Robust affine registration method using line/surface normals and correntropy criterion

The problem of matching point clouds is an efficient way of registration, which is significant for many research fields including computer vision, machine learning, and robotics. There may be linear or non-linear transformation between point clouds, but determining the affine relation is more challenging among linear cases. Various methods have been presented to overcome this problem in the literature and one of them is the affine variant of the iterative closest point (ICP) algorithm. However, traditional affine ICP variants are highly sensitive to effects such as noises, deformations, and outliers; the least-square metric is substituted with the correntropy criterion to increase the robustness of ICPs to such effects. Correntropy-based robust affine ICPs available in the literature use point-to-point metric to estimate transformation between point clouds. Conversely, in this study, a line/surface normal that examines point-to-curve or point-to-plane distances is employed together with the correntropy criterion for affine point cloud registration problems. First, the maximum correntropy criterion measure is built for line/surface normal conditions. Then, the closed-form solution that maximizes the similarity between point sets is achieved for 2D registration and extended for 3D registration. Finally, the application procedure of the developed robust affine ICP method is given and its registration performance is examined through extensive experiments on 2D and 3D point sets. The results achieved highlight that our method can align point clouds more robustly and precisely than the state-of-the-art methods in the literature, while the registration time of the process remains at reasonable levels.

CT-to-fluoroscopy registration versus scan-and-plan registration for robot-assisted insertion of lumbar pedicle screws

OBJECTIVE Pedicle screw insertion for stabilization after lumbar fusion surgery is commonly performed by spine surgeons. With the advent of navigation technology, the accuracy of pedicle screw insertion has increased. Robotic guidance has revolutionized the placement of pedicle screws with 2 distinct radiographic registration methods, the scan-and-plan method and CT-to-fluoroscopy method. In this study, the authors aimed to compare the accuracy and safety of these methods. METHODS A retrospective chart review was conducted at 2 centers to obtain operative data for consecutive patients who underwent robot-assisted lumbar pedicle screw placement. The newest robotic platform (Mazor X Robotic System) was used in all cases. One center used the scan-and-plan registration method, and the other used CT-to-fluoroscopy for registration. Screw accuracy was determined by applying the Gertzbein-Robbins scale. Fluoroscopic exposure times were collected from radiology reports. RESULTS Overall, 268 patients underwent pedicle screw insertion, 126 patients with scan-and-plan registration and 142 with CT-to-fluoroscopy registration. In the scan-and-plan cohort, 450 screws were inserted across 266 spinal levels (mean 1.7 ± 1.1 screws/level), with 446 (99.1%) screws classified as Gertzbein-Robbins grade A (within the pedicle) and 4 (0.9%) as grade B (< 2-mm deviation). In the CT-to-fluoroscopy cohort, 574 screws were inserted across 280 lumbar spinal levels (mean 2.05 ± 1.7 screws/ level), with 563 (98.1%) grade A screws and 11 (1.9%) grade B (p = 0.17). The scan-and-plan cohort had nonsignificantly less fluoroscopic exposure per screw than the CT-to-fluoroscopy cohort (12 ± 13 seconds vs 11.1 ± 7 seconds, p = 0.3). CONCLUSIONS Both scan-and-plan registration and CT-to-fluoroscopy registration methods were safe, accurate, and had similar fluoroscopy time exposure overall.

Multi-Sequence MRI Registration of Atherosclerotic Carotid Arteries Based on Cross-Scale Siamese Network

Cardiovascular disease (CVD) is a common disease with high mortality rate, and carotid atherosclerosis (CAS) is one of the leading causes of cardiovascular disease. Multisequence carotid MRI can not only identify carotid atherosclerotic plaque constituents with high sensitivity and specificity, but also obtain different morphological features, which can effectively help doctors improve the accuracy of diagnosis. However, it is difficult to evaluate the accurate evolution of local changes in carotid atherosclerosis in multi-sequence MRI due to the inconsistent parameters of different sequence images and the geometric space mismatch caused by the motion deviation of tissues and organs. To solve these problems, we propose a cross-scale multi-modal image registration method based on the Siamese U-Net. The network uses sub-networks with image inputs of different sizes to extract various features, and a special padding module is designed to make the network available for training on cross-scale features. In addition, to improve the registration performance, a multi-scale loss function under Gaussian smoothing is applied for optimization. For the experiments, we have collected a multi-sequence MRI image dataset from 11 patients with carotid atherosclerosis for a retrospective study. We evaluate our overall architectures by cross-validation on our carotid dataset. The experimental results show that our method can generate precise and reliable results with cross-scale multi-sequence inputs and the registration accuracy can be greatly improved by using the Gaussian smoothing loss function. The DSC of our Siamese structure can reach 84.1% on the carotid data set with cross-size input. With the use of GDSC loss, the average DSC can be improved by 5.23%, while the average distance between fixed landmarks and moving landmarks can be decreased by 6.46%.Our code is made publicly available at: https://github.com/MingHan98/Cross-scale-Siamese-Unet.

A Two-stage Cardiac PET and Late Gadolinium Enhancement MRI Co-registration Method for Improved Assessment of Non-ischemic Cardiomyopathies Using Integrated PET/MR

PurposeRespiratory motion causes mismatches between PET images of the myocardium and the corresponding cardiac MR images in cardiac integrated PET/MR. The mismatch may affect the attenuation correction and the diagnosis of non-ischemic cardiomyopathies. In this study, we present a two-stage cardiac PET and MR Late Gadolinium Enhancement (LGE) co-registration method, which seeks to improve diagnostic accuracy of non-ischemic cardiomyopathies via better image co-registration using an integrated whole-body PET/MR system.MethodsThe proposed PET and LGE two-stage co-registration method was evaluated through comparison with one-stage direct co-registration and no-registration. One hundred and ninety-one slices of LGE and forty lesions were studied. Two trained nuclear medicine physicians independently assessed the displacement between LGE and PET to qualitatively evaluate the co-registration quality. The changes of the mean SUV in the normal myocardium and the LGE-enhanced lesions before and after image co-registration were measured to quantitatively evaluate the accuracy and value of image co-registration.ResultsThe two-stage method had an improved image registration score (4.93±0.89) compared with the no-registration method (3.49±0.84, p value <0.001) and the single-stage method (4.23±0.81, p value <0.001). Furthermore, the two-stage method led to increased SUV value in the myocardium (3.87±2.56) compared with the no-registration method (3.14±1.92, p value <0.001) and the single-stage method (3.32±2.16, p value <0.001). The mean SUV in the LGE lesion significantly increased from 2.51±2.09 to 2.85±2.35 (p value<0.001) after the two-stage co-registration.ConclusionThe proposed two-stage registration method significantly improved the co-registration between PET and LGE in integrated PET/MR imaging. The technique may improve diagnostic accuracy of non-ischemic cardiomyopathies via better image co-registration.Registered No.DF-2020-085, 2020.04.30

Measurement of Lead Localization Accuracy Based on Magnetic Resonance Imaging

Post-implantation localization of deep brain stimulation (DBS) lead based on a magnetic resonance (MR) image is widely used. Existing localization methods use artifact center method or template registration method, which may lead to a considerable deviation of &gt; 2 mm, and result in severe side effects or even surgical failure. Accurate measurement of lead position can instantly inform surgeons of the imprecise implantation. This study aimed to identify the influencing factors in DBS lead post-implantation localization approach, analyze their influence, and describe a localization approach that uses the individual template method to reduce the deviation. We verified that reconstructing direction should be parallel or perpendicular to lead direction, instead of the magnetic field. Besides, we used simplified relationship between magnetic field angle and deviation error to correct the localization results. The mean localization error can be reduced after correction and favors the feasibility of direct localization of DBS lead using MR images. We also discussed influence of in vivo noise on localization frequency and the possibility of using only MR images to localize the contacts.

Using IVIM Parameters to Differentiate Prostate Cancer and Contralateral Normal Tissue through Fusion of MRI Images with Whole-Mount Pathology Specimen Images by Control Point Registration Method

The intravoxel incoherent motion (IVIM) model may enhance the clinical value of multiparametric magnetic resonance imaging (mpMRI) in the detection of prostate cancer (PCa). However, while past IVIM modeling studies have shown promise, they have also reported inconsistent results and limitations, underscoring the need to further enhance the accuracy of IVIM modeling for PCa detection. Therefore, this study utilized the control point registration toolbox function in MATLAB to fuse T2-weighted imaging (T2WI) and diffusion-weighted imaging (DWI) MRI images with whole-mount pathology specimen images in order to eliminate potential bias in IVIM calculations. Sixteen PCa patients underwent prostate MRI scans before undergoing radical prostatectomies. The image fusion method was then applied in calculating the patients’ IVIM parameters. Furthermore, MRI scans were also performed on 22 healthy young volunteers in order to evaluate the changes in IVIM parameters with aging. Among the full study cohort, the f parameter was significantly increased with age, while the D* parameter was significantly decreased. Among the PCa patients, the D and ADC parameters could differentiate PCa tissue from contralateral normal tissue, while the f and D* parameters could not. The presented image fusion method also provided improved precision when comparing regions of interest side by side. However, further studies with more standardized methods are needed to further clarify the benefits of the presented approach and the different IVIM parameters in PCa characterization.

LESSONS LEARNED FROM REGISTRATION OF OCCUPANCY AND USE OF LIGHTING IN OFFICES, SCHOOLS, UNIVERSITIES AND INDUSTRY BUILDINGS, A CROSS COUNTRY STUDY

The paper presents a registration of occupancy and the use of (day)light in four buildings representing respectively offices, primary schools, universities, and industry buildings; it was done across Europe in 2020. A self-registration method was used, assisted with light technical measurements outdoors and indoors. In general, occupants consider the visual environment at the workplace when they are coming in or out of the room. It happens mainly at the beginning (adjustment of blinds and switching light on) and at the end of the working day (switching light off). In the primary school building, where users move in-out many times during the day, the adjustment happens more frequently. Also use of projector generates very low general light level; covering windows and switching off the electric light happens accordingly, but the pattern is not consistent. In general, the changes in the electrical lighting use follow the occupancy pattern, not the light levels.