AUTOMATION OF LANDMARK SELECTION FOR RODENT BRAIN MRI-HISTOLOGY REGISTRATION USING THIN-PLATE SPLINES

Image registration is the process of aligning two different images of the same object taken at different times, at different orientations or using different instruments. This is common in medical applications since multiple modalities are used to image different parts of the body. This is an important early step in many diagnostic procedures such as change detection, monitoring tumor or quantifying spread of a disease. The widely used landmark based registration approach is tedious, time consuming, inconsistent and error prone. Furthermore, the standard schemes based on rigid and affine transformation can only describe global geometric differences between the objects of interest. In the medical domain, local variations and changes are common due to natural, instrument, surgical and patient induced distortions. Such effects can be accommodated by elastic or non-linear schemes. Thin-plate spline warping is a non-linear technique that is widely used for registering different types of medical images including magnetic resonance and histology images. However, this technique is constrained by manual landmark selection. In this research, we have developed a method to automate the landmark selection process using thin-plate splines by maximizing the normalized mutual information between the two images. The approach has been studied in the context of registering MRI images and the histological sections of a rodent brain. The approach involves using level-set evolution to isolate the brain in a volumetric MRI image. Then the MRI volume is registered to the corresponding 3D histology (stacked histological sections) image using an affine transformation. The MRI volume is then re-sliced to match the corresponding histological sections. Finally these 2D MRI slices are warped to the histological sections using thin-plate splines maximizing the normalized mutual information. The approach was tested with images from 4 rodent brains with over 170 MRI images and over 120 block face images for each brain. The effectiveness of the landmark was determined by comparing its performance with the results manually obtained by three experienced technicians. The results show that the landmarks obtained using the NMI optimization approach is effective and comparable to manual extraction results. Advisor: Ashok Sama