The lung is characterized by high elasticity and complex structure, which implies that the lung is capable of undergoing complex deformation and the shape variable is substantial. Large deformation estimation poses significant challenges to lung image registration. The traditional U-Net architecture is difficult to cover complex deformation due to its limited receptive field. Moreover, the relationship between voxels weakens as the number of downsampling times increases, that is, the long-range dependence issue. In this paper, we propose a novel multilevel registration framework which enhances the correspondence between voxels to improve the ability of estimating large deformations. Our approach consists of a convolutional neural network (CNN) with a two-stream registration structure and a cross-scale mapping attention (CSMA) mechanism. The former extracts the robust features of image pairs within layers, while the latter establishes frequent connections between layers to maintain the correlation of image pairs. This method fully utilizes the context information of different scales to establish the mapping relationship between low-resolution and high-resolution feature maps. We have achieved remarkable results on DIRLAB (TRE 1.56 ± 1.60) and POPI (NCC 99.72% SSIM 91.42%) dataset, demonstrating that this strategy can effectively address the large deformation issues, mitigate long-range dependence, and ultimately achieve more robust lung CT image registration.

UNASSIGNED: Frontotemporal lobar degeneration (FTLD) is associated with FTLD due to tau (FTLD-tau) or TDP (FTLD-TDP) inclusions found at autopsy. Arterial Spin Labeling (ASL) MRI is often acquired in the same session as a structural T1-weighted image (T1w), enabling detection of regional changes in cerebral blood flow (CBF). We hypothesize that ASL-T1w registration with more degrees of freedom using boundary-based registration (BBR) will better align ASL and T1w images and show increased sensitivity to regional hypoperfusion differences compared to manual registration in patient participants. We hypothesize that hypoperfusion will be associated with a clinical measure of disease severity, the FTLD-modified clinical dementia rating scale sum-of-boxes (FTLD-CDR).
UNASSIGNED: Patients with sporadic likely FTLD-tau (sFTLD-tau; N = 21), with sporadic likely FTLD-TDP (sFTLD-TDP; N = 14), and controls (N = 50) were recruited from the Connectomic Imaging in Familial and Sporadic Frontotemporal Degeneration project (FTDHCP). Pearson\'s Correlation Coefficients (CC) were calculated on cortical vertex-wise CBF between each participant for each of 3 registration methods: (1) manual registration, (2) BBR initialized with manual registration (manual+BBR), (3) and BBR initialized using FLIRT (FLIRT+BBR). Mean CBF was calculated in the same regions of interest (ROIs) for each registration method after image alignment. Paired t-tests of CC values for each registration method were performed to compare alignment. Mean CBF in each ROI was compared between groups using t-tests. Differences were considered significant at p < 0.05 (Bonferroni-corrected). We performed linear regression to relate FTLD-CDR to mean CBF in patients with sFTLD-tau and sFTLD-TDP, separately (p < 0.05, uncorrected).
UNASSIGNED: All registration methods demonstrated significant hypoperfusion in frontal and temporal regions in each patient group relative to controls. All registration methods detected hypoperfusion in the left insular cortex, middle temporal gyrus, and temporal pole in sFTLD-TDP relative to sFTLD-tau. FTLD-CDR had an inverse association with CBF in right temporal and orbitofrontal ROIs in sFTLD-TDP. Manual+BBR performed similarly to FLIRT+BBR.
UNASSIGNED: ASL is sensitive to distinct regions of hypoperfusion in patient participants relative to controls, and in patients with sFTLD-TDP relative to sFTLD-tau, and decreasing perfusion is associated with increasing disease severity, at least in sFTLD-TDP. BBR can register ASL-T1w images adequately for controls and patients.

OBJECTIVE: Registration of pulmonary computed tomography (CT) images with radiation-induced lung diseases (RILD) was essential to investigate the voxel-wise relationship between the formation of RILD and the radiation dose received by different tissues. Although various approaches had been developed for the registration of lung CTs, their performances remained clinically unsatisfactory for registration of lung CT images with RILD. The main difficulties arose from the longitudinal change in lung parenchyma, including RILD and volumetric change of lung cancers, after radiation therapy, leading to inaccurate registration and artifacts caused by erroneous matching of the RILD tissues.
METHODS: To overcome the influence of the parenchymal changes, a divide-and-conquer approach rooted in the coherent point drift (CPD) paradigm was proposed. The proposed method was based on two kernel ideas. One was the idea of component structure wise registration. Specifically, the proposed method relaxed the intrinsic assumption of equal isotropic covariances in CPD by decomposing a lung and its surrounding tissues into component structures and independently registering the component structures pairwise by CPD. The other was the idea of defining a vascular subtree centered at a matched branch point as a component structure. This idea could not only provide a sufficient number of matched feature points within a parenchyma, but avoid being corrupted by the false feature points resided in the RILD tissues due to globally and indiscriminately sampling using mathematical operators. The overall deformation model was built by using the Thin Plate Spline based on all matched points.
RESULTS: This study recruited 30 pairs of lung CT images with RILD, 15 of which were used for internal validation (leave-one-out cross-validation) and the other 15 for external validation. The experimental results showed that the proposed algorithm achieved a mean and a mean of maximum 1 % of average surface distances <2 and 8 mm, respectively, and a mean and a maximum target registration error <2 mm and 5 mm on both internal and external validation datasets. The paired two-sample t-tests corroborated that the proposed algorithm outperformed a recent method, the Stavropoulou\'s method, on the external validation dataset (p < 0.05).
CONCLUSIONS: The proposed algorithm effectively reduced the influence of parenchymal changes, resulting in a reasonably accurate and artifact-free registration.

A deep understanding of neuron structure and function is crucial for elucidating brain mechanisms, diagnosing and treating diseases. Optical microscopy, pivotal in neuroscience, illuminates neuronal shapes, projections, and electrical activities. To explore the projection of specific functional neurons, scientists have been developing optical-based multimodal imaging strategies to simultaneously capture dynamic in vivo signals and static ex vivo structures from the same neuron. However, the original position of neurons is highly susceptible to displacement during ex vivo imaging, presenting a significant challenge for integrating multimodal information at the single-neuron level. This study introduces a graph-model-based approach for cell image matching, facilitating precise and automated pairing of sparsely labeled neurons across different optical microscopic images. It has been shown that utilizing neuron distribution as a matching feature can mitigate modal differences, the high-order graph model can address scale inconsistency, and the nonlinear iteration can resolve discrepancies in neuron density. This strategy was applied to the connectivity study of the mouse visual cortex, performing cell matching between the two-photon calcium image and the HD-fMOST brain-wide anatomical image sets. Experimental results demonstrate 96.67% precision, 85.29% recall rate, and 90.63% F1 Score, comparable to expert technicians. This study builds a bridge between functional and structural imaging, offering crucial technical support for neuron classification and circuitry analysis.

Medical image registration has become pivotal in recent years with the integration of various imaging modalities like X-ray, ultrasound, MRI, and CT scans, enabling comprehensive analysis and diagnosis of biological structures. This paper provides a comprehensive review of registration techniques for medical images, with an in-depth focus on 2D-2D image registration methods. While 3D registration is briefly touched upon, the primary emphasis remains on 2D techniques and their applications. This review covers registration techniques for diverse modalities, including unimodal, multimodal, interpatient, and intra-patient. The paper explores the challenges encountered in medical image registration, including geometric distortion, differences in image properties, outliers, and optimization convergence, and discusses their impact on registration accuracy and reliability. Strategies for addressing these challenges are highlighted, emphasizing the need for continual innovation and refinement of techniques to enhance the accuracy and reliability of medical image registration systems. The paper concludes by emphasizing the importance of accurate medical image registration in improving diagnosis.

Annotation of multiple regions of interest across the whole mouse brain is an indispensable process for quantitative evaluation of a multitude of study endpoints in neuroscience digital pathology. Prior experience and domain expert knowledge are the key aspects for image annotation quality and consistency. At present, image annotation is often achieved manually by certified pathologists or trained technicians, limiting the total throughput of studies performed at neuroscience digital pathology labs. It may also mean that simpler and quicker methods of examining tissue samples are used by non-pathologists, especially in the early stages of research and preclinical studies. To address these limitations and to meet the growing demand for image analysis in a pharmaceutical setting, we developed AnNoBrainer, an open-source software tool that leverages deep learning, image registration, and standard cortical brain templates to automatically annotate individual brain regions on 2D pathology slides. Application of AnNoBrainer to a published set of pathology slides from transgenic mice models of synucleinopathy revealed comparable accuracy, increased reproducibility, and a significant reduction (~ 50%) in time spent on brain annotation, quality control and labelling compared to trained scientists in pathology. Taken together, AnNoBrainer offers a rapid, accurate, and reproducible automated annotation of mouse brain images that largely meets the experts\' histopathological assessment standards (> 85% of cases) and enables high-throughput image analysis workflows in digital pathology labs.

A fast scanner of optical-resolution photoacoustic microscopy is inherently vulnerable to perturbation, leading to severe image distortion and significant misalignment among multiple 2D or 3D images. Restoration and registration of these images is critical for accurately quantifying dynamic information in long-term imaging. However, traditional registration algorithms face a great challenge in computational throughput. Here, we develop an unsupervised deep learning based registration network to achieve real-time image restoration and registration. This method can correct artifacts from B-scan distortion and remove misalignment among adjacent and repetitive images in real time. Compared with conventional intensity based registration algorithms, the throughput of the developed algorithm is improved by 50 times. After training, the new deep learning method performs better than conventional feature based image registration algorithms. The results show that the proposed method can accurately restore and register the images of fast-scanning photoacoustic microscopy in real time, offering a powerful tool to extract dynamic vascular structural and functional information.

We introduce a novel AI-driven approach to unsupervised fundus image registration utilizing our Generalized Polynomial Transformation (GPT) model. Through the GPT, we establish a foundational model capable of simulating diverse polynomial transformations, trained on a large synthetic dataset to encompass a broad range of transformation scenarios. Additionally, our hybrid pre-processing strategy aims to streamline the learning process by offering model-focused input. We evaluated our model\'s effectiveness on the publicly available AREDS dataset by using standard metrics such as image-level and parameter-level analyzes. Linear regression analysis reveals an average Pearson correlation coefficient (R) of 0.9876 across all quadratic transformation parameters. Image-level evaluation, comprising qualitative and quantitative analyzes, showcases significant improvements in Structural Similarity Index (SSIM) and Normalized Cross Correlation (NCC) scores, indicating its robust performance. Notably, precise matching of the optic disc and vessel locations with minimal global distortion are observed. These findings underscore the potential of GPT-based approaches in image registration methodologies, promising advancements in diagnosis, treatment planning, and disease monitoring in ophthalmology and beyond.

Registering longitudinal infant brain images is challenging, as the infant brain undergoes rapid changes in size, shape and tissue contrast in the first months and years of life. Diffusion tensor images (DTI) have relatively consistent tissue properties over the course of infancy compared to commonly used T1 or T2-weighted images, presenting great potential for infant brain registration. Moreover, groupwise registration has been widely used in infant neuroimaging studies to reduce bias introduced by predefined atlases that may not be well representative of samples under study. To date, however, no methods have been developed for groupwise registration of tensor-based images. Here, we propose a novel registration approach to groupwise align longitudinal infant DTI images to a sample-specific common space. Longitudinal infant DTI images are first clustered into more homogenous subgroups based on image similarity using Louvain clustering. DTI scans are then aligned within each subgroup using standard tensor-based registration. The resulting images from all subgroups are then further aligned onto a sample-specific common space. Results show that our approach significantly improved registration accuracy both globally and locally compared to standard tensor-based registration and standard fractional anisotropy-based registration. Additionally, clustering based on image similarity yielded significantly higher registration accuracy compared to no clustering, but comparable registration accuracy compared to clustering based on chronological age. By registering images groupwise to reduce registration bias and capitalizing on the consistency of features in tensor maps across early infancy, our groupwise registration framework facilitates more accurate alignment of longitudinal infant brain images.

Synthetic aperture radar (SAR) image registration is an important process in many applications, such as image stitching and remote sensing surveillance. The registration accuracy is commonly affected by the presence of speckle noise in SAR images. When speckle noise is intense, the number of image features acquired by single-feature-based methods is insufficient. An SAR image registration method that combines nonlinear diffusion filtering, Hessian features and edge points is proposed in this paper to reduce speckle noise and obtain more image features. The proposed method uses the infinite symmetric exponential filter (ISEF) for image pre-processing and nonlinear diffusion filtering for scale-space construction. These measures can remove speckle noise from SAR images while preserving image edges. Hessian features and edge points are also employed as image features to optimize the utilization of feature information. Experiments with different noise levels, geometric transformations and image scenes demonstrate that the proposed method effectively improves the accuracy of SAR image registration compared with the SIFT-OCT, SAR-SIFT, Harris-SIFT, NF-Hessian and KAZE-SAR algorithms.