OCT2Former: A retinal OCT-angiography vessel segmentation transformer.

BACKGROUND AND OBJECTIVE: Retinal vessel segmentation plays an important role in the automatic retinal disease screening and diagnosis. How to segment thin vessels and maintain the connectivity of vessels are the key challenges of the retinal vessel segmentation task. Optical coherence tomography angiography (OCTA) is a noninvasive imaging technique that can reveal high-resolution retinal vessels. Aiming at make full use of its characteristic of high resolution, a new end-to-end transformer based network named as OCT2Former (OCT-a Transformer) is proposed to segment retinal vessel accurately in OCTA images. METHODS: The proposed OCT2Former is based on encoder-decoder structure, which mainly includes dynamic transformer encoder and lightweight decoder. Dynamic transformer encoder consists of dynamic token aggregation transformer and auxiliary convolution branch, in which the multi-head dynamic token aggregation attention based dynamic token aggregation transformer is designed to capture the global retinal vessel context information from the first layer throughout the network and the auxiliary convolution branch is proposed to compensate for the lack of inductive bias of the transformer and assist in the efficient feature extraction. A convolution based lightweight decoder is proposed to decode features efficiently and reduce the complexity of the proposed OCT2Former. RESULTS: The proposed OCT2Former is validated on three publicly available datasets i.e. OCTA-SS, ROSE-1, OCTA-500 (subset OCTA-6M and OCTA-3M). The Jaccard indexes of the proposed OCT2Former on these datasets are 0.8344, 0.7855, 0.8099 and 0.8513, respectively, outperforming the best convolution based network 1.43, 1.32, 0.75 and 1.46%, respectively. CONCLUSION: The experimental results have demonstrated that the proposed OCT2Former can achieve competitive performance on retinal OCTA vessel segmentation tasks.

A novel vessel segmentation algorithm for pathological en-face images based on matched filter.

The vascular information in fundus images can provide important basis for detection and prediction of retina-related diseases. However, the presence of lesions such as Coroidal Neovascularization can seriously interfere with normal vascular areas in optical coherence tomography (OCT) fundus images. In this paper, a novel method is proposed for detecting blood vessels in pathological OCT fundus images. First of all, an automatic localization and filling method is used in preprocessing step to reduce pathological interference. Afterwards, in terms of vessel extraction, a pore ablation method based on capillary bundle model is applied. The ablation method processes the image after matched filter feature extraction, which can eliminate the interference caused by diseased blood vessels to a great extent. At the end of the proposed method, morphological operations are used to obtain the main vascular features. Experimental results on the dataset show that the proposed method achieves 0.88 ± 0.03, 0.79 ± 0.05, 0.66 ± 0.04, results in DICE, PRECISION and TPR, respectively. Effective extraction of vascular information from OCT fundus images is of great significance for the diagnosis and treatment of retinal related diseases.

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.

[A heart sound classification method based on complete ensemble empirical modal decomposition with adaptive noise permutation entropy and support vector machine].

Heart sound signal is a kind of physiological signal with nonlinear and nonstationary features. In order to improve the accuracy and efficiency of the phonocardiogram (PCG) classification, a new method was proposed by means of support vector machine (SVM) in which the complete ensemble empirical modal decomposition with adaptive noise (CEEMDAN) permutation entropy was as the eigenvector of heart sound signal. Firstly, the PCG was decomposed by CEEMDAN into a number of intrinsic mode functions (IMFs) from high to low frequency. Secondly, the IMFs were sifted according to the correlation coefficient, energy factor and signal-to-noise ratio. Then the instantaneous frequency was extracted by Hilbert transform, and its permutation entropy was constituted into eigenvector. Finally, the accuracy of the method was verified by using a hundred PCG samples selected from the 2016 PhysioNet/CinC Challenge. The results showed that the accuracy rate of the proposed method could reach up to 87%. In comparison with the traditional EMD and EEMD permutation entropy methods, the accuracy rate was increased by 18%-24%, which demonstrates the efficiency of the proposed method.

Global and Local Feature Reconstruction for Medical Image Segmentation.

Learning how to capture long-range dependencies and restore spatial information of down-sampled feature maps are the basis of the encoder-decoder structure networks in medical image segmentation. U-Net based methods use feature fusion to alleviate these two problems, but the global feature extraction ability and spatial information recovery ability of U-Net are still insufficient. In this paper, we propose a Global Feature Reconstruction (GFR) module to efficiently capture global context features and a Local Feature Reconstruction (LFR) module to dynamically up-sample features, respectively. For the GFR module, we first extract the global features with category representation from the feature map, then use the different level global features to reconstruct features at each location. The GFR module establishes a connection for each pair of feature elements in the entire space from a global perspective and transfers semantic information from the deep layers to the shallow layers. For the LFR module, we use low-level feature maps to guide the up-sampling process of high-level feature maps. Specifically, we use local neighborhoods to reconstruct features to achieve the transfer of spatial information. Based on the encoder-decoder architecture, we propose a Global and Local Feature Reconstruction Network (GLFRNet), in which the GFR modules are applied as skip connections and the LFR modules constitute the decoder path. The proposed GLFRNet is applied to four different medical image segmentation tasks and achieves state-of-the-art performance.

GDCSeg-Net: general optic disc and cup segmentation network for multi-device fundus images.

Accurate segmentation of optic disc (OD) and optic cup (OC) in fundus images is crucial for the analysis of many retinal diseases, such as the screening and diagnosis of glaucoma and atrophy segmentation. Due to domain shift between different datasets caused by different acquisition devices and modes and inadequate training caused by small sample dataset, the existing deep-learning-based OD and OC segmentation networks have poor generalization ability for different fundus image datasets. In this paper, adopting the mixed training strategy based on different datasets for the first time, we propose an encoder-decoder based general OD and OC segmentation network (named as GDCSeg-Net) with the newly designed multi-scale weight-shared attention (MSA) module and densely connected depthwise separable convolution (DSC) module, to effectively overcome these two problems. Experimental results show that our proposed GDCSeg-Net is competitive with other state-of-the-art methods on five different public fundus image datasets, including REFUGE, MESSIDOR, RIM-ONE-R3, Drishti-GS and IDRiD.

OCTRexpert:A Feature-based 3D Registration Method for Retinal OCT Images.

Medical image registration can be used for studying longitudinal and cross-sectional data, quantitatively monitoring disease progression and guiding computer assisted diagnosis and treatments. However, deformable registration which enables more precise and quantitative comparison has not been well developed for retinal optical coherence tomography (OCT) images. This paper proposes a new 3D registration approach for retinal OCT data called OCTRexpert. To the best of our knowledge, the proposed algorithm is the first full 3D registration approach for retinal OCT images which can be applied to longitudinal OCT images for both normal and serious pathological subjects. In this approach, a pre-processing method is first performed to remove eye motion artifact and then a novel design-detection-deformation strategy is applied for the registration. In the design step, a couple of features are designed for each voxel in the image. In the detection step, active voxels are selected and the point-to-point correspondences between the subject and template images are established. In the deformation step, the image is hierarchically deformed according to the detected correspondences in multi-resolution. The proposed method is evaluated on a dataset with longitudinal OCT images from 20 healthy subjects and 4 subjects diagnosed with serious Choroidal Neovascularization (CNV). Experimental results show that the proposed registration algorithm consistently yields statistically significant improvements in both Dice similarity coefficient and the average unsigned surface error compared with the other registration methods.

A Survey of Graph Cuts/Graph Search Based Medical Image Segmentation.

Medical image segmentation is a fundamental and challenging problem for analyzing medical images. Among different existing medical image segmentation methods, graph-based approaches are relatively new and show good features in clinical applications. In the graph-based method, pixels or regions in the original image are interpreted into nodes in a graph. By considering Markov random field to model the contexture information of the image, the medical image segmentation problem can be transformed into a graph-based energy minimization problem. This problem can be solved by the use of minimum s-t cut/ maximum flow algorithm. This review is devoted to cut-based medical segmentation methods, including graph cuts and graph search for region and surface segmentation. Different varieties of cut-based methods, including graph-cuts-based methods, model integrated graph cuts methods, graph-search-based methods, and graph search/graph cuts based methods, are systematically reviewed. Graph cuts and graph search with deep learning technique are also discussed.