Background

Images captured using different modalities usually have significant variations in their intensities, which makes it difficult to reveal their internal structural similarities and achieve accurate registration. Most conventional feature-based image registration techniques are fast and efficient, but they cannot be used directly for the registration of multi-modal images because of these intensity variations.

Methods

This paper introduces the theory of manifold learning to transform the original images into mono-modal modalities, which is a feature-based method that is applicable to multi-modal image registration. Subsequently, scale-invariant feature transform is used to detect highly distinctive local descriptors and matches between corresponding images, and a point-based registration is executed.

Results

The algorithm was tested with T1- and T2-weighted magnetic resonance (MR) images obtained from BrainWeb. Both qualitative and quantitative evaluations of the method were performed and the results compared with those produced previously. The experiments showed that feature point matching after manifold learning achieved more accurate results than did the similarity measure for multi-modal image registration.

Conclusions

This study provides a new manifold-based feature point matching method for multi-modal medical image registration, especially for MR images. The proposed method performs better than do conventional intensity-based techniques in terms of its registration accuracy and is suitable for clinical procedures.