Automatic Retrieval of Anatomical Structures in 3D Medical Images

نویسندگان

  • Jérôme Declerck
  • Gérard Subsol
  • Jean-Philippe Thirion
  • Nicholas Ayache
چکیده

This paper describes a method to automatically generate the mapping between a completely labeled reference image and the 3D medical image of a patient. To a c hieve this, we combined three techniques: the extraction of 3D feature lines, their matching using 3D deformable line models, the extension of the deformation to the whole image space using warping techniques. We present experimental results for the segmentation of structures in Magnetic Resonance images of the brain of diierent patients; the segmentation of the cortical and ventricle structures. We emphasize the advantages of using crest lines deformable models prior to surface based models. This gives a sparser representation of the data, easier to manipulate, and which makes the convergence of the model much less sensitive to initial positionning. In the future, we hope to use this method to generate anatomical atlases, by the automatic interpretation of large sets of 3D medical images. D etection Automatique de Structures Anatomiques dans les Images M edicales 3D R esum e : Le pr esent rapport d ecrit une m ethode pour identiier automati-quement des structures anatomiques dans une image 3D d'un patient a partir d'une image o u ces m^ emes structures sont compl etement r ef erenc ees. Pour ce faire, nous avons combin e trois techniques : l'extraction de lignes caract eris-tiques, leur mise en correspondance en utilisant des mod eles d eformables de ces lignes, l'extension de la d eformation ainsi obtenue a l'image enti ere gr^ ace a des techniques de d eformation d'images. Nous pr esentons des r esultats exp erimentaux sur des images par r esonance magn etique de cerveaux de patients dii erents, en identiiant plus pr ecis ement les structures corticales et ventriculaires. Nous insistons sur les avantages d'uti-liser des mod eles d eformables de lignes de cr^ ete plut^ ot que des mod eles de surfaces : en eeet, cette repr esentation des donn ees est plus concise et plus facile a manipuler. De plus, la convergence du mod ele est moins sensible au positionnement initial. A l'avenir, nous esp erons appliquer ce proc ed e pour g en erer des atlas ana-tomiques electroniques par l'interpr etation automatique de grands ensembles d'images m edicales 3D.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Model-Based Interpretation of 3D Medical Images

The automatic segmentation and labelling of anatomical structures in 3D medical images is a challenging task of practical importance. We describe a model-based approach which allows robust and accurate interpretation using explicit anatomical knowledge. Our method is based on the extension to 3D of Point Distribution Models (PDMs) and associated image search algorithms. A combination of global,...

متن کامل

Development of an Anaglyph Anatomical Atlas of Rabbit as a New Generation of Printable 3D Anatomical Atlases

Introduction: To improve anatomical atlases, we tried to create a printable 3D atlas of rabbit's anatomy based on the Anaglyph. Methods: In this study, twenty white rabbits euthanized and dissected. All 3D images were reconstructed by means of "stereo photo maker (SPM®)" software. Results: By this atlas, users can easily understand nomenclature, the topography and, certainly, the transpo...

متن کامل

A Hybrid Method for Segmentation and Visualization of Teeth in Multi-Slice CT scan Images

Introduction: Various computer assisted medical procedures such as dental implant, orthodontic planning, face, jaw and cosmetic surgeries require automatic quantification and volumetric visualization of teeth. In this regard, segmentation is a major step. Material and Methods: In this paper, inspired by our previous experiences and considering the anatomical knowledge of teeth and jaws, we prop...

متن کامل

Fuzzy Neighbor Voting for Automatic Image Annotation

With quick development of digital images and the availability of imaging tools, massive amounts of images are created. Therefore, efficient management and suitable retrieval, especially by computers, is one of themost challenging fields in image processing. Automatic image annotation (AIA) or refers to attaching words, keywords or comments to an image or to a selected part of it. In this paper,...

متن کامل

3D live-wire-based semi-automatic segmentation of medical images

Segmenting anatomical structures from medical images is usually one of the most important initial steps in many applications, including visualization, computer-aided diagnosis, and morphometric analysis. Manual 2D segmentation suffers from operator variability and is tedious and time-consuming. These disadvantages are accentuated in 3D applications and, the additional requirement of producing i...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1995