Image segmentation in MRI using true T1 and true PD values

Segmentation of tissues in magnetic resonance images is essential especially for a radiologist to be able to identify a disease, tumors, or any tissue. In any magnetic resonance image there exists many different types of tissues each with characteristic T₁ and T₂ decay times and proton densities. If these parameters of tissues can be calculated from the regular magnetic resonance images, the type of tissue could also be determined on any MR image independent of MR hardware characteristics. One such important hardware limitation is the varying sensitivity of an imaging coil spatially. Segmentation algorithms cannot distinguish between an intensity variation caused by the imaging coil sensitivity or a variation by tissue change. Calculated T₁, T₂, and PD images which provide consistent pixel intensity corresponding to the same tissue are therefore easier to utilize in conventional segmentation algorithms. To be able to calculate true T₁ and PD parameters, a slice of human head were imaged sixteen times by holding TE fixed and changing TR each time. The Levenberg-Marquardt method is applied to the data and T₁ and PD values were estimated. The true T₁ and true PD images were produced. The maximum likelihood classification is then applied successfully to four MR images of different slices of human head and the robustness of this method in segmenting CSF, WM, and GM is illustrated.