Adaptive registration of magnetic resonance images based on a viscous fluid model

Multimodal Image Registration Using a Viscous Fluid Model with the Bhattacharyya Distance

Image registration is an elementary task in medical image processing and analysis, which can be divided into monomodal and multimodal. Direct 3D multimodal registration in volumetric medical images can provide more insight into the interpretation of subsequent image processing applications than 2D methods. This paper is dedicated to the development of a 3D multimodal image registration algorithm based on a viscous fluid model associated with the Bhattacharyya distance. In our approach, a modified Navier-Stoke's equation is exploited as the foundation of the multimodal image registration framework. The hopscotch method is numerically implemented to solve the velocity field, whose values at the explicit locations are first computed and the values at the implicit positions are solved by transposition. The differential of the Bhattacharyya distance is incorporated into the body force function, which is the main driving force for deformation, to enable multimodal registration. A variety of simulated and real brain MR images were utilized to assess the proposed 3D multimodal image registration system. Preliminary experimental results indicated that our algorithm produced high registration accuracy in various registration scenarios and outperformed other competing methods in many multimodal image registration tasks.Clinical Relevance- This facilitates the disease diagnosis and treatment planning that requires accurate 3D multimodal image registration without massive image data and extensive training regardless of the imaging modality.

A deep learning based framework for the registration of three dimensional multi-modal medical images of the head

Image registration is a fundamental task in image analysis in which the transform that moves the coordinate system of one image to another is calculated. Registration of multi-modal medical images has important implications for clinical diagnosis, treatment planning, and image-guided surgery as it provides the means of bringing together complimentary information obtained from different image modalities. However, since different image modalities have different properties due to their different acquisition methods, it remains a challenging task to find a fast and accurate match between multi-modal images. Furthermore, due to reasons such as ethical issues and need for human expert intervention, it is difficult to collect a large database of labelled multi-modal medical images. In addition, manual input is required to determine the fixed and moving images as input to registration algorithms. In this paper, we address these issues and introduce a registration framework that (1) creates synthetic data to augment existing datasets, (2) generates ground truth data to be used in the training and testing of algorithms, (3) registers (using a combination of deep learning and conventional machine learning methods) multi-modal images in an accurate and fast manner, and (4) automatically classifies the image modality so that the process of registration can be fully automated. We validate the performance of the proposed framework on CT and MRI images of the head obtained from a publicly available registration database.

Medical decision making for 5D cardiac model: Template matching technique and simulation of the fifth dimension

The purpose of this paper is to develop a 5D cardiac model which is inspired from the 5D model for the lungs. This model depends on five variables: the anatomical structure of the 3D heart, temporal dimension and the function of blood flow as the fifth dimension. To test this hypothesis, we took the same mathematical modeling as a reference for the fifth dimension of pulmonary flow where r→_ρ(t)=r→_v(t)+r_f→(t) wherer→_v(t) is the displacement vectors with approximate magnitudes by linear functions of the tidal volume and r_f→(t) is the blood flow. The scans were acquired for 10 patients,in the 404 series for a total of 18,483 images studied in three cases: healthy patient, case of heart failure and aortic stenosis. Where r→_vand r→_f are the unit vectors along the volume of ejection and the blood flow axes, indicating the direction of motion of the object due to heart volume ejection and blood flow variations, respectively. The quantities of α and β coefficients are determined from real-time patient image data. The alpha and beta coefficients are derived from the following dimension equations[mm / ml] [mm*ms / ml] . Since the cardiac system has two diastolic and systolic phases, we have calculated α₁ and β₁ for telediatolic volume and α₂ and β₂ for telesystolic volume throughout the cardiac cycle as a function of the location of the cuts chosen randomly. Fifth-dimensional experiments are used to track, simulate the behavior of blood flow to detect preliminary indications for the identification of stenosis or valve leakage. The average discrepancy was tabulated as the global fraction of systolic ejection. The results shown in Fig. 3 detect a correspondence between the hunting chamber cut and the flow sequence through the orifice of aorta for this patient with suspicious of having an aortic stenosis disease and an ejection fraction about 71% with a maximum of velocity (Vmax) detected=250 (cm / ms) = 2.5 (m / 10-3 s). In this case this patient has a minor stenosis in the aorta. It should be referred that the normalization of this measures is classified such as : Minor stenosis: area 1.5 cm2, Vmax <3 m / moderate stenosis: area 1.0 - 1.5 cm2, Vmax 3 - 4 m / severe stenosis: area <1.0 cm2, Vmax> 4 m / s. For a patient who has an aortic stenosis the cloud of the points is accumulated comparing to the origin of the axis while the patient with a symptom of insufficiency the points are widened with a remarkable gap in the trajectory. To solve the issue of the bad prediction, the inaccuracy of the clouds points of the model 5D, the lack of the exact measurements to estimate the degree of cardiac insufficiency (leakage or stenosis), a solution of 5D imagery was depicted. Our main contribution is to test the validity of the template-matching algorithm and the fifth dimension simulation to provide more clues to detect the aortic stenosis and cardiac insufficiency in the context of medical decision support.

A Parallel Nonrigid Registration Algorithm Based on B-Spline for Medical Images

The nonrigid registration algorithm based on B-spline Free-Form Deformation (FFD) plays a key role and is widely applied in medical image processing due to the good flexibility and robustness. However, it requires a tremendous amount of computing time to obtain more accurate registration results especially for a large amount of medical image data. To address the issue, a parallel nonrigid registration algorithm based on B-spline is proposed in this paper. First, the Logarithm Squared Difference (LSD) is considered as the similarity metric in the B-spline registration algorithm to improve registration precision. After that, we create a parallel computing strategy and lookup tables (LUTs) to reduce the complexity of the B-spline registration algorithm. As a result, the computing time of three time-consuming steps including B-splines interpolation, LSD computation, and the analytic gradient computation of LSD, is efficiently reduced, for the B-spline registration algorithm employs the Nonlinear Conjugate Gradient (NCG) optimization method. Experimental results of registration quality and execution efficiency on the large amount of medical images show that our algorithm achieves a better registration accuracy in terms of the differences between the best deformation fields and ground truth and a speedup of 17 times over the single-threaded CPU implementation due to the powerful parallel computing ability of Graphics Processing Unit (GPU).