Distance Map Supervised Landmark Localization for MR-TRUS Registration
This work addresses a domain-specific problem in medical imaging for prostate cancer diagnosis and treatment, offering an incremental improvement over existing methods.
The authors tackled the problem of MR-TRUS image registration for prostate by using deep learning to localize landmarks and generate an affine transformation matrix, resulting in a significant improvement over manual rigid registration in terms of Target Registration Error (TRE).
In this work, we propose to explicitly use the landmarks of prostate to guide the MR-TRUS image registration. We first train a deep neural network to automatically localize a set of meaningful landmarks, and then directly generate the affine registration matrix from the location of these landmarks. For landmark localization, instead of directly training a network to predict the landmark coordinates, we propose to regress a full-resolution distance map of the landmark, which is demonstrated effective in avoiding statistical bias to unsatisfactory performance and thus improving performance. We then use the predicted landmarks to generate the affine transformation matrix, which outperforms the clinicians' manual rigid registration by a significant margin in terms of TRE.