkers for degenerative brain pathologies
Papier #1: Fan,Batmanghelich, Clark, Davatzikos, "Spatial
patterns of brain atrophy in MCI patients, identified via
high-dimensional pattern classification, predict subsequent cognitive
decline", Neuroimage, vol 39, 2008 link
Papier #2: Thompson, Hayashi, de Zubicaray, Janke, Rose, Semple, Hong, Herman, Gravano, Doddrell, Toga, "Mapping hippocampal and ventricular change in Alzheimer disease", Neuroimage, vol 22, 2004. link
[12] Mounir Kaddouri
3D reconstruction in interventional radiology
Papier #1: Wiesent, Barth, Navab, Durlak, Brunner, Schuetz, Seissler, "Enhanced 3-D-Reconstruction Algorithm for C-Arm Systems Suitable for Interventional Procedures", TMI, vol 19, 2000 link
Papier #2: Markelj, Tomazevi, Pernus, Likar, "Robust Gradient-Based 3-D/2-D Registration of CT and MR to X-Ray Images", TMI, vol 12, 2008. link
[13] Yann Leprince
Intraoperative registration MRI-Echography in neurosurgery
Papier #1: Lunn, Paulsen, Roberts, Kennedy, Hartov, West, "Displacement
Estimation With Co-Registered Ultrasound for Image Guided Neurosurgery:
A Quantitative In Vivo Porcine Study", TMI, vol 22, 2003 link
Papier #2: Coupe, P. Hellier, Morandi, Barillot, "Probe trajectory interpolation for 3D reconstruction of freehand ultrasound", MediA, vol11, 2007. link
[14] Ludovic Fillon
Denoising of MRI spectroscopy
Papier #1: Meije , Roerdink, "Denoising Functional MR Images: A Comparison of Wavelet Denoising and Gaussian Smoothing", TMI, vol 23, 2004 link
Papier #2: Ahmed, "New Denoising Scheme for Magnetic Resonance Spectroscopy Signals", TMI, vol 24, 2005. link
===============================================
Some Tips on Reading Research Papers (from the Computer Vision Faculty at UCF)
1. You have to read the paper several times to understand it. When you read
the paper first time, if you do not understand something do not get stuck, keep
reading assuming you will figure out that later. When you read it the second
time, you will understand much more, and the third time even more ...
2. Try first to get a general idea of the paper: What problem is being
solved? What are the main steps? How can I implement the method?, even though I
do not understand why each step is performed the way it is performed?
3. Try to relate the method to other methods you know, and conceptually find
similarities and differences.
4. In the first reading it may be a good idea to skip the related work,
since you do not know all other papers, they will confuse you more.
5. Do not use dictionary to just look up the meaning of technical terms like
particle filters, maximum likelihood, they are concepts, dictionaries do not
define them. They will tell you literal meanings, which may not be useful.
6. Try to understand each concept in isolation, and then integrate them to
understand the whole paper. For instance, the paper on "Feature Integration
with adaptive weights in a sequential Monte Carlo Tracker" is quite complex
paper at the first look. Because it uses Monte Carlo, particle filter,
likelihood etc. But try to understand the gist of it. The paper is about
tracking, you know a few tracking methods already. It uses features: color
histogram, templates in correlation, shape, etc. You know these features, and
you have used them. The probabilities obtained by each features are combined
(fused) to achieve tracking. How will you combine the probabilities or
confidences of each features: multiply, add, apply threshold and then add
...
Particle filter/condensation method is already available in Intell Open CV
library, use it, get some idea how it works, what are the parameters, then go
back to read the paper again ... If you keep doing it for one week, you will
understand a lot about that paper! Next week you do the second paper, and so on
...