Automatic Exploration and Morphometry/Morphology Assessment of Medical Image Databases

Alexandre Guimond (1) , Gérard Subsol (1, 2, 3) , Jean Meunier (4, 5) , Jean-Philippe Thirion (1)

1 EPIDAURE - Medical imaging and robotics
2 Intrasense SAS
3 LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier
4 DIRO - Département d'Informatique et de Recherche Opérationnelle [Montreal]
5 IGB - Institut de génie biomédical [Montreal]

The design of representative models of the human body is of great interest to medical doctors. Qualitative information about the characteristics of the brain is widely available, but due to the volume of information that needs to be analyzed and the complexity of its structure, rarely is there quanti cation according to a standard model. To address this problem, we propose in this paper an automatic method to retrieve corresponding structures from a database of medical images. This procedure being local and fast, will permit navigation through large databases in a practical amount of time. We present as examples of applications the building of an average volume of interest and preliminary results of classi cation according to morphology.

Mots clés: image database; exploration; volume of interest (VOI); average patient; medical atlas; classication; registration; magnetic resonance imaging (MRI)

Domaines: Imagerie médicale; Modélisation et simulation; Imagerie; Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Alexandre Guimond, Gérard Subsol, Jean Meunier, Jean-Philippe Thirion. Automatic Exploration and Morphometry/Morphology Assessment of Medical Image Databases. Medical Imaging, 1997, Newport Beach, United States. pp.659-670, ⟨10.1117/12.274152⟩. ⟨inria-00615786⟩