Performance evaluation of MIND demons deformable registration of MR and CT images in spinal interventions

Multimodal image synthesis based on disentanglement representations of anatomical and modality specific features, learned using uncooperative relativistic GAN

Growing number of methods for attenuation-coefficient map estimation from magnetic resonance (MR) images have recently been proposed because of the increasing interest in MR-guided radiotherapy and the introduction of positron emission tomography (PET) MR hybrid systems. We propose a deep-network ensemble incorporating stochastic-binary-anatomical encoders and imaging-modality variational autoencoders, to disentangle image-latent spaces into a space of modality-invariant anatomical features and spaces of modality attributes. The ensemble integrates modality-modulated decoders to normalize features and image intensities based on imaging modality. Besides promoting disentanglement, the architecture fosters uncooperative learning, offering ability to maintain anatomical structure in a cross-modality reconstruction. Introduction of a modality-invariant structural consistency constraint further enforces faithful embedding of anatomy. To improve training stability and fidelity of synthesized modalities, the ensemble is trained in a relativistic generative adversarial framework incorporating multiscale discriminators. Analyses of priors and network architectures as well as performance validation were performed on computed tomography (CT) and MR pelvis datasets. The proposed method demonstrated robustness against intensity inhomogeneity, improved tissue-class differentiation, and offered synthetic CT in Hounsfield units with intensities consistent and smooth across slices compared to the state-of-the-art approaches, offering median normalized mutual information of 1.28, normalized cross correlation of 0.97, and gradient cross correlation of 0.59 over 324 images.

Characterization of a new physical phantom for testing rigid and deformable image registration

The purpose of this study was to describe a new user-friendly, low-cost phantom that was developed to test the accuracy of rigid and deformable image registration (DIR) systems and to demonstrate the functional efficacy of the new phantom. The phantom was constructed out of acrylic and includes a variety of inserts that simulate different tissue shapes and properties. It can simulate deformations and location changes in patient anatomy by changing the rotations of both the phantom and the inserts. CT scans of this phantom were obtained and used to test the rigid and deformable registration accuracy of the Velocity software. Eight rotation and translation scenarios were used to test the rigid registration accuracy, and 11 deformation scenarios were used to test the DIR accuracy. The mean rotation accuracies in the X-Y (axial) and X-Z (coronal) planes were 0.50° and 0.13°, respectively. The mean translation accuracy was 1 mm in both the X and Y direction and was tested in soft tissue and bone. The DIR accuracies for soft tissue and bone were 0.93 (mean Dice similarity coefficient), 8.3 and 4.5 mm (mean Hausdouff distance), 0.95 and 0.79 mm (mean distance), and 1.13 and 1.12 (mean volume ratio) for soft tissue content (DTE oil) and bone, respectively. The new phantom has a simple design and can be constructed at a low cost. This phantom will allow DIR systems to be effectively and efficiently verified to ensure system performance.

Inter-scanner Variation Independent Descriptors for Constrained Diffeomorphic Demons Registration of Retina OCT

PURPOSE

OCT offers high in-plane micrometer resolution, enabling studies of neurodegenerative and ocular-disease mechanisms via imaging of the retina at low cost. An important component to such studies is inter-scanner deformable image registration. Image quality of OCT, however, is suboptimal with poor signal-to-noise ratio and through-plane resolution. Geometry of OCT is additionally improperly defined. We developed a diffeomorphic deformable registration method incorporating constraints accommodating the improper geometry and a decentralized-modality-insensitive-neighborhood-descriptors (D-MIND) robust against degradation of OCT image quality and inter-scanner variability.

METHOD

The method, called D-MIND Demons, estimates diffeomorphisms using D-MINDs under constraints on the direction of velocity fields in a MIND-Demons framework. Descriptiveness of D-MINDs with/without denoising was ranked against four other shape/texture-based descriptors. Performance of D-MIND Demons and its variants incorporating other descriptors was compared for cross-scanner, intra- and inter-subject deformable registration using clinical retina OCT data.

RESULT

D-MINDs outperformed other descriptors with the difference in mutual descriptiveness between high-contrast and homogenous regions > 0.2. Among Demons variants, D-MIND-Demons was computationally efficient, demonstrating robustness against OCT image degradation (noise, speckle, intensity-non-uniformity, and poor through-plane resolution) and consistent registration accuracy [(4±4 μm) and (4±6 μm) in cross-scanner intra- and inter-subject registration] regardless of denoising.

CONCLUSIONS

A promising method for cross-scanner, intra- and inter-subject OCT image registration has been developed for ophthalmological and neurological studies of retinal structures. The approach could assist image segmentation, evaluation of longitudinal disease progression, and patient population analysis, which in turn, facilitate diagnosis and patient-specific treatment.