Computational investigation of blood cell transport in retinal microaneurysms.

Microaneurysms (MAs) are one of the earliest clinically visible signs of diabetic retinopathy (DR). MA leakage or rupture may precipitate local pathology in the surrounding neural retina that impacts visual function. Thrombosis in MAs may affect their turnover time, an indicator associated with visual and anatomic outcomes in the diabetic eyes. In this work, we perform computational modeling of blood flow in microchannels containing various MAs to investigate the pathologies of MAs in DR. The particle-based model employed in this study can explicitly represent red blood cells (RBCs) and platelets as well as their interaction in the blood flow, a process that is very difficult to observe in vivo. Our simulations illustrate that while the main blood flow from the parent vessels can perfuse the entire lumen of MAs with small body-to-neck ratio (BNR), it can only perfuse part of the lumen in MAs with large BNR, particularly at a low hematocrit level, leading to possible hypoxic conditions inside MAs. We also quantify the impacts of the size of MAs, blood flow velocity, hematocrit and RBC stiffness and adhesion on the likelihood of platelets entering MAs as well as their residence time inside, two factors that are thought to be associated with thrombus formation in MAs. Our results show that enlarged MA size, increased blood velocity and hematocrit in the parent vessel of MAs as well as the RBC-RBC adhesion promote the migration of platelets into MAs and also prolong their residence time, thereby increasing the propensity of thrombosis within MAs. Overall, our work suggests that computational simulations using particle-based models can help to understand the microvascular pathology pertaining to MAs in DR and provide insights to stimulate and steer new experimental and computational studies in this area.

Automatic Detection of Microaneurysms in Fundus Images Using an Ensemble-Based Segmentation Method.

In this study, a novel method for automatic microaneurysm detection in color fundus images is presented. The proposed method is based on three main steps: (1) image breakdown to smaller image patches, (2) inference to segmentation models, and (3) reconstruction of the predicted segmentation map from output patches. The proposed segmentation method is based on an ensemble of three individual deep networks, such as U-Net, ResNet34-UNet and UNet++. The performance evaluation is based on the calculation of the Dice score and IoU values. The ensemble-based model achieved higher Dice score (0.95) and IoU (0.91) values compared to other network architectures. The proposed ensemble-based model demonstrates the high practical application potential for detection of early-stage diabetic retinopathy in color fundus images.

Deep Learning Approach for Automatic Microaneurysms Detection.

In diabetic retinopathy (DR), the early signs that may lead the eyesight towards complete vision loss are considered as microaneurysms (MAs). The shape of these MAs is almost circular, and they have a darkish color and are tiny in size, which means they may be missed by manual analysis of ophthalmologists. In this case, accurate early detection of microaneurysms is helpful to cure DR before non-reversible blindness. In the proposed method, early detection of MAs is performed using a hybrid feature embedding approach of pre-trained CNN models, named as VGG-19 and Inception-v3. The performance of the proposed approach was evaluated using publicly available datasets, namely "E-Ophtha" and "DIARETDB1", and achieved 96% and 94% classification accuracy, respectively. Furthermore, the developed approach outperformed the state-of-the-art approaches in terms of sensitivity and specificity for microaneurysms detection.

[Detection of microaneurysms in fundus images based on improved YOLOv4 with SENet embedded].

Microaneurysm is the initial symptom of diabetic retinopathy. Eliminating this lesion can effectively prevent diabetic retinopathy in the early stage. However, due to the complex retinal structure and the different brightness and contrast of fundus image because of different factors such as patients, environment and acquisition equipment, the existing detection algorithms are difficult to achieve the accurate detection and location of the lesion. Therefore, an improved detection algorithm of you only look once (YOLO) v4 with Squeeze-and-Excitation networks (SENet) embedded was proposed. Firstly, an improved and fast fuzzy c-means clustering algorithm was used to optimize the anchor parameters of the target samples to improve the matching degree between the anchors and the feature graphs; Then, the SENet attention module was embedded in the backbone network to enhance the key information of the image and suppress the background information of the image, so as to improve the confidence of microaneurysms; In addition, an spatial pyramid pooling was added to the network neck to enhance the acceptance domain of the output characteristics of the backbone network, so as to help separate important context information; Finally, the model was verified on the Kaggle diabetic retinopathy dataset and compared with other methods. The experimental results showed that compared with other YOLOv4 network models with various structures, the improved YOLOv4 network model could significantly improve the automatic detection results such as F-score which increased by 12.68%; Compared with other network models and methods, the automatic detection accuracy of the improved YOLOv4 network model with SENet embedded was obviously better, and accurate positioning could be realized. Therefore, the proposed YOLOv4 algorithm with SENet embedded has better performance, and can accurately and effectively detect and locate microaneurysms in fundus images.

[Microaneurysms as a biomarker of diabetic retinopathy]. / Mikroanevrizmy kak marker diabeticheskoi retinopatii.

Diabetic retinopathy is a microvascular pathology, which is the most common complication of diabetes mellitus. Improvement of instrumental diagnostics of retinal pathologies has contributed to identification of various phenotypes of the progression of ocular fundus pathology in diabetes based on specific changes in the retina - biomarkers. In particular, microaneurysms initially described in diabetes, which are a manifestation of a wide range of systemic pathologies and retinal diseases, are an indicator of the severity of diabetic retinopathy. Dynamic changes in the number of microaneurysms are a confirmed prognostic biomarker of clinically significant macular edema. In diabetic retinopathy, microaneurysms are one of the earliest recognizable signs, and the dynamic of their formation and disappearance may serve as a predictor for the disease progression. This literature review presents the characteristics of microaneurysms based on various imaging techniques, and analyses the link between structural features and dynamic changes in microaneurysms, and progression of diabetic retinopathy.

Microaneurysms detection in color fundus images using machine learning based on directional local contrast.

BACKGROUND: As one of the major complications of diabetes, diabetic retinopathy (DR) is a leading cause of visual impairment and blindness due to delayed diagnosis and intervention. Microaneurysms appear as the earliest symptom of DR. Accurate and reliable detection of microaneurysms in color fundus images has great importance for DR screening. METHODS: A microaneurysms' detection method using machine learning based on directional local contrast (DLC) is proposed for the early diagnosis of DR. First, blood vessels were enhanced and segmented using improved enhancement function based on analyzing eigenvalues of Hessian matrix. Next, with blood vessels excluded, microaneurysm candidate regions were obtained using shape characteristics and connected components analysis. After image segmented to patches, the features of each microaneurysm candidate patch were extracted, and each candidate patch was classified into microaneurysm or non-microaneurysm. The main contributions of our study are (1) making use of directional local contrast in microaneurysms' detection for the first time, which does make sense for better microaneurysms' classification. (2) Applying three different machine learning techniques for classification and comparing their performance for microaneurysms' detection. The proposed algorithm was trained and tested on e-ophtha MA database, and further tested on another independent DIARETDB1 database. Results of microaneurysms' detection on the two databases were evaluated on lesion level and compared with existing algorithms. RESULTS: The proposed method has achieved better performance compared with existing algorithms on accuracy and computation time. On e-ophtha MA and DIARETDB1 databases, the area under curve (AUC) of receiver operating characteristic (ROC) curve was 0.87 and 0.86, respectively. The free-response ROC (FROC) score on the two databases was 0.374 and 0.210, respectively. The computation time per image with resolution of 2544×1969, 1400×960 and 1500×1152 is 29 s, 3 s and 2.6 s, respectively. CONCLUSIONS: The proposed method using machine learning based on directional local contrast of image patches can effectively detect microaneurysms in color fundus images and provide an effective scientific basis for early clinical DR diagnosis.

Retinopathy Analysis Based on Deep Convolution Neural Network.

At medical checkups or mass screenings, the fundus examination is effective for early detection of systemic hypertension, arteriosclerosis, diabetic retinopathy, etc. In most cases, ophthalmologists and physicians grade retinal images by the condition of the blood vessels, lesions. However, human observation does not provide quantitative results, thus blood vessel analysis is an important process in determining hypertension and arteriosclerosis, quantitatively. This chapter describes the latest automated blood vessel extraction using the deep convolution neural network (DCNN). Diabetic retinopathy is a common cardiovascular disease and a major factor in blindness. Therefore, early detection of diabetic retinopathy is very important to preventing blindness. A microaneurysm is an initial sign of diabetic retinopathy, and much research has been conducted for microaneurysm detection. This chapter also describes diabetic retinopathy detection and automated microaneurysm detection using the DCNN.

Secondary Observer System for Detection of Microaneurysms in Fundus Images Using Texture Descriptors.

The increase of diabetic retinopathy patients and diabetic mellitus worldwide yields lot of challenges to ophthalmologists in the screening of diabetic retinopathy. Different signs of diabetic retinopathy were identified in retinal images taken through fundus photography. Among these stages, the early stage of diabetic retinopathy termed as microaneurysms plays a vital role in diabetic retinopathy patients. To assist the ophthalmologists, and to avoid vision loss among diabetic retinopathy patients, a computer-aided diagnosis is essential that can be used as a second opinion while screening diabetic retinopathy. On this vision, a new methodology is proposed to detect the microaneurysms and non-microaneurysms through the stages of image pre-processing, candidate extraction, feature extraction, and classification. The feature extractor, generalized rotational invariant local binary pattern, contributes in extracting the texture-based features of microaneurysms. As a result, our proposed system achieved a free-response receiver operating characteristic score of 0.421 with Retinopathy Online Challenge database.

Microaneurysm detection in fundus images using a two-step convolutional neural network.

BACKGROUND AND OBJECTIVES: Diabetic retinopathy (DR) is the leading cause of blindness worldwide, and therefore its early detection is important in order to reduce disease-related eye injuries. DR is diagnosed by inspecting fundus images. Since microaneurysms (MA) are one of the main symptoms of the disease, distinguishing this complication within the fundus images facilitates early DR detection. In this paper, an automatic analysis of retinal images using convolutional neural network (CNN) is presented. METHODS: Our method incorporates a novel technique utilizing a two-stage process with two online datasets which results in accurate detection while solving the imbalance data problem and decreasing training time in comparison with previous studies. We have implemented our proposed CNNs using the Keras library. RESULTS: In order to evaluate our proposed method, an experiment was conducted on two standard publicly available datasets, i.e., Retinopathy Online Challenge dataset and E-Ophtha-MA dataset. Our results demonstrated a promising sensitivity value of about 0.8 for an average of >6 false positives per image, which is competitive with state of the art approaches. CONCLUSION: Our method indicates significant improvement in MA-detection using retinal fundus images for monitoring diabetic retinopathy.

THREE-DIMENSIONAL ANALYSIS OF RETINAL MICROANEURYSMS WITH ADAPTIVE OPTICS OPTICAL COHERENCE TOMOGRAPHY.

PURPOSE: To characterize retinal microaneurysms (MAs) in patients with diabetes using adaptive optics optical coherence tomography (AOOCT) and compare details found in AOOCT with those found in commercially available retinal imaging techniques. METHODS: Patients with diabetes and MA in the macular area were included in this pilot study. The area of interest, identified in standard fluorescein angiography, was imaged using an AO fundus camera and AOOCT. Microaneurysms were characterized in AOOCT (visibility, reflectivity, feeding/draining vessels, and intraretinal location) and compared with findings in AO fundus camera, OCT angiography, and fluorescein angiography. RESULTS: Fifty-three MAs were imaged in 15 eyes of 10 patients. Feeding and/or draining vessels from both capillary plexus could be identified in 34 MAs in AOOCT images. Of 45 MAs imaged with OCT angiography, 18 (40%) were visible in the superior plexus, 12 (27%) in the deep capillary plexus, and 15 MAs (33%) could not be identified at all. Intraluminal hyperreflectivity, commonly seen in AO fundus camera, corresponded only in 8 of 27 cases (30%) to intraluminal densities seen in AOOCT. CONCLUSION: Adaptive optics OCT imaging revealed that MAs located in the inner nuclear layer were connected to the intermediate and/or deep capillary plexus. Intraluminal hyperreflectivity seen on AO fundus camera images originated from a strong reflection from the vessel wall and only in a third of the cases from intraluminal clots. Currently, AOOCT is the most expedient in vivo imaging method to capture morphologic details of retinal microvasculature in 3D and in the context of the surrounding retinal anatomy.

Distinguising Proof of Diabetic Retinopathy Detection by Hybrid Approaches in Two Dimensional Retinal Fundus Images.

Diabetes is characterized by constant high level of blood glucose. The human body needs to maintain insulin at very constrict range. The patients who are all affected by diabetes for a long time affected by eye disease called Diabetic Retinopathy (DR). The retinal landmarks namely Optic disc is predicted and masked to decrease the false positive in the exudates detection. The abnormalities like Exudates, Microaneurysms and Hemorrhages are segmented to classify the various stages of DR. The proposed approach is employed to separate the landmarks of retina and lesions of retina for the classification of stages of DR. The segmentation algorithms like Gabor double-sided hysteresis thresholding, maximum intensity variation, inverse surface adaptive thresholding, multi-agent approach and toboggan segmentation are used to detect and segment BVs, ODs, EXs, MAs and HAs. The feature vector formation and machine learning algorithm used to classify the various stages of DR are evaluated using images available in various retinal databases, and their performance measures are presented in this paper.

Spontaneous liver rupture secondary to distal right hepatic artery microaneurysms in a patient admitted due to Staphylococcus aureus pneumonia.

Spontaneous liver rupture is an uncommon and life-threatening condition often associated with high mortality rate. The most common causes are preeclampsia and HELLP syndrome during pregnancy, liver tumours and overdosing of anticoagulant therapy, however, hepatic rupture in the absence of underlying pathology is an extremely rare occurrence. Treatment can include observation, embolization, hepatic artery ligation, hepatic lobectomy, hematoma evacuation and packing, and even liver transplantation has been described.

Fundus images analysis using deep features for detection of exudates, hemorrhages and microaneurysms.

BACKGROUND: Convolution neural networks have been considered for automatic analysis of fundus images to detect signs of diabetic retinopathy but suffer from low sensitivity. METHODS: This study has proposed an alternate method using probabilistic output from Convolution neural network to automatically and simultaneously detect exudates, hemorrhages and microaneurysms. The method was evaluated using two approaches: patch and image-based analysis of the fundus images on two public databases: DIARETDB1 and e-Ophtha. The novelty of the proposed method is that the images were analyzed using probability maps generated by score values of the softmax layer instead of the use of the binary output. RESULTS: The sensitivity of the proposed approach was 0.96, 0.84 and 0.85 for detection of exudates, hemorrhages and microaneurysms, respectively when considering patch-based analysis. The results show overall accuracy for DIARETDB1 was 97.3% and 86.6% for e-Ophtha. The error rate for image-based analysis was also significantly reduced when compared with other works. CONCLUSION: The proposed method provides the framework for convolution neural network-based analysis of fundus images to identify exudates, hemorrhages, and microaneurysms. It obtained accuracy and sensitivity which were significantly better than the reported studies and makes it suitable for automatic diabetic retinopathy signs detection.

Statistical Geometrical Features for Microaneurysm Detection.

Automated microaneurysm (MA) detection is still an open challenge due to its small size and similarity with blood vessels. In this paper, we present a novel method which is simple, efficient, and real-time for segmenting and detecting MA in color fundus images (CFI). To do this, a novel set of features based on statistics of geometrical properties of connected regions, that can easily discriminate lesion and non-lesion pixels are used. For large-scale evaluation proposed method is validated on DIARETDB1, ROC, STARE, and MESSIDOR dataset. It proves robust with respect to different image characteristics and camera settings. The best performance was achieved on per-image evaluation on DIARETDB1 dataset with sensitivity of 88.09 at 92.65% specificity which is quite encouraging for clinical use.

Endovascular Management of Microcerebral Aneurysms with Diameter Smaller than 3 mm: Is It Feasible and Safe?

BACKGROUND: The neurosurgical management of microcerebral aneurysms with diameter smaller than 3 mm remains a great challenge as many complications can occur. AIM: Our target was to assess the efficacy and usefulness of endovascular treatment of these lesions. METHODS: We did a prospective and retrospective gathering of the results of endovascular treatments for a group of 16 patients with 16 microcerebral aneurysms. Four patients were treated by direct coil embolization, and 12 patients were managed by remodeling techniques. RESULTS: Coil embolization was technically accessible in all cases. Initial complete occlusion is achieved in 12 patients. We did not face major technical complications such as aneurysmal rupture or coil migration during the endovascular management in 15 patients. Only in 1 case the second and last coil (2/1 mm) migrated distally and could not be retrieved. In this case clinical evidence of neurologic deterioration and weakness in left lower limb due to right anterior cerebral artery territory stroke was evidenced in the follow-up computed tomography scan. Follow-up clinical and radiological studies were available for 9 of 12 surviving patients and showed complete occlusion in 7 cases, and in 1 case aneurysm tiny recanalization was demonstrated after 1 year, which was retreated with complete occlusion, and in another case tiny aneurysm recanalization at the neck appeared after 2 years, which was left under observation. CONCLUSIONS: Endovascular treatment is a beneficial and effective therapeutic alternative to microsurgery for microaneurysms. The long-term assessment of endovascular management for these lesions was not included in that study.

Neurofibromatosis 1 and massive hemothorax: a fatal combination.

Type 1 neurofibromatosis (NF 1), a rare genetic disease with autosomal dominant transmission, has typical dermatologic manifestations with pathognomonic Lisch nodules, and is rarely known for vascular alterations. Among these, aneurysmal dilatation is the most common form. We report a fatal case of massive hemothorax due to a spontaneous rupture of the left pulmonary artery branch micro-aneurysm in a NF 1 patient. Indeed, spontaneous rupture of these pathologic vessels is very rare in clinical practice and the literature, but, for its potentially life-threatening complications, there is the need for it to be taken into account in differential diagnosis. The origin of bleeding was first confirmed by computed tomography angiography (CTA). The patient's condition worsened suddenly leading to pulmonary hemorrhage and death. A clinical autopsy was required to assess the definitive cause of death.

Higher skin autofluorescence in young people with Type 1 diabetes and microvascular complications.

AIM: To test the hypothesis that non-invasive skin autofluorescence, a measure of advanced glycation end products, would provide a surrogate measure of long-term glycaemia and be associated with early markers of microvascular complications in adolescents with Type 1 diabetes. METHODS: Forearm skin autofluorescence (arbitrary units) was measured in a cross-sectional study of 135 adolescents with Type 1 diabetes [mean ± sd age 15.6 ± 2.1 years, diabetes duration 8.7 ± 3.5 years, HbA1c 72 ± 16 mmol/mol (8.7 ± 1.5%)]. Retinopathy, assessed using seven-field stereoscopic fundal photography, was defined as ≥1 microaneurysm or haemorrhage. Cardiac autonomic function was measured by standard deviation of consecutive RR intervals on a 10-min continuous electrocardiogram recording, as a measure of heart rate variability. RESULTS: Skin autofluorescence was significantly associated with age (R2 = 0.15; P < 0.001). Age- and gender-adjusted skin autofluorescence was associated with concurrent HbA1c (R2 = 0.32; P < 0.001) and HbA1c over the previous 2.5-10 years (R2 = 0.34-0.43; P < 0.002). Age- and gender-adjusted mean skin autofluorescence was higher in adolescents with retinopathy vs those without retinopathy [mean 1.38 (95% CI 1.29, 1.48) vs 1.22 (95% CI 1.17, 1.26) arbitrary units; P = 0.002]. In multivariable analysis, retinopathy was significantly associated with skin autofluorescence, adjusted for duration (R2 = 0.19; P = 0.03). Cardiac autonomic dysfunction was also independently associated with skin autofluorescence (R2 = 0.11; P = 0.006). CONCLUSIONS: Higher skin autofluorescence is associated with retinopathy and cardiac autonomic dysfunction in adolescents with Type 1 diabetes. The relationship between skin autofluorescence and previous glycaemia may provide insight into metabolic memory. Longitudinal studies will determine the utility of skin autofluorescence as a non-invasive screening tool to predict future microvascular complications.

Automatic detection of microaneurysms in diabetic retinopathy fundus images using the L*a*b color space.

We develop an automated image processing system for detecting microaneurysm (MA) in diabetic patients. Diabetic retinopathy is one of the main causes of preventable blindness in working age diabetic people with the presence of an MA being one of the first signs. We transform the eye fundus images to the L*a*b* color space in order to separately process the L* and a* channels, looking for MAs in each of them. We then fuse the results, and last send the MA candidates to a k-nearest neighbors classifier for final assessment. The performance of the method, measured against 50 images with an ophthalmologist's hand-drawn ground-truth, shows high sensitivity (100%) and accuracy (84%), and running times around 10 s. This kind of automatic image processing application is important in order to reduce the burden on the public health system associated with the diagnosis of diabetic retinopathy given the high number of potential patients that need periodic screening.