FULLY-AUTOMATIC IDENTIFICATION OF AC AND PC LANDMARKS ON BRAIN MRI USING SCENE ANALYSIS

We describe a method for identification of brain structures from MRI d ata sets, The bulk of the paper concerns an automatic system for findi ng the anterior and posterior commissures [(AC) and (PC)] in the midsa gittal plane. These landmarks are hey for the definition of the Talair ach space, commonly used in stereotactic neurosurgery, in the definiti on of common coordinate systems for the pooling of functional positron emission tomography (PET) images and for neuroanatomy studies, The pr ocess works according to a step-by-step procedure: it first analyzes t he skull limits. A grey-level histogram is then calculated and allows an automated selection of thresholds, Then, the interhemispheric plane is detected, Following an advanced scene analysis in the midsagittal plane for anatomical structures, the AC and the PC are identified, Exp erimentally, with a set of 200 patients, the process never failed, Its performances and limits are comparable to that of neuroanatomy expert s, Those results are due to a high degree of robustness at each step o f the program.