Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 33.927
Filtrar
1.
Curr Opin Ophthalmol ; 31(6): 495-502, 2020 Nov.
Artigo em Inglês | MEDLINE | ID: mdl-33009082

RESUMO

PURPOSE OF REVIEW: This review discusses general features and organ-specific presentations of Susac syndrome as well as diagnosis and treatment. RECENT FINDINGS: Latest literature regarding demographics, new diagnostic modalities such as optical coherence tomography and treatment options for Susac syndrome are discussed in detail in this review, summarizing the most recent updated information. SUMMARY: Susac syndrome is a rare, underdiagnosed, and often misdiagnosed disease that can lead to severe complications such as deafness, vision loss, dementia, and death. It involves the central nervous system and may mimic other neurological and neuro-ophthalmological diseases.


Assuntos
Síndrome de Susac , Transtornos da Visão/etiologia , Encéfalo , Humanos , Síndrome de Susac/complicações , Síndrome de Susac/diagnóstico , Síndrome de Susac/terapia , Tomografia de Coerência Óptica , Transtornos da Visão/epidemiologia
2.
Vestn Oftalmol ; 136(5): 14-22, 2020.
Artigo em Russo | MEDLINE | ID: mdl-33056959

RESUMO

Preservation of visual functions in patients with chiasmo-sellar region compression (CSRC) is possible with early diagnosis and surgical decompression. PURPOSE: To analyze the parameters of optical coherence tomography (OCT) and optical coherence tomography-angiography (OCTA) in patients with CSRC. MATERIAL AND METHODS: The study included 10 patients (20 eyes) with CSRC, 15 healthy volunteers (30 eyes). OCT, OCTA was performed on Cirrus HD-OCT 5000 AngioPlex™ (Carl Zeiss Meditec, U.S.A.) with AngioVue system. RESULTS: Patients with CSRC were revealed to have decreased thickness of ILM-RPE in the nasal sector of outer circle (p<0.001) and average mGCIPL - total and for all six sectors (p<0.001), decreased RNFL in the inferior sector (p=0.017); decreased superficial vessel density (SVD) and perfusion density in the inner and outer circle areas and in all sectors of the ETDRS grid (p<0.001) except temporal; in the peripapillary area, decreased vessel perfusion density (VPD) in the inferior sector (p=0.025), capillary flux index (CFI) in all sectors (p<0.001; p=0.025 in the inferior sector). Informative diagnostic criteria included ILM-RPE in nasal sector of the outer circle (AUC=0.896); mGCIPL in the inferonasal sector (AUC=0.914), average (AUC=0.846), superior (AUC=0.829) and superonasal (AUC=0.846) sectors; average SVD (AUC=0.805) and SVD in the inner circle area (AUC=0.810); CFI in the inferior sector (AUC=0.806) with p<0.001. CONCLUSION: In CSRC, changes can be seen in OCT and OCTA parameters recorded in the macular and peripapillary regions before the changes in the central visual field. Informative diagnostic OCT and OCTA criteria can help diagnose the pathology early, expand the indications for decompression, and preserve the visual funcitons.


Assuntos
Disco Óptico , Tomografia de Coerência Óptica , Angiografia , Humanos , Células Ganglionares da Retina , Vasos Retinianos/diagnóstico por imagem
3.
Vestn Oftalmol ; 136(5): 46-51, 2020.
Artigo em Russo | MEDLINE | ID: mdl-33056963

RESUMO

PURPOSE: To compare the changes of the macular morphological and functional parameters in the postoperative period in patients with silicone oil tamponade after successful surgery of the macula-on rhegmatogenous retinal detachment (RRD). MATERIAL AND METHODS: The study included 20 eyes operated on for macula-on RRD, which made up the first group, and the control group (20 eyes) for comparison. All patients of the study group underwent vitrectomy using silicone oil tamponade. Standard ophthalmological examination was performed on the 3rd day (early postoperative period) and the 14th day (late postoperative period), including OCT and OCT-A that were used to assess morphological and functional changes. RESULTS: A significant decrease in visual acuity was seen on the 3rd day after surgery involving the use of silicone oil tamponade, in comparison with the 14th day (p=0.0237) and the control group (p=0.0001). A decrease in the FD parameter (p=0.045), a decrease in vascular density in the fovea (p=0.020) and parafovea (p=0.024) in SCP were found on the 3rd day in comparison with control. On the 14th day of postoperative observation, a tendency was detected for choroidal perfusion to restore, as well as significant increase in FD (p=0.016), and an increase in vascular density in parafovea (p=0.01) compared with the early postoperative period. No statistically significant changes were seen in the FAZ area and vessel density DCP (p>0.05).


Assuntos
Macula Lutea , Descolamento Retiniano , Humanos , Macula Lutea/diagnóstico por imagem , Descolamento Retiniano/diagnóstico , Descolamento Retiniano/cirurgia , Óleos de Silicone/efeitos adversos , Tomografia de Coerência Óptica , Vitrectomia
4.
Vestn Oftalmol ; 136(5): 77-86, 2020.
Artigo em Russo | MEDLINE | ID: mdl-33056967

RESUMO

PURPOSE: To evaluate biocompatibility of the new keratoprosthesis supporting plates (KSP) in rabbits in vivo. MATERIAL AND METHODS: The study included 15 chinchilla rabbits. In the first group (5 rabbit eyes) KSP made of hydrophobic acryl with square penetrating holes of 220×220 micron (model 1) were inserted into rabbits' corneas. In the second group (5 eyes), KSP made of hydrophobic acryl were used that had trapezoidal fenestrations with size (from 170×130 micron to 180×70 microns) gradually changing from periphery to the center of KSP (model 2). The control group rabbits (5 eyes) had 1/2 of Fyodorov-Zuev KSP made of titanium implanted. All animals were observed for up to 3 months with biomicroscopy and optical coherence tomography of the anterior segment. The animals were then euthanized and had their corneo-scleral discs excised and then examined with optical microscopy and scanning electron microscopy (SEM). RESULTS: After 3 months, there was only one case of KSP protrusion in the first group. In the second group, thinning of the corneal layers above the central part of KSP occurred in one case. The presence of polymer KSP (of both models) in the corneal stroma was found not to cause formation of rough fibrotic tissue. At the same time, adhered cellular and fibrous elements were discovered on the surface and inside the holes of the polymer KSP, while on the surface of the titanium plate cellular elements were absent. CONCLUSION: Supporting plates made of hydrophobic acrylic material can potentially serve as a foundation for the new keratoprosthesis design.


Assuntos
Córnea , Próteses e Implantes , Animais , Córnea/diagnóstico por imagem , Córnea/cirurgia , Substância Própria , Coelhos , Tomografia de Coerência Óptica
5.
Klin Monbl Augenheilkd ; 237(10): 1187-1193, 2020 Oct.
Artigo em Inglês, Alemão | MEDLINE | ID: mdl-33059378

RESUMO

In recent years, an increasing incidence of laser pointer-associated retinal injuries has been observed, likely due to easy access to incorrectly classified laser pointers, their labelling as toys, and lack of awareness concerning the associated risk. Laser pointer exposure can lead to irreversible retinal damage and associated vision loss, depending on the wavelength, radiation power, duration of exposure, localization, and spot size. Pronounced retinal laser damage is especially seen in children and teenagers. The structural appearance of retinal laser pointer damage varies and, in some cases, may be a diagnostic challenge. Besides often subtle findings on optical coherence tomography examination, characteristic alterations on near-infrared autofluorescence imaging may be valuable for the diagnosis of retinal laser pointer injuries and for differentiating other retinal lesions with similar appearance. The increase in laser pointer injuries indicates that regulatory actions and increased public awareness are required regarding the dangers of laser pointers.


Assuntos
Retina , Doenças Retinianas , Adolescente , Criança , Humanos , Lasers , Retina/diagnóstico por imagem , Doenças Retinianas/etiologia , Tomografia de Coerência Óptica , Acuidade Visual
6.
Klin Monbl Augenheilkd ; 237(10): 1225-1229, 2020 Oct.
Artigo em Alemão | MEDLINE | ID: mdl-33059379

RESUMO

One of the most controversial discussions in retinal surgery is currently being held about the importance of intraoperative OCT (iOCT). The background is the desire to combine the 2-dimensional fundus view of the surgeon with the layered depth information of OCT to achieve a 4-dimensional "augmented reality" (3-D plus change over time). This should help to visualise fine structures, which have been hidden from the surgeon's view. Therefore, retinal surgery seems to be predestined for the use of iOCT. The great hope is that a dynamic live 3-D image with real-time feedback will provide the surgeon with additional information and improve safety. Although fascinating at the first glance, in the surgical routine, however, iOCT technology is disappointing, especially in macular surgery. It rarely provides substantial information that would not be obtainable without iOCT or that would not be available in much better quality through preoperative diagnostic testing. Only some special indications remain, particularly related to subretinal surgery.


Assuntos
Retina , Tomografia de Coerência Óptica , Fundo de Olho , Procedimentos Cirúrgicos Oftalmológicos , Retina/diagnóstico por imagem , Retina/cirurgia , Corpo Vítreo
7.
Vestn Oftalmol ; 136(5): 58-66, 2020.
Artigo em Russo | MEDLINE | ID: mdl-33056965

RESUMO

PURPOSE: To evaluate the influence of prolonged neuroprotective therapy on disease progression in patients with primary open-angle glaucoma (POAG) with compensated intraocular pressure (IOP). MATERIAL AND METHODS: The study included 147 patients with stages I-II POAG (249 eyes) who were randomized into the main (69 patients, 119 eyes) and control groups (78 patients, 130 eyes). Patients of the main group underwent retinalamin treatment course every 6 months. Patients were examined before enrolling and then every 3 months during the 24-months follow-up including optical coherence tomography (OCT; RNFL - retinal nerve fiber layer, NRR - neuroretinal rim, GCL - ganglion cell layer) and static perimetry (MD - mean deviation, PSD - pattern standard deviation). RESULTS: Visual acuity and refraction did not change in either group (p>0.05). IOP increased in the control group (p=0.033). There was no difference between the groups by the 24th month (p=0.87). No MD changes were noted in the main (p=0.45) and control groups (p=0.27). PSD changed in the main (4.84±3.21 and 6.01±2.584 dB in the beginning and the end, respectively, p=0.0004) and the control groups (3.46±2.23 and 5.86±2.26 dB, respectively; p<0.0001). The groups differed in MD and PSD initially (p=0.15; p=0.02) and became equal by the end (p=0.59; p=0.53). RNFL did not change significantly in the main group (p=0.078) and decreased from 83.5±22.47 to 76.7±20.7 µm in the control group (p=0.001); no differences between the groups were noted in the beginning (p=0.276) or in the end of the study (p=0.524). NRR increased in the main group from 222±88.94 to 231±99.3 (p=0.012), and decreased in the control group from 248±87.09 to 234±96.2 (p=0.0006); no differences were found between groups in the beginning or in the end of the study (p=0.109; p=0.909). GCL thickness did not change either in the main, or in the control group (p=0.211; p=0.16), with no difference between the group noted in the beginning or the end of the study (p=0.44; p=0.51). CONCLUSION: Regular treatment with retinalamin arrests the development of glaucomatous optic neuropathy. Longer-term research is required to study its influence on the visual function and the quality of life.


Assuntos
Glaucoma , Peptídeos , Qualidade de Vida , Progressão da Doença , Humanos , Fibras Nervosas , Peptídeos/uso terapêutico , Células Ganglionares da Retina , Tomografia de Coerência Óptica , Acuidade Visual
8.
Vestn Oftalmol ; 136(5): 116-122, 2020.
Artigo em Russo | MEDLINE | ID: mdl-33056972

RESUMO

Vascular disorders account for a significant proportion of acute loss of vision. In recent years, scientific and technical progress in ophthalmology has provided new opportunities in the study of vascular pathology, significantly expanding the understanding of their pathogenesis. The article presents a clinical case of a patient with acute retinal ischemia syndrome who had retinal blood flow disturbances studied using optical coherence tomography (OCT) imaging. It demonstrates extensive possibilities of diagnostics of ischemic retinal lesions using OCT angiography that make this method the most informative in terms of evaluating the blood flow at different levels, independently in each vascular plexus.


Assuntos
Doenças Retinianas , Vasos Retinianos , Angiofluoresceinografia , Humanos , Retina , Vasos Retinianos/diagnóstico por imagem , Tomografia de Coerência Óptica
9.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1286-1289, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018223

RESUMO

Many ocular diseases are associated with choroidal changes. Therefore, it is crucial to be able to segment the choroid to study its properties. Previous methods for choroidal segmentation have focused on single cross-sectional scans. Volumetric choroidal segmentation has yet to be widely reported. In this paper, we propose a sequential segmentation approach using a variation of U-Net with a bidirectional C-LSTM(Convolutional Long Short Term Memory) module in the bottleneck region. The model is evaluated on volumetric scans from 40 high myopia subjects, obtained using SS-OCT(Swept Source Optical Coherence Tomography). A comparison with other U-Net-based variants is also presented. The results demonstrate that volumetric segmentation of the choroid can be achieved with an accuracy of IoU(Intersection over Union) 0.92.Clinical relevance- This deep learning approach can automatically segment the choroidal volume, which can enable better evaluation and monitoring at ocular diseases.


Assuntos
Aprendizado Profundo , Miopia , Corioide/diagnóstico por imagem , Estudos Transversais , Humanos , Tomografia de Coerência Óptica
10.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1360-1363, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018241

RESUMO

Registration of multimodal retinal images is of great importance in facilitating the diagnosis and treatment of many eye diseases, such as the registration between color fundus images and optical coherence tomography (OCT) images. However, it is difficult to obtain ground truth, and most existing algorithms are for rigid registration without considering the optical distortion. In this paper, we present an unsupervised learning method for deformable registration between the two images. To solve the registration problem, the structure achieves a multi-level receptive field and takes contour and local detail into account. To measure the edge difference caused by different distortions in the optics center and edge, an edge similarity (ES) loss term is proposed, so loss function is composed by local cross-correlation, edge similarity and diffusion regularizer on the spatial gradients of the deformation matrix. Thus, we propose a multi-scale input layer, U-net with dilated convolution structure, squeeze excitation (SE) block and spatial transformer layers. Quantitative experiments prove the proposed framework is best compared with several conventional and deep learningbased methods, and our ES loss and structure combined with Unet and multi-scale layers achieve competitive results for normal and abnormal images.


Assuntos
Algoritmos , Retina , Fundo de Olho , Retina/diagnóstico por imagem , Tomografia de Coerência Óptica
11.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1404-1407, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018252

RESUMO

Diabetic retinopathy (DR) is a progressive eye disease that affects a large portion of working-age adults. DR, which may progress to an irreversible state that causes blindness, can be diagnosed with a comprehensive dilated eye exam. With the eye dilated, the Doctor takes pictures of the inside of the eye via a medical procedure called Fluorescein Angiography, in which a dye is injected into the bloodstream. The dye highlights the blood vessels in the back of the eye so they can be photographed. In addition, the Doctor may request an Optical Coherence Tomography (OCT) exam, by which cross-sectional photos of the retina are produced to measure the thickness of the retina. Early prognostication is vital in treating the disease and preventing it from progressing into advanced irreversible stages. Skilled medical personnel and necessary medical facilities are required to detect DR in its five major stages. In this paper, we propose a diagnostic tool to detect Diabetic retinopathy from fundus images by using an ensemble of multi-inception CNN networks. Our inception block consists of three Convolutional layers with kernel sizes of 3x3, 5x5, and 1x1 that are concatenated deeply and forwarded to the max-pooling layer. We experimentally compare our proposed method with two pre-trained models: VGG16 and GoogleNets. The experiment results show that the proposed method can achieve an accuracy of 93.2% by an ensemble of 10 random networks, compared to 81% obtained with transfer learning based on VGG19.


Assuntos
Diabetes Mellitus , Retinopatia Diabética , Estudos Transversais , Retinopatia Diabética/diagnóstico , Fundo de Olho , Humanos , Redes Neurais de Computação , Tomografia de Coerência Óptica
12.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1641-1645, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018310

RESUMO

Since the thickness and shape of the choroid layer are indicators for the diagnosis of several ophthalmic diseases, the choroid layer segmentation is an important task. There exist many challenges in segmentation of the choroid layer. In this paper, in view of the lack of context information due to the ambiguous boundaries, and the subsequent inconsistent predictions of the same category targets ascribed to the lack of context information or the large regions, a novel Skip Connection Attention (SCA) module which is integrated into the U-Shape architecture is proposed to improve the precision of choroid layer segmentation in Optical Coherence Tomography (OCT) images. The main function of the SCA module is to capture the global context in the highest level to provide the decoder with stage-by-stage guidance, to extract more context information and generate more consistent predictions for the same class targets. By integrating the SCA module into the U-Net and CE-Net, we show that the module improves the accuracy of the choroid layer segmentation.


Assuntos
Aprendizado Profundo , Tomografia de Coerência Óptica , Atenção , Corioide/diagnóstico por imagem , Coleta de Dados
13.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1646-1649, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018311

RESUMO

Lens structures segmentation on anterior segment optical coherence tomography (AS-OCT) images is a fundamental task for cataract grading analysis. In this paper, in order to reduce the computational cost while keeping the segmentation accuracy, we propose an efficient segmentation method for lens structures segmentation. At first, we adopt an efficient semantic segmentation network in the work, and used it to extract the lens area image instead of the conventional object detection method, and then used it once again to segment the lens structures. Finally, we introduce the curve fitting processing (CFP) on the segmentation results. Experiment results show that our method has good performance on accuracy and processing speed, and could be applied to CASIA II device for practical applications.


Assuntos
Cristalino , Lentes , Projetos de Pesquisa , Tomografia de Coerência Óptica
14.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1832-1835, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018356

RESUMO

Glaucoma is a progressive optic neuropathy that leads to loss of retinal ganglion cells and thinning of retinal nerve fiber layer (RNFL). Circumpapillary RNFL thickness measurements have been used for glaucoma diagnostic and monitoring purposes. However, manual measurement of the RNFL thickness is tedious and subjective. We proposed and evaluated the performance of automated RNFL segmentation from OCT images using a state-of-the-art deep learning-based model. Circumpapillary OCT scans were extracted from volumetric OCT scans using a high-resolution swept-source OCT device. Manual annotation was performed on the extracted scans and used for training and evaluation. The results show that the accuracy and diagnostic performance is comparable to manual assessment, and the potential application of deep learning-based approach in such segmentation.


Assuntos
Disco Óptico , Doenças do Nervo Óptico , Humanos , Fibras Nervosas , Disco Óptico/diagnóstico por imagem , Células Ganglionares da Retina , Tomografia de Coerência Óptica
15.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1863-1866, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018363

RESUMO

The deterioration of the retina center could be the main reason for vision loss. Older people usually ranging from 50 years and above are exposed to age-related macular degeneration (AMD) disease that strikes the retina. The lack of human expertise to interpret the complexity in diagnosing diseases leads to the importance of developing an accurate method to detect and localize the targeted infection. Approaching the performance of ophthalmologists is the consistent main challenge in retinal disease segmentation. Artificial intelligence techniques have shown enormous achievement in various tasks in computer vision. This paper depicts an automated end-to-end deep neural network for retinal disease segmentation on optical coherence tomography (OCT) scans. The work proposed in this study shows the performance difference between convolution operations and atrous convolution operations. Three deep semantic segmentation architectures, namely U-net, Segnet, and Deeplabv3+, have been considered to evaluate the performance of varying convolution operations. Empirical outcomes show a competitive performance to the human level, with an average dice score of 0.73 for retinal diseases.


Assuntos
Doenças Retinianas , Tomografia de Coerência Óptica , Idoso , Idoso de 80 Anos ou mais , Inteligência Artificial , Humanos , Redes Neurais de Computação , Retina/diagnóstico por imagem , Doenças Retinianas/diagnóstico por imagem
16.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1867-1870, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018364

RESUMO

Automatic detection of age-related macular degeneration (AMD) from optical coherence tomography (OCT) images is often performed using the retinal layers only and choroid is excluded from the analysis. This is because symptoms of AMD manifest in the choroid only in the later stages and clinical literature is divided over the role of the choroid in detecting earlier stages of AMD. However, more recent clinical research suggests that choroid is affected at a much earlier stage. In the proposed work, we experimentally verify the effect of including the choroid in detecting AMD from OCT images at an intermediate stage. We propose a deep learning framework for AMD detection and compare its accuracies with and without including the choroid. Results suggest that including the choroid improves the AMD detection accuracy. In addition, the proposed method achieves an accuracy of 96.78% which is comparable to the state-of-the-art works.


Assuntos
Degeneração Macular , Tomografia de Coerência Óptica , Corioide/diagnóstico por imagem , Humanos , Degeneração Macular/diagnóstico por imagem , Retina/diagnóstico por imagem
17.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1871-1874, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018365

RESUMO

Near infrared autofluorescence (NIRAF) optical coherence tomography (OCT) is an intravascular imaging modality, based on a catheter which emits light at two different wavelengths through an optical fiber. Since OCT is becoming the method of choice in interventional cardiology and NIRAF is proven to be higher in plaque lesions having higher risk morphologic phenotypes, the NIRAF-OCT can become powerful and promising technology. However, there is NIRAF- distance dependence which has to be addressed before the technology can be applied in clinical practice. The present paper aims at presenting a method which calibrates the distance dependent NIRAF signal and ensures that similar NIRAF values are depicted when targeting the same lesion. Towards this purpose, autofluorescence phantoms were constructed, accurate distance measurements were conducted and the NIRAF-distance relationship was quantified. Finally, a calibration function was proposed which is able to accurately calibrate the NIRAF signal in any NIRAF-OCT pullback.


Assuntos
Doença da Artéria Coronariana , Placa Aterosclerótica , Calibragem , Humanos , Tomografia de Coerência Óptica
18.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1875-1878, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018366

RESUMO

Optical coherence tomography (OCT) allows in vivo volumetric imaging of the eye. Identification and localization of anatomical features in enface OCT are important steps in OCT-based image analysis. However the visibility of anatomical features in both structural OCT or vascular OCT angiography is limited. In this paper, we propose to use vascular-enhanced enface OCT image for the concurrent detection of anatomical features, using a FasterRCNN object detection framework based on convolutional networks. Transfer learning was applied to adapt pre-trained models as the backbone networks. Models were evaluated on a dataset of 419 images. The results showed that VGG-FasterRCNN achieved a mean average precision 0.77, with localization errors of 0.18 ± 0.10 mm and 0.24 ± 0.13 mm for the macula and optic disc respectively. The results are promising and suggest that this network could potentially be used to automatically and concurrently detect anatomical features.Clinical Relevance- Localization of anatomical features in enface OCT is needed for the automation of OCT image analysis protocols. The use of fast detection networks could potentially suggest image-based real-time tracking during image acquisition.


Assuntos
Disco Óptico , Tomografia de Coerência Óptica , Angiografia
19.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1879-1882, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018367

RESUMO

Optical coherence tomography (OCT) has stimulated a wide range of medical image-based diagnosis and treatment. In cardiac imaging, OCT has been used in assessing plaques before and after stenting. While needed in many scenarios, high resolution comes at the costs of demanding optical design and data storage/transmission. In OCT, there are two types of resolutions to characterize image quality: optical and digital resolutions. Although multiple existing works have heavily emphasized on improving the digital resolution, the studies on improving optical resolution or both resolutions remain scarce. In this paper, we focus on improving both resolutions. In particular, we investigate a deep learning method to address the problem of generating a high-resolution (HR) OCT image from a low optical and low digital resolution (L2R) image. To this end, we have modified the existing super-resolution generative adversarial network (SR-GAN) for OCT image reconstruction. Experimental results from the human coronary OCT images have demonstrated that the reconstructed images from highly compressed data could achieve high structural similarity and accuracy in comparison with the HR images. Besides, our method has obtained better denoising performance than the block-matching and 3D filtering (BM3D) and Denoising Convolutional Neural Networks (DnCNN) denoising method.


Assuntos
Aprendizado Profundo , Tomografia de Coerência Óptica , Humanos , Processamento de Imagem Assistida por Computador , Redes Neurais de Computação
20.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1883-1886, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018368

RESUMO

Precise three-dimensional segmentation of choroidal vessels helps us understand the development and progression of multiple ocular diseases, such as agerelated macular degeneration and pathological myopia. Here we propose a novel automatic choroidal vessel segmentation framework for swept source optical coherence tomography (SS-OCT) to visualize and quantify three-dimensional choroidal vessel networks. Retinal pigment epithelium (RPE) was delineated from volumetric data and enface frames along the depth were extracted under the RPE. Choroidal vessels on the first enface frame were labeled by adaptive thresholding and each subsequent frame was segmented via segment propagation from the frame above and was in turn used as the reference for the next frame. Choroid boundary was determined by structural similarity index between adjacent frames. The framework was tested on 33 mm SS-OCT volumes acquired by a prototype SS-OCT system (PlexElite 9000, Zeiss Meditec, Dublin, CA, US), and vessel metrics including perfusion density, vessel density and mean vessel diameter were computed. Results from human subjects (N = 8) and non-human primates (N = 6) were summarized.Clinical Relevance- Accurate 3D choroid vessel segmentation can help clinicians better quantify blood perfusion which can lead to improved diagnosis and management of retinal eye diseases.


Assuntos
Degeneração Macular , Miopia Degenerativa , Corioide/diagnóstico por imagem , Humanos , Degeneração Macular/diagnóstico por imagem , Epitélio Pigmentado da Retina/diagnóstico por imagem , Tomografia de Coerência Óptica
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA