Retinal Image Registration Research Articles

ConKeD: multiview contrastive descriptor learning for keypoint-based retinal image registration

Retinal image registration is of utmost importance due to its wide applications in medical practice. In this context, we propose ConKeD, a novel deep learning approach to learn descriptors for retinal image registration. In contrast to current registration methods, our approach employs a novel multi-positive multi-negative contrastive learning strategy that enables the utilization of additional information from the available training samples. This makes it possible to learn high-quality descriptors from limited training data. To train and evaluate ConKeD, we combine these descriptors with domain-specific keypoints, particularly blood vessel bifurcations and crossovers, that are detected using a deep neural network. Our experimental results demonstrate the benefits of the novel multi-positive multi-negative strategy, as it outperforms the widely used triplet loss technique (single-positive and single-negative) as well as the single-positive multi-negative alternative. Additionally, the combination of ConKeD with the domain-specific keypoints produces comparable results to the state-of-the-art methods for retinal image registration, while offering important advantages such as avoiding pre-processing, utilizing fewer training samples, and requiring fewer detected keypoints, among others. Therefore, ConKeD shows a promising potential towards facilitating the development and application of deep learning-based methods for retinal image registration.Graphical abstract

MEMO: dataset and methods for robust multimodal retinal image registration with large or small vessel density differences

The measurement of retinal blood flow (RBF) in capillaries can provide a powerful biomarker for the early diagnosis and treatment of ocular diseases. However, no single modality can determine capillary flowrates with high precision. Combining erythrocyte-mediated angiography (EMA) with optical coherence tomography angiography (OCTA) has the potential to achieve this goal, as EMA can measure the absolute RBF of retinal microvasculature and OCTA can provide the structural images of capillaries. However, multimodal retinal image registration between these two modalities remains largely unexplored. To fill this gap, we establish MEMO, the first public multimodal EMA and OCTA retinal image dataset. A unique challenge in multimodal retinal image registration between these modalities is the relatively large difference in vessel density (VD). To address this challenge, we propose a segmentation-based deep-learning framework (VDD-Reg), which provides robust results despite differences in vessel density. VDD-Reg consists of a vessel segmentation module and a registration module. To train the vessel segmentation module, we further designed a two-stage semi-supervised learning framework (LVD-Seg) combining supervised and unsupervised losses. We demonstrate that VDD-Reg outperforms existing methods quantitatively and qualitatively for cases of both small VD differences (using the CF-FA dataset) and large VD differences (using our MEMO dataset). Moreover, VDD-Reg requires as few as three annotated vessel segmentation masks to maintain its accuracy, demonstrating its feasibility.

A novel vector field analysis for quantitative structure changes after macular epiretinal membrane surgery.

The aim of this study was to introduce novel vector field analysis for the quantitative measurement of retinal displacement after epiretinal membrane (ERM) removal. We developed a novel framework to measure retinal displacement from retinal fundus images as follows: (1) rigid registration of preoperative retinal fundus images in reference to postoperative retinal fundus images, (2) extraction of retinal vessel segmentation masks from these retinal fundus images, (3) non-rigid registration of preoperative vessel masks in reference to postoperative vessel masks, and (4) calculation of the transformation matrix required for non-rigid registration for each pixel. These pixel-wise vector field results were summarized according to predefined 24 sectors after standardization. We applied this framework to 20 patients who underwent ERM removal to obtain their retinal displacement vector fields between retinal fundus images taken preoperatively and at postoperative 1, 4, 10, and 22months. The mean direction of displacement vectors was in the nasal direction. The mean standardized magnitudes of retinal displacement between preoperative and postoperative 1month, postoperative 1 and 4, 4 and 10, and 10 and 22months were 38.6, 14.9, 7.6, and 5.4, respectively. In conclusion, the proposed method provides a computerized, reproducible, and scalable way to analyze structural changes in the retina with a powerful visualization tool. Retinal structural changes were mostly concentrated in the early postoperative period and tended to move nasally.

SuperJunction: Learning-Based Junction Detection for Retinal Image Registration

Keypoints-based approaches have shown to be promising for retinal image registration, which superimpose two or more images from different views based on keypoint detection and description. However, existing approaches suffer from ineffective keypoint detector and descriptor training. Meanwhile, the non-linear mapping from 3D retinal structure to 2D images is often neglected. In this paper, we propose a novel learning-based junction detection approach for retinal image registration, which enhances both the keypoint detector and descriptor training. To improve the keypoint detection, it uses a multi-task vessel detection to regularize the model training, which helps to learn more representative features and reduce the risk of over-fitting. To achieve effective training for keypoints description, a new constrained negative sampling approach is proposed to compute the descriptor loss. Moreover, we also consider the non-linearity between retinal images from different views during matching. Experimental results on FIRE dataset show that our method achieves mean area under curve of 0.850, which is 12.6% higher than 0.755 by the state-of-the-art method. All the codes are available at https://github.com/samjcheng/SuperJunction.

Synergistic registration of CT-MRI brain images and retinal images: A novel approach leveraging reinforcement learning and modified artificial rabbit optimization

Medical image registration is a pivotal application within the field of medical imaging. It entails the fusion of commonalities among data of disparate modalities into a unified coordinate system, thereby achieving complementary imaging information. This process plays a crucial role in scenarios such as accurate disease diagnosis, surgical guidance, patient monitoring, and radiological therapy. Due to the distinct characteristics exhibited by changes in the same region over time or across different modalities, swiftly and accurately identifying corresponding relationships between pre-registered images remains a formidable challenge. This paper proposes the incorporation of an enhanced Artificial Rabbits Optimization (ARO) algorithm as an agent within the framework of reinforcement learning. The method, referred to as RL-mARO, is employed for medical image registration. By utilizing Normalized Mutual Information (NMI) as a reward and penalty feedback for the similarity metric, the agent continuously adjusts and alters the learning strategies within the population, thereby progressively converging towards the correct registration direction. The contribution of reinforcement learning to ARO was validated on the IEEE CEC2020 benchmark dataset. Simultaneously, registration experiments were conducted on the multi-modal brain dataset, Retrospective Image Registration Evaluation Project (RIRE), as well as the single-modal fundus dataset, Fundus Image Registration Dataset (FIRE). The results of both registration experiments demonstrate that the RL-mARO model exhibits elevated robustness and registration accuracy.

Substrip-based registration and automatic montaging of adaptive optics retinal images.

Precise registration and montage are critical for high-resolution adaptive optics retinal image analysis but are challenged by rapid eye movement. We present a substrip-based method to improve image registration and facilitate the automatic montaging of adaptive optics scanning laser ophthalmoscopy (AOSLO). The program first batches the consecutive images into groups based on a translation threshold and selects an image with minimal distortion within each group as the reference. Within each group, the software divides each image into multiple strips and calculates the Normalized Cross-Correlation with the reference frame using two substrips at both ends of the whole strip to estimate the strip translation, producing a registered image. Then, the software aligns the registered images of all groups also using a substrip based registration, thereby generating a montage with cell-for-cell precision in the overlapping areas of adjacent frames. The algorithm was evaluated with AOSLO images acquired in human subjects with normal macular health and patients with age-related macular degeneration (AMD). Images with a motion amplitude of up to 448 pixels in the fast scanner direction over a frame of 512 × 512 pixels can be precisely registered. Automatic montage spanning up to 22.6 degrees on the retina was achieved on a cell-to-cell precision with a low misplacement rate of 0.07% (11/16,501 frames) in normal eyes and 0.51% (149/29,051 frames) in eyes with AMD. Substrip based registration significantly improved AOSLO registration accuracy.

A Multi-Scale Fusion and Transformer Based Registration Guided Speckle Noise Reduction for OCT Images.

Optical coherence tomography (OCT) images are inevitably affected by speckle noise because OCT is based on low-coherence interference. Multi-frame averaging is one of the effective methods to reduce speckle noise. Before averaging, the misalignment between images must be calibrated. In this paper, in order to reduce misalignment between images caused during the acquisition, a novel multi-scale fusion and Transformer based (MsFTMorph) method is proposed for deformable retinal OCT image registration. The proposed method captures global connectivity and locality with convolutional vision transformer and also incorporates a multi-resolution fusion strategy for learning the global affine transformation. Comparative experiments with other state-of-the-art registration methods demonstrate that the proposed method achieves higher registration accuracy. Guided by the registration, subsequent multi-frame averaging shows better results in speckle noise reduction. The noise is suppressed while the edges can be preserved. In addition, our proposed method has strong cross-domain generalization, which can be directly applied to images acquired by different scanners with different modes.

Ultra-wide field and new wide field composite retinal image registration with AI-enabled pipeline and 3D distortion correction algorithm

PurposeThis study aimed to compare a new Artificial Intelligence (AI) method to conventional mathematical warping in accurately overlaying peripheral retinal vessels from two different imaging devices: confocal scanning laser ophthalmoscope (cSLO) wide-field images and SLO ultra-wide field images.MethodsImages were captured using the Heidelberg Spectralis 55-degree field-of-view and Optos ultra-wide field. The conventional mathematical warping was performed using Random Sample Consensus—Sample and Consensus sets (RANSAC-SC). This was compared to an AI alignment algorithm based on a one-way forward registration procedure consisting of full Convolutional Neural Networks (CNNs) with Outlier Rejection (OR CNN), as well as an iterative 3D camera pose optimization process (OR CNN + Distortion Correction [DC]). Images were provided in a checkerboard pattern, and peripheral vessels were graded in four quadrants based on alignment to the adjacent box.ResultsA total of 660 boxes were analysed from 55 eyes. Dice scores were compared between the three methods (RANSAC-SC/OR CNN/OR CNN + DC): 0.3341/0.4665/4784 for fold 1-2 and 0.3315/0.4494/4596 for fold 2-1 in composite images. The images composed using the OR CNN + DC have a median rating of 4 (out of 5) versus 2 using RANSAC-SC. The odds of getting a higher grading level are 4.8 times higher using our OR CNN + DC than RANSAC-SC (p < 0.0001).ConclusionPeripheral retinal vessel alignment performed better using our AI algorithm than RANSAC-SC. This may help improve co-localizing retinal anatomy and pathology with our algorithm.

Deformable registration of multimodal retinal images using a weakly supervised deep learning approach

There are different retinal vascular imaging modalities widely used in clinical practice to diagnose different retinal pathologies. The joint analysis of these multimodal images is of increasing interest since each of them provides common and complementary visual information. However, if we want to facilitate the comparison of two images, obtained with different techniques and containing the same retinal region of interest, it will be necessary to make a previous registration of both images. Here, we present a weakly supervised deep learning methodology for robust deformable registration of multimodal retinal images, which is applied to implement a method for the registration of fluorescein angiography (FA) and optical coherence tomography angiography (OCTA) images. This methodology is strongly inspired by VoxelMorph, a general unsupervised deep learning framework of the state of the art for deformable registration of unimodal medical images. The method was evaluated in a public dataset with 172 pairs of FA and superficial plexus OCTA images. The degree of alignment of the common information (blood vessels) and preservation of the non-common information (image background) in the transformed image were measured using the Dice coefficient (DC) and zero-normalized cross-correlation (ZNCC), respectively. The average values of the mentioned metrics, including the standard deviations, were DC = 0.72 ± 0.10 and ZNCC = 0.82 ± 0.04. The time required to obtain each pair of registered images was 0.12 s. These results outperform rigid and deformable registration methods with which our method was compared.

Combining Feature Correspondence With Parametric Chamfer Alignment: Hybrid Two-Stage Registration for Ultra-Widefield Retinal Images.

We propose a novel hybrid framework for registering retinal images in the presence of extreme geometric distortions that are commonly encountered in ultra-widefield (UWF) fluorescein angiography. Our approach consists of two stages: a feature-based global registration and a vessel-based local refinement. For the global registration, we introduce a modified RANSAC (random sample and consensus) that jointly identifies robust matches between feature keypoints in reference and target images and estimates a polynomial geometric transformation consistent with the identified correspondences. Our RANSAC modification particularly improves feature point matching and the registration in peripheral regions that are most severely impacted by the geometric distortions. The second local refinement stage is formulated in our framework as a parametric chamfer alignment for vessel maps obtained using a deep neural network. Because the complete vessel maps contribute to the chamfer alignment, this approach not only improves registration accuracy but also aligns with clinical practice, where vessels are typically a key focus of examinations. We validate the effectiveness of the proposed framework on a new UWF fluorescein angiography (FA) dataset and on the existing narrow-field FIRE (fundus image registration) dataset and demonstrate that it significantly outperforms prior retinal image registration methods in accuracy. The proposed approach enhances the utility of large sets of longitudinal UWF images by enabling: (a) automatic computation of vessel change metrics such as vessel density and caliber, and (b) standardized and co-registered examination that can better highlight changes of clinical interest to physicians.

Retinal OCT Image Registration: Methods and Applications.

Retinal image registration is a critical task in the diagnosis and treatment of various eye diseases. And as a relatively new imaging method, optical coherence tomography (OCT) has been widely used in the diagnosis of retinal diseases. This paper is devoted to retinal OCT image registration methods and their clinical applications. Registration methods including volumetric transformation-based registration methods and image features-based registration methods are systematically reviewed. Furthermore, to better understanding these methods, their applications in correcting scanning artifacts, reducing speckle noise, fusing and splicing images and evaluating longitudinal disease progression are studied as well. At the end of this paper, registration of retina with serious pathology and registration with deep learning technique are also discussed.

Robust Detection Model of Vascular Landmarks for Retinal Image Registration: A Two-Stage Convolutional Neural Network.

Registration is useful for image processing in computer vision. It can be applied to retinal images and provide support for ophthalmologists in tracking disease progression and monitoring therapeutic responses. This study proposed a robust detection model of vascular landmarks to improve the performance of retinal image registration. The proposed model consists of a two-stage convolutional neural network, in which one segments the retinal vessels on a pair of images, and the other detects junction points from the vessel segmentation image. Information obtained from the model was utilized for the registration. The keypoints were extracted based on the acquired vascular landmark points, and the orientation features were calculated as descriptors. Then, the reference and sensed images were registered by matching keypoints using a homography matrix and random sample consensus algorithm. The proposed method was evaluated on five databases and seven evaluation metrics to verify both clinical effectiveness and robustness. The results established that the proposed method showed outstanding performance for registration compared with other state-of-the-art methods. In particular, the high and significantly improved registration results were identified on FIRE database with area under the curve (AUC) of 0.988, 0.511, and 0.803 in S, P, and A classes. Furthermore, the proposed method worked well on poor quality and multimodal datasets demonstrating an ability to achieve high AUC above 0.8.

Retinal fundus image registration framework using Bayesian integration and asymmetric Gaussian mixture model

AbstractRetinal image registration, which is applied in diagnosing and treating eye diseases, plays an important role in medical image analysis. Existing methods suffer from problems due to different imaging viewpoints, times, quality, modalities, and retinal disasters. In this paper, we propose an efficient retinal images registration framework that overcomes these challenges without supervision. We present a layer‐wise matching method to achieve a uniform distribution of features in both image‐space and scale‐space. Then, a novel method called Bayesian integration is generated to accumulate more meaningful inputs. We use the results of different matches as priors, assign a score to each match, and categorize them using a dynamic threshold. Finally, in accordance with previous work, we transform the problem into a probabilistic model, with the asymmetric Gaussian mixture model representing the distribution. A robust estimation is performed on a non‐rigid transformation. The experimental results demonstrate that our proposed framework is robust to kinds of retinal image degradation and produces a more stable and accurate result than state‐of‐the‐art methods.

An O-Shape Neural Network With Attention Modules to Detect Junctions in Biomedical Images Without Segmentation.

Junction plays an important role in biomedical research such as retinal biometric identification, retinal image registration, eye-related disease diagnosis and neuron reconstruction. However, junction detection in original biomedical images is extremely challenging. For example, retinal images contain many tiny blood vessels with complicated structures and low contrast, which makes it challenging to detect junctions. In this paper, we propose an O-shape Network architecture with Attention modules (Attention O-Net), which includes Junction Detection Branch (JDB) and Local Enhancement Branch (LEB) to detect junctions in biomedical images without segmentation. In JDB, the heatmap indicating the probabilities of junctions is estimated and followed by choosing the positions with the local highest value as the junctions, whereas it is challenging to detect junctions when the images contain weak filament signals. Therefore, LEB is constructed to enhance the thin branch foreground and make the network pay more attention to the regions with low contrast, which is helpful to alleviate the imbalance of the foreground between thin and thick branches and to detect the junctions of the thin branch. Furthermore, attention modules are utilized to introduce the feature maps of LEB to JDB, which can establish a complementary relationship and further integrate local features and contextual information between these two branches. The proposed method achieves the highest average F1-scores of 0.82, 0.73 and 0.94 in two retinal datasets and one neuron dataset, respectively. The experimental results confirm that Attention O-Net outperforms other state-of-the-art detection methods, and is helpful for retinal biometric identification.

Self-Supervised Rigid Registration for Multimodal Retinal Images.

The ability to accurately overlay one modality retinal image to another is critical in ophthalmology. Our previous framework achieved the state-of-the-art results for multimodal retinal image registration. However, it requires human-annotated labels due to the supervised approach of the previous work. In this paper, we propose a self-supervised multimodal retina registration method to alleviate the burdens of time and expense to prepare for training data, that is, aiming to automatically register multimodal retinal images without any human annotations. Specially, we focus on registering color fundus images with infrared reflectance and fluorescein angiography images, and compare registration results with several conventional and supervised and unsupervised deep learning methods. From the experimental results, the proposed self-supervised framework achieves a comparable accuracy comparing to the state-of-the-art supervised learning method in terms of registration accuracy and Dice coefficient.

Two-Step Registration on Multi-Modal Retinal Images via Deep Neural Networks.

Multi-modal retinal image registration plays an important role in the ophthalmological diagnosis process. The conventional methods lack robustness in aligning multi-modal images of various imaging qualities. Deep-learning methods have not been widely developed for this task, especially for the coarse-to-fine registration pipeline. To handle this task, we propose a two-step method based on deep convolutional networks, including a coarse alignment step and a fine alignment step. In the coarse alignment step, a global registration matrix is estimated by three sequentially connected networks for vessel segmentation, feature detection and description, and outlier rejection, respectively. In the fine alignment step, a deformable registration network is set up to find pixel-wise correspondence between a target image and a coarsely aligned image from the previous step to further improve the alignment accuracy. Particularly, an unsupervised learning framework is proposed to handle the difficulties of inconsistent modalities and lack of labeled training data for the fine alignment step. The proposed framework first changes multi-modal images into a same modality through modality transformers, and then adopts photometric consistency loss and smoothness loss to train the deformable registration network. The experimental results show that the proposed method achieves state-of-the-art results in Dice metrics and is more robust in challenging cases.

Fundus Image Registration Technique Based on Local Feature of Retinal Vessels

Feature-based retinal fundus image registration (RIR) technique aligns fundus images according to geometrical transformations estimated between feature point correspondences. To ensure accurate registration, the feature points extracted must be from the retinal vessels and throughout the image. However, noises in the fundus image may resemble retinal vessels in local patches. Therefore, this paper introduces a feature extraction method based on a local feature of retinal vessels (CURVE) that incorporates retinal vessels and noises characteristics to accurately extract feature points on retinal vessels and throughout the fundus image. The CURVE performance is tested on CHASE, DRIVE, HRF and STARE datasets and compared with six feature extraction methods used in the existing feature-based RIR techniques. From the experiment, the feature extraction accuracy of CURVE (86.021%) significantly outperformed the existing feature extraction methods (p ≤ 0.001*). Then, CURVE is paired with a scale-invariant feature transform (SIFT) descriptor to test its registration capability on the fundus image registration (FIRE) dataset. Overall, CURVE-SIFT successfully registered 44.030% of the image pairs while the existing feature-based RIR techniques (GDB-ICP, Harris-PIIFD, Ghassabi’s-SIFT, H-M 16, H-M 17 and D-Saddle-HOG) only registered less than 27.612% of the image pairs. The one-way ANOVA analysis showed that CURVE-SIFT significantly outperformed GDB-ICP (p = 0.007*), Harris-PIIFD, Ghassabi’s-SIFT, H-M 16, H-M 17 and D-Saddle-HOG (p ≤ 0.001*).

Perspective Distortion Correction for Multi-Modal Registration between Ultra-Widefield and Narrow-Angle Retinal Images.

Multi-modal retinal image registration between 2D Ultra-Widefield (UWF) and narrow-angle (NA) images has not been well-studied, since most existing methods mainly focus on NA image alignment. The stereographic projection model used in UWF imaging causes strong distortions in peripheral areas, which leads to inferior alignment quality. We propose a distortion correction method that remaps the UWF images based on estimated camera view points of NA images. In addition, we set up a CNN-based registration pipeline for UWF and NA images, which consists of the distortion correction method and three networks for vessel segmentation, feature detection and matching, and outlier rejection. Experimental results on our collected dataset shows the effectiveness of the proposed pipeline and the distortion correction method.

A Convolutional Neural Network Pipeline For Multi-Temporal Retinal Image Registration.

A sequence of images is usually captured to observe the change of health status in medical diagnosis. However, an image sequence taken over year usually suffers from severe deformation, making it time-consuming for physicians to match corresponding patterns. In this paper, we propose a coarse-to-fine pipeline for retinal image registration based on convolutional neural network. By leveraging the three components of the pipeline: feature matching, outlier rejection, and local registration, we recover the deformation and accurately align multi-temporal image sequences. Experimental results show that the proposed network is robust to severe deformation as well as illumination and contrast variations. With the proposed registration pipeline, the change of image patterns over time can be identified through visual analysis.

Hybrid registration of retinal fluorescein angiography and optical coherence tomography images of patients with diabetic retinopathy.

Diabetic retinopathy (DR) is a common ophthalmic disease among diabetic patients. It is essential to diagnose DR in the early stages of treatment. Various imaging systems have been proposed to detect and visualize retina diseases. The fluorescein angiography (FA) imaging technique is now widely used as a gold standard technique to evaluate the clinical manifestations of DR. Optical coherence tomography (OCT) imaging is another technique that provides 3D information of the retinal structure. The FA and OCT images are captured in two different phases and field of views and image fusion of these modalities are of interest to clinicians. This paper proposes a hybrid registration framework based on the extraction and refinement of segmented major blood vessels of retinal images. The newly extracted features significantly improve the success rate of global registration results in the complex blood vessel network of retinal images. Afterward, intensity-based and deformable transformations are utilized to further compensate the motion magnitude between the FA and OCT images. Experimental results of 26 images of the various stages of DR patients indicate that this algorithm yields promising registration and fusion results for clinical routine.