Microaneurysms Research Articles

Turnover of Microaneurysms After Intravitreal Injections of Faricimab for Diabetic Macular Edema.

Microaneurysm (MA) plays an important role in the pathogenesis of diabetic macular edema (DME) progression and response to anti-vascular endothelial growth factor (VEGF) therapy. This study aimed to investigate the effect of faricimab, a bispecific antibody against angiopoietin-2 and VEGF, on the number of MAs and their turnover in the treatment of DME. We included that patients with DME who underwent three monthly injections of faricimab in one eye, with the other eye as control. We examined central retinal thickness (CRT) based on optical coherence tomography (OCT) and best-corrected visual acuity. Turnover, including loss and newly formed MAs, and the total number of MAs were counted based on merged images of the OCT map and fluorescein angiography. We enrolled 28 patients with DME. After 3 monthly injections of faricimab, CRT significantly improved, 66.0 ± 16.2% of MAs disappeared, and 6.71 ± 5.6% of new MAs were generated, resulting in total reduction to 40.7 ± 15.2%. In the treated eyes, MA disappearance (P < 0.0001) and turnover (P = 0.007) were significantly greater, and new formation was smaller (P < 0.0001) than in non-treated eyes. The size of the retained MAs decreased after treatment. Microaneurysm turnover was not significantly different between areas with and without edema before treatment. In the process of improving edema in DME with faricimab, MAs shrink and disappear, and formation of MAs are inhibited, resulting in decreased total number of MAs. Intravitreal administration of faricimab suppresses vascular permeability and improves vascular structure.

Automated microaneurysms detection in retinal images using SSA optimised U-NET and Bayesian optimised CNN

ABSTRACT Diabetic retinopathy (DR) is a cause of vision loss and blindness, and early detection of red lesions, particularly microaneurysms (MAs), is crucial to prevent its progression. In this study, we propose an effective deep learning-based DR segmentation and classification method that leverages hyper-parameter optimisation to achieve high detection accuracy. In our proposed method, we first pre-processed retinal images to reduce background variability. Then, we employed a squirrel search optimised bidirectional ConvLSTM U-net with an attention gate for DR segmentation in the main processing step. Finally, we used a Bayesian-optimised Convolutional Neural Network for classification. We selected the optimal architectures for our proposed CNNs and optimised their hyper-parameters using the Bayesian optimisation technique.Our study demonstrates that the proposed CNNs effectively classify diabetic retinopathy in fundus images when model hyper-parameters are tuned with the help of Bayesian optimisation. We conducted statistical tests based on the receiver operating characteristic curve, histogram, and ANOVA test to verify the effectiveness of our suggested models.We proposed a deep learning-based DR segmentation and classification method that leverages hyper-parameter optimisation to achieve high detection accuracy. This study highlights the potential of Bayesian optimisation as an effective technique to optimise hyper-parameters of deep learning networks for disease classification tasks.

Perfused and Nonperfused Microaneurysms Identified and Characterized by Structural and Angiographic OCT

Microaneurysms (MAs) have distinct, oval-shaped, hyperreflective walls on structural OCT, and inconsistent flow signal in the lumen with OCT angiography (OCTA). Their relationship to regional macular edema in diabetic retinopathy (DR) has not been quantitatively explored. Retrospective, cross-sectional study. A total of 99 participants, including 23 with mild, nonproliferative DR (NPDR), 25 with moderate NPDR, 34 with severe NPDR, and 17 with proliferative DR. We obtained 3× 3-mm scans with a commercial device (Solix, Visionix/Optovue) in 99 patients with DR. Trained graders manually identified MAs and their location relative to the anatomic layers from cross-sectional OCT. Microaneurysms were first classified as perfused if flow signal was present in the OCTA channel. Then, perfused MAs were further classified into fully and partially perfused MAs based on the flow characteristics in en face OCTA. The presence of retinal fluid based on OCT near MAs was compared between perfused and nonperfused types. We also compared OCT-based MA detection to fundus photography (FP)- and fluorescein angiography (FA)-based detection. OCT-identified MAs can be classified according to colocalized OCTA flow signal into fully perfused, partially perfused, and nonperfused types. Fully perfused MAs may be more likely to be associated with diabetic macular edema (DME) than those without flow. We identified 308 MAs (166 fully perfused, 88 partially perfused, 54 nonperfused) in 42 eyes using OCT and OCTA. Nearly half of the MAs identified in this study straddle the inner nuclear layer and outer plexiform layer. Compared with partially perfused and nonperfused MAs, fully perfused MAs were more likely to be associated with local retinal fluid. The associated fluid volumes were larger with fully perfused MAs compared with other types. OCT/OCTA detected all MAs found on FP. Although not all MAs seen with FA were identified with OCT, some MAs seen with OCT were not visible with FA or FP. OCT-identified MAs with colocalized flow on OCTA are more likely to be associated with DME than those without flow. Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Retinal vein changes in patients with high-risk proliferative diabetic retinopathy treated with conbercept and panretinal photocoagulation co-therapy: a cohort study.

This study aimed to observe and compare retinal vein diameter changes and other essential indicators in patients with high-risk proliferative diabetic retinopathy (PDR) treated with intravitreal injection of conbercept (IVC) combined with panretinal photocoagulation (PRP) versus PRP monotherapy. A retrospective analysis was conducted on data from patients with high-risk PDR who received specific treatment and were followed up for 24 months. Among 82 patients with high-risk PDR, 50 eyes received PRP combined with IVC, whereas 32 eyes received PRP alone. During the 24-month follow-up period, changes in best-corrected visual acuity (BCVA), central foveal thickness (CFT), retinal vein diameter, number of microaneurysms (MA), neovascularization (NV) area, hard exudate (HE) area, size of the foveal avascular zone (FAZ), superficial capillary plexus (SCP) blood flow density, and adverse effects were recorded and compared between the two groups at baseline and at 6, 12, 18, and 24 months after treatment. The relationship between each observation index and vein diameter was also analyzed. During the 24-month follow up, significant improvements in the BCVA, CFT, retinal vein diameter, number of MAs, NV area, HE area, FAZ, and SCP were observed in the IVC+PRP group after treatment. The PRP group only showed significant reductions in NV and HE areas. The IVC+PRP group showed significant superiority over the PRP group in improving the vein diameter, number of MA, and HE area. However, no statistically significant difference in NV area reduction was found between the groups. In the treatment of high-risk PDR, IVC+PRP therapy has a significant advantage over PRP monotherapy. IVC+PRP therapy may reverse diabetes-induced retinal vein changes, restoring morphology and function.

Diabetic microaneurysms detected by fluorescein angiography spatially correlate with regions of macular ischemia delineated by optical coherence tomography angiography.

To characterize the relationship between diabetic macular ischemia (DMI) delineated by optical coherence tomography angiography (OCTA) and microaneurysms (MAs) identified by fundus fluorescein angiography (FFA). Patients with diabetic retinopathy (DR) who underwent OCTA and FFA were retrospectively identified. FFA images were cropped and aligned with their respective OCTA images using i2k Align Retina software (Dual-Align, Clifton Park, NY, USA). Foveal avascular zone (FAZ) and ischemic areas were manually delineated on OCTA images, and MAs were marked on the corresponding FFA images before overlaying paired scans for analysis (ImageJ; National Institutes of Health, Bethesda, MD, USA). Twenty-eight eyes of 20 patients were included. The average number of MAs identified in cropped FFA images was 127 ± 42. More DMI was noted in the superficial capillary plexus (SCP; 36 ± 13%) compared to the deep capillary plexus (DCP; 28 ± 14%, P < 0.001). Similarly, more MAs were associated with ischemic areas in SCP compared to DCP (92.0 ± 35.0 vs. 76.8 ± 36.5, P < 0.001). Most MAs bordered ischemic areas; fewer than 10% localized inside these regions. As DMI area increased, so did associated MAs (SCP: r = 0.695, P < 0.001; DCP: r = 0.726, P < 0.001). Density of MAs surrounding FAZ (7.7 ± 6.0 MAs/mm2) was similar to other DMI areas (SCP: 7.0 ± 4.0 MAs/mm2, P = 0.478; DCP: 9.2 ± 10.9 MAs/mm2, P = 0.394). MAs identified in FFA strongly associate with, and border areas of, DMI delineated by OCTA. Although more MAs are localized to SCP ischemia, the concentration of MAs associated with DCP ischemia is greater. By contrast, few MAs are present inside low-flow regions, likely because capillary loss is associated with their regression.

Detection and location of microaneurysms in fundus images based on improved YOLOv4 with IFCM

AbstractDiabetic retinopathy (DR) is one of the leading causes of blindness for people suffering from diabetes. Microaneurysm (MA) is the initial symptom of DR. MA is a lesion based disease which starts as small red spots on the retina and increases in size as the DR progresses which finally leads to blindness. So eliminating the lesion can effectively prevent DR at an early stage. However, due to complex retinal structure, different brightness and contrast of fundus images with effects of factors such as different patients, environment changes, and difference in acquisition equipment, it is difficult for existing detection algorithms to achieve accurate results of MA detection and location. Therefore, the detection algorithm of improved YOLOv4 (YOLOv4‐Pro) was proposed. First, an improved Fuzzy C‐Means (IFCM) clustering algorithm was proposed to optimize anchor parameters of target samples to improve matching results between anchors and feature graphs. In order to control noise and improve efficiency, a median filtering method was employed to update the criterion function of the original FCM algorithm, and a K‐means algorithm was employed to initialize clustering. Second, a SENet attention module was added in the backbone of YOLOv4 to enhance key information and suppress background, improving the confidence of MA effectively. Finally, the spatial pyramid pooling (SPP) module was added to the neck to enhance the acceptance domain of the output characteristics of the backbone network, and profits separating of important context information. The improved YOLOv4 with IFCM was verified on the Kaggle DR dataset and compared with other methods. Experimental results show that optimizing the prior frame with the IFCM algorithm can make it suitable to frame the Kaggle DR dataset, which improves the detection accuracy of the network by nearly 5%, and provides a nice performance on detection and location of MA in fundus images. This would help ophthalmologists finding the exact location of MA on retina, thereby simplifying the process and eliminating any manual intervention.

Fine-grained attention & knowledge-based collaborative network for diabetic retinopathy grading

Accurate diabetic retinopathy (DR) grading is crucial for making the proper treatment plan to reduce the damage caused by vision loss. This task is challenging due to the fact that the DR related lesions are often small and subtle in visual differences and intra-class variations. Moreover, relationships between the lesions and the DR levels are complicated. Although many deep learning (DL) DR grading systems have been developed with some success, there are still rooms for grading accuracy improvement. A common issue is that not much medical knowledge was used in these DL DR grading systems. As a result, the grading results are not properly interpreted by ophthalmologists, thus hinder the potential for practical applications. This paper proposes a novel fine-grained attention & knowledge-based collaborative network (FA+KC-Net) to address this concern. The fine-grained attention network dynamically divides the extracted feature maps into smaller patches and effectively captures small image features that are meaningful in the sense of its training from large amount of retinopathy fundus images. The knowledge-based collaborative network extracts a-priori medical knowledge features, i.e., lesions such as the microaneurysms (MAs), soft exudates (SEs), hard exudates (EXs), and hemorrhages (HEs). Finally, decision rules are developed to fuse the DR grading results from the fine-grained network and the knowledge-based collaborative network to make the final grading. Extensive experiments are carried out on four widely-used datasets, the DDR, Messidor, APTOS, and EyePACS to evaluate the efficacy of our method and compare with other state-of-the-art (SOTA) DL models. Simulation results show that proposed FA+KC-Net is accurate and stable, achieves the best performances on the DDR, Messidor, and APTOS datasets.

Quantification of Microvascular Lesions in the Central Retinal Field: Could It Predict the Severity of Diabetic Retinopathy?

Diabetic retinopathy (DR) is a neurodegenerative disease characterized by the presence of microcirculatory lesions. Among them, microaneurysms (MAs) are the first observable hallmark of early ophthalmological changes. The present work aims to study whether the quantification of MAs, hemorrhages (Hmas) and hard exudates (HEs) in the central retinal field could have a predictive value on DR severity. These retinal lesions were quantified in a single field NM-1 of 160 retinographies of diabetic patients from the IOBA's reading center. Samples included different disease severity levels and excluded proliferating forms: no DR (n = 30), mild non-proliferative (n = 30), moderate (n = 50) and severe (n = 50). Quantification of MAs, Hmas, and HEs revealed an increasing trend as DR severity progresses. Differences between severity levels were statistically significant, suggesting that the analysis of the central field provides valuable information on severity level and could be used as a clinical tool to assess DR grading in the eyecare routine. Even though further validation is needed, counting microvascular lesions in a single retinal field can be proposed as a rapid screening system to classify DR patients with different stages of severity according to the international classification.

A Retinal Lesion Detection of Diabetic Retinopathy

Diabetic retinopathy (DR) is the most common cause of vision loss among people with diabetes and leading to the cause of blindness. Microaneurysms (MAs) are primary lesion of Diabetic retinopathy, so their detection can give time to prevent further vision loss. Hemorrhages (HMs) and exudates (EXs) are the other type of lesions occurs during Diabetic retinopathy. The Retinal lesion detection consists of retinal image preprocessing, Optic disc detection and removal, Blood vessel segmentation, Candidate Lesion detection, Feature extraction, Classification and post processing . Publicly available DiaretDB1 dataset is used for performance evaluation.

A Survey on Diabetic Retinopathy Lesion Detection and Segmentation

Diabetes is a global problem which impacts people of all ages. Diabetic retinopathy (DR) is a main ailment of the eyes resulting from diabetes which can result in loss of eyesight if not detected and treated on time. The current process of detecting DR and its progress involves manual examination by experts, which is time-consuming. Extracting the retinal vasculature, and segmentation of the optic disc (OD)/fovea play a significant part in detecting DR. Detecting DR lesions like microaneurysms (MA), hemorrhages (HM), and exudates (EX), helps to establish the current stage of DR. Recently with the advancement in artificial intelligence (AI), and deep learning(DL), which is a division of AI, is widely being used in DR related studies. Our study surveys the latest literature in “DR segmentation and lesion detection from fundus images using DL”.

Navigated direct photocoagulation with a 30-ms short-pulse laser for treating microaneurysms in diabetic macular edema exhibits a high closure rate

This study carried out direct photocoagulation for treating microaneurysms (MAs) in diabetic macular edema (DME) using a navigation laser system with a 30-ms pulse duration. The MA closure rate after 3 months was investigated using pre and postoperative fluorescein angiography images. MAs primarily inside the edematous area based on optical coherence tomography (OCT) maps were selected for treatment, and leaking MAs (n = 1151) were analyzed in 11 eyes (eight patients). The total MA closure rate was 90.1% (1034/1151), and the mean MA closure rate in each eye was 86.5 ± 8.4%. Mean central retinal thickness (CRT) decreased from 471.9 ± 73.0 μm to 420.0 ± 87.5 μm (P = 0.049), and there was a correlation between the MA closure rate and the CRT reduction rate (r = 0.63, P = 0.037). There was no difference in the MA closure rate depending on the degree of edema thickness based on a false-color topographic OCT map image. Direct photocoagulation for DME with a short pulse using the navigated photocoagulator resulted in a high MA closure rate in just 3 months and a corresponding improvement in retinal thickness. These findings encourage the use of a new therapeutic approach for DME.

Automatic detection of microaneurysms in fundus images based on multiple preprocessing fusion to extract features

Diabetic retinopathy (DR) is the main cause of new cases of blindness, and retinal microaneurysm (MA) is one of the early clinical manifestations of DR. However, it is difficult to directly observe MA with naked eyes because of their small size and poor contrast with the surrounding background. This paper presents a new method for automatic detection of MAs from fundus images. It mainly includes four steps: image preprocessing, candidate region extraction, feature extraction and classification. At the stage of feature extraction, different from traditional methods, we propose a feature extraction method based on multi-preprocessing fusion. In this paper, features are extracted from the original green channel image and the original gray image respectively, and then different processing methods are used to extract the same features from multiple pre-processed images. Finally, the extracted features are classified by multi-layer perceptron (MLP) classifier to determine whether the candidate object is microaneurysm (MA). The method is evaluated on e-ophtha-MA database and achieved high sensitivity. Using the FROC (free-response ROC) indicator, the detection achieves the F-score, accuracy, sensitivity, specificity and AUC (area under the curve) of 0.507, 0.940, 0.870, 0.938 and 0.9821, respectively, compared to the most advanced methods available. The proposed method of multi-preprocessing and fusion feature extraction is beneficial to classification and improves the detection performance.

Microaneurysms detection in retinal fundus images based on shape constraint with region-context features

Microaneurysms (MAs) are the earliest lesions diabetic retinopathy (DR), and the accurate MA detection can assist in early diagnosis of diabetes. Many effective detection techniques have been proposed recently, the interference of blood vessels and blurry boundaries of MAs reduce the performance of these methods. To address these problems, this paper proposes an accurate MA detection method. In the candidate detection stage, a shape suppression filter is proposed to remove strip-shaped blood vessels and retain the dark blobs. In order to enhance blurry boundaries of MAs, we apply the additive bias correction level set to locate circular regions. In the next stage of feature extraction, a new set of features based on gray level co-occurrence matrix (GLCM) is extracted for each candidate to discriminate the MAs from non-MAs candidates using the random undersampling boosting (RUSBoost) classifier. We test our method on four public datasets, resulting in the optimal performance to the existing methods. It achieves average sensitivity values of 0.672, 0.721, 0.602 and 0.735, respectively.

Microperimetric analysis of diabetic macular edema after navigated direct photocoagulation with short-pulse laser for microaneurysms

BackgroundFocal laser photocoagulation is an important treatment option for diabetic macular edema (DME). This study aimed to examine the retinal sensitivity (RS) and morphological changes at the coagulated site after direct photocoagulation of microaneurysms (MAs) in patients with DME using a navigated laser photocoagulator with a short-pulse duration of 30 ms.MethodsImages of early-phase fluorescein angiography were merged with images from the optical coherence tomography (OCT) map with 9 Early Treatment Diabetic Retinopathy Study grid circles, and MAs inside the edema area were selected for direct photocoagulation. The best-corrected visual acuity (BCVA), parameters of the OCT map including central retinal thickness and retinal thickness in edema range, central RS, and RS in the edema area were assessed at 1 and 3 months after the laser treatment. The RS points that overlapped with the laser spots were identified by merging the Navilas’ digital treatment reports and the microperimetry images.ResultsSeventeen eyes from 14 patients were studied. The mean retinal thickness in the edema range decreased at 3 months compared with pretreatment (P = 0.042), but the BCVA, central retinal thickness, central RS, and RS in the edema area remained unchanged. Overall, 32 of 400 sensitivity points overlapped with the laser-coagulated spots. The mean RS at these spots were 22.4 ± 5.3 dB at 1 month and 22.5 ± 4.8 dB at 3 months, with no significant change from the baseline of 22.7 ± 3.5 dB.ConclusionsRetinal thickness improved in the coagulated edema area without a decrease in RS after direct photocoagulation of MAs with a short 30-ms pulse using Navilas. This promising therapeutic strategy for DME is effective and minimally invasive.

Role of Microaneurysms in the Pathogenesis and Therapy of Diabetic Macular Edema: A Descriptive Review

Background and Objectives: This study aims to elucidate the role of microaneurysms (MAs) in the pathogenesis and treatment of diabetic retinopathy (DR) and diabetic macular edema (DME), the major causes of acquired visual impairment. Materials and Methods: We synthesized the relevance of findings on the clinical characteristics, pathogenesis, and etiology of MAs in DR and DME and their role in anti-vascular endothelial growth factor (VEGF) therapy. Results: MAs, a characteristic feature in DR and DME, can be detected by fluorescein angiography, optical coherence tomography (OCT) and OCT angiography. These instrumental analyses demonstrated a geographic and functional association between MA and ischemic areas. MA turnover, the production and loss of MA, reflects the activity of DME and DR. Several cytokines are involved in the pathogenesis of MAs, which is characterized by pericyte loss and endothelial cell proliferation in a VEGF-dependent or -independent manner. Ischemia and MAs localized in the deep retinal layers are characteristic of refractory DME cases. Even in the current anti-VEGF era, laser photocoagulation targeting MAs in the focal residual edema is still an effective therapeutic tool, but it is necessary to be creative in accurately identifying the location of MAs and performing highly precise and minimally invasive coagulation. Conclusions: MAs play a distinctive and important role in the pathogenesis of the onset, progression of DR and DME, and response to anti-VEGF treatment. Further research on MA is significant not only for understanding the pathogenesis of DME but also for improving the effectiveness of treatment.

Prognostic Imaging Biomarkers in Diabetic Macular Edema Eyes Treated with Intravitreal Dexamethasone Implant

The aim was to evaluate predictive value of baseline optical coherence tomography (OCT) and OCT angiography (OCTA) parameters in diabetic macular edema (DME) treated with dexamethasone implant (DEXi). OCT and OCTA parameters were collected: central macular thickness (CMT), vitreomacular abnormalities (VMIAs), intraretinal and subretinal fluid (mixed DME pattern), hyper-reflective foci (HRF), microaneurysms (MAs) reflectivity, ellipsoid zone disruption, suspended scattering particles in motion (SSPiM), perfusion density (PD), vessel length density, and foveal avascular zone. Responders' (RES) and non-responders' (n-RES) eyes were classified considering morphological (CMT reduction ≥ 10%) and functional (BCVA change ≥ 5 ETDRS letters) changes after DEXi. Binary logistic regression OCT, OCTA, and OCT/OCTA-based models were developed. Thirty-four DME eyes were enrolled (18 treatment-naïve). OCT-based model combining DME mixed pattern + MAs + HRF and OCTA-based model combining SSPiM and PD showed the best performance to correctly classify the morphological RES eyes. In the treatment-naïve eyes, VMIAs were included with a perfect fit for n-RES eyes. The presence of DME mixed pattern, a high number of parafoveal HRF, hyper-reflective MAs, SSPiM in the outer nuclear layers, and high PD represent baseline predictive biomarkers for DEXi treatment responsiveness. The application of these models to treatment-naïve patients allowed a good identification of n-RES eyes.

Longitudinal Quantitative Ultrawide-field Fluorescein Angiography Dynamics in the RUBY Diabetic Macular Edema Study

The purpose of this study was to evaluate the longitudinal change in quantitative ultrawide-field angiographic (UWFA) parameters and correlate them with functional outcomes and spectral domain-OCT metrics. This study is a post hoc analysis of the phase II RUBY study: a prospective, randomized trial of patients with diabetic macular edema (DME) treated with either intravitreal aflibercept injection (IAI) or combined IAI/nesvacumab (antiangiopoietin 2 mAb). Subjects with DME that underwent UWFA across all treatment groups (n= 44). A machine learning-enabled feature extraction system generated panretinal quantitative UWFA metrics, including leakage, ischemia, and microaneurysm (MA) burden. Zonal assessments were performed corresponding to the macula, midperiphery, and far periphery. Changes in ischemic area and index (proportion of nonperfusion in analyzable retina), leakage area and index (proportion of leakage in analyzable retina), and MA count at baseline, week 12, week 24, and week 36 were analyzed. Spectral-domain-OCT quantitative metrics, such as central subfield thickness, ellipsoid zone (EZ) integrity parameters, intraretinal fluid (IRF) volume, and subretinal fluid (SRF) volume were extracted via a machine learning-enhanced OCT feature extraction platform and analyzed. Additionally, the effect of these changes on best-corrected visual acuity (BCVA) was evaluated. Mean panretinal leakage index, zonal leakage area, and panretinal MA count improved significantly between baseline and week 36. Panretinal ischemic index decreased between baseline and week 36, with some aspects showing significant improvement. Mean BCVA significantly improved from baseline to week 36. There was a significant inverse correlation between change in BCVA and change in macular leakage area. A direct correlation was observed between both baseline macular leakage area and panretinal leakage index with IRF volume, SRF volume, and EZ disruption on OCT. Assessment of UWFA parameters demonstrates a significant improvement in panretinal leakage index, leakage area, and MA burden in eyes treated with IAI with or without nesvacumab. A numeric reduction in panretinal ischemic index and area was noted. The analysis also shows the critical association of leakage with visual and OCT features. This highlights the potential role of UWFA in disease burden assessment, with leakage parameters serving as a primary end point. Proprietary or commercial disclosure may be found after the references.

MCA-UNet: multi-scale cross co-attentional U-Net for automatic medical image segmentation.

Medical image segmentation is a challenging task due to the high variation in shape, size and position of infections or lesions in medical images. It is necessary to construct multi-scale representations to capture image contents from different scales. However, it is still challenging for U-Net with a simple skip connection to model the global multi-scale context. To overcome it, we proposed a dense skip-connection with cross co-attention in U-Net to solve the semantic gaps for an accurate automatic medical image segmentation. We name our method MCA-UNet, which enjoys two benefits: (1) it has a strong ability to model the multi-scale features, and (2) it jointly explores the spatial and channel attentions. The experimental results on the COVID-19 and IDRiD datasets suggest that our MCA-UNet produces more precise segmentation performance for the consolidation, ground-glass opacity (GGO), microaneurysms (MA) and hard exudates (EX). The source code of this work will be released via https://github.com/McGregorWwww/MCA-UNet/.

T-Net: Hierarchical Pyramid Network for Microaneurysm Detection in Retinal Fundus Image

The mainstream techniques to detect microaneurysm in medical images involve the use of stacked convolutional neural networks. But these techniques can not provide adequate detecting performance for the MA scenarios with limited information and different sizes. In this article, a hierarchical pyramid network with a ‘T’ structure is proposed to detect microaneurysms (MAs) in retinal fundus images, which can overcome the difficulties caused by the above scenarios.We design a data preparation technique that can adaptively compute the best receptive fields of MAs to generate various patch sizes, resulting in multi-size datasets for training. The ‘T’ network consists of two pyramid feature extractors, rather than a deep network to adequately extract features of MAs and avoid feature loss caused by deep layers. Experiments on five public retinal datasets demonstrate that our method achieves the state-of-the-art performance.

Anatomical changes in the retinal capillary plexuses assessed by optical coherence tomography angiography in diabetic patients

AbstractPurpose: To assess anatomical changes in the retinal superficial capillary (SCP) and deep capillary (PCP) plexuses, as well as choriocapillary (CC) in patients with diabetes mellitus (DM) without diabetic retinopathy (DR), and in DM patients with mild and moderate DR without diabetic macular edema (DME) using optical coherence tomography angiography (OCTA).Methods: Ninety eyes were included, 34 patients with long‐term DM (more than 10 years) but without DR signs, and 54 patients with mild or moderate DR (levels 35 and 43 on the ETDRS scale) without DME. All participants underwent a complete ophthalmic examination including best corrected visual acuity (BCVA) and OCTA examination using deep‐range imaging with the DRI‐Triton SS‐OCT.Results: The mean age was 63.82 ± 8.56 years and 63.00 ± 13.21 years in long‐term DM without DR and with DR, respectively. In patients with long‐term DM without DR, foveal avascular zone (FAZ) abnormalities were seen in both SCP and DCP (55% and 5%), and microaneurysms (MAs) were present in SCP and DCP (35% and 47.5%). Loss of perfusion was detected in SCP and DCP (30% and 47.5%), and ischemia was observed in SCP, DCP and CC (60%, 37.5% and 10%). In patients with mild or moderate DR without DME, OCTA also detected morphological abnormalities such as FAZ changes and MAs (79.6% and 81.11%), loss of perfusion (83.3% and 64.2%), and ischemia (66.67%, 81.1% and 18.5%) in SCP, DCP and CC respectively. Microvascular tortuosity and intraretinal microvascular anomalies (IRMAs) were detected in 48.1% and 46.3% in SCP vs 22.6% and 20.8% in DCP, respectively.Conclusions: Patients with long‐term DM without DR present morphological changes measured with OCTA, such as MAs in both retinal plexuses. The changes in the FAZ are more evident in the SCP due to the capillary anastomosis. Capillary dropout can be found in both plexuses. Patients with DR show more evident changes that include MAs, loss of perfusion and ischemia and other vascular abnormalities.