Discontinuity Preserving Image Registration through Motion Segmentation: A Primal-Dual Approach.

Image registration is a powerful tool in medical image analysis and facilitates the clinical routine in several aspects. There are many well established elastic registration methods, but none of them can so far preserve discontinuities in the displacement field. These discontinuities appear in particular at organ boundaries during the breathing induced organ motion. In this paper, we exploit the fact that motion segmentation could play a guiding role during discontinuity preserving registration. The motion segmentation is embedded in a continuous cut framework guaranteeing convexity for motion segmentation. Furthermore we show that a primal-dual method can be used to estimate a solution to this challenging variational problem. Experimental results are presented for MR images with apparent breathing induced sliding motion of the liver along the abdominal wall.

Reliable volumetry of the cervical spinal cord in MS patient follow-up data with cord image analyzer (Cordial).

Spinal cord (SC) atrophy is an important contributor to the development of disability in many neurological disorders including multiple sclerosis (MS). To assess the spinal cord atrophy in clinical trials and clinical practice, largely automated methods are needed due to the sheer amount of data. Moreover, using these methods in longitudinal trials requires them to deliver highly reliable measurements, enabling comparisons of multiple data sets of the same subject over time. We present a method for SC volumetry using 3D MRI data providing volume measurements for SC sections of fixed length and location. The segmentation combines a continuous max flow approach with SC surface reconstruction that locates the SC boundary based on image voxel intensities. Two cutting planes perpendicular to the SC centerline are determined based on predefined distances to an anatomical landmark, and the cervical SC volume (CSCV) is then calculated in-between these boundaries. The development of the method focused on its application in MRI follow-up studies; the method provides a high scan-rescan reliability, which was tested on healthy subject data. Scan-rescan reliability coefficients of variation (COV) were below 1 %, intra- and interrater COV were even lower (0.1-0.2 %). To show the applicability in longitudinal trials, 3-year follow-up data of 48 patients with a progressive course of MS were assessed. In this cohort, CSCV loss was the only significant predictor of disability progression (p = 0.02). We are, therefore, confident that our method provides a reliable tool for SC volumetry in longitudinal clinical trials.

Histology to microCT data matching using landmarks and a density biased RANSAC.

The fusion of information from different medical imaging techniques plays an important role in data analysis. Despite the many proposed registration algorithms the problem of registering 2D histological images to 3D CT or MR imaging data is still largely unsolved. In this paper we propose a computationally efficient automatic approach to match 2D histological images to 3D micro Computed Tomography data. The landmark-based approach in combination with a density-driven RANSAC plane-fitting allows efficient localization of the histology images in the 3D data within less than four minutes (single-threaded MATLAB code) with an average accuracy of 0.25 mm for orrect and 2.21mm for mismatched slices. The approach managed to uccessfully localize 75% of the histology images in our database. The proposed algorithm is an important step towards solving the problem of registering 2D histology sections to 3D data fully automatically.