RESUMEN
Objective: To characterize changes in the retinal microvasculature in eyes with birdshot chorioretinopathy (BCR) using OCT angiography (OCTA). Design: Retrospective, observational, single center. Subjects: Twenty-eight patients (53 eyes) with BCR and 59 age-matched controls (110 eyes). Methods: En face OCTA images of the superficial capillary plexus (SCP) and deep capillary plexus (DCP) of each eye were assessed for the presence of microvascular abnormalities and used to measure the vessel and foveal avascular zone (FAZ) areas. A longitudinal analysis was performed with a representative cohort of 23 BCR eyes (16 patients) at baseline and at a 2-year time point. Main Outcome Measures: Whole-image vessel density (VD, %), extrafoveal avascular zone (extra-FAZ) VD (%), and FAZ area (%) were calculated and compared between control and BCR eyes. The frequency of microvascular abnormalities in BCR eyes was recorded. Results: In the SCP, increased intercapillary space and capillary loops were common features present on OCTA images. Whole-image and extra-FAZ VD were lower in the BCR group compared with controls (P < 0.0001 [SCP and DCP]). Foveal avascular zone area was enlarged in BCR eyes (P = 0.0008 [DCP]). Worsening best-corrected visual acuity was associated with a decrease in whole-image and extra-FAZ VD in the SCP (P < 0.0001 for both) and the DCP (P < 0.005 for both). Multivariable analysis, with vessel analysis parameters as outcomes, demonstrated that increasing age, increasing disease duration, lower central subfield thickness, and treatment-naive eyes (compared with those on only biologics) were associated with a significant decrease in both DCP whole-image and extra-FAZ VD. Increasing disease duration was associated with a significant decrease in both SCP whole-image and extra-FAZ VD. Longitudinal analysis demonstrated no significant difference in any vessel analysis parameters except for an increase in DCP FAZ area. Conclusions: Our results demonstrate a significant a decrease in VD in BCR eyes and an association on multivariable analysis with disease duration. Quantifying VD in the retinal microvasculature may be a useful biomarker for monitoring disease severity and progression in patients with BCR. Further studies with extended longitudinal follow-up are needed to characterize its utility in monitoring disease progression and treatment response. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
RESUMEN
BACKGROUND: A significant proportion of patients with heart failure (HF) progress to an advanced stage, which is associated with a substantial increase in morbidity and mortality. These patients may be eligible for advanced treatment strategies such as mechanical circulatory support with ventricular assist devices (VAD). Vascular dysfunction is a hallmark of heart failure pathophysiology and prognosis. However, whether and to what degree the hemodynamic benefits of VADs influence vascular function remain unknown. METHODS AND RESULTS: In this study, we evaluated endothelial vascular function with flow-mediated vasodilatation (FMD) and with flicker-light induced retinal vasodilatation (FID). 34 patients with a VAD (age 58 ± 10 years, 85% male, 74% ischemic heart disease, 26 continuous-flow (CF)-LVAD, and 8 pulsatile biventricular (bi)-VAD) were compared to 34 propensity-matched patients (mean age 62 ± 9 years, 68% male, 59% ischemic heart disease) with advanced HF (AdvHF). Endothelial function of larger arteries (FMD) was significantly better in patients after VAD implantation compared to matched AdvHF patients (7.2 ± 4.6% vs. 5.0 ± 3.2%, p = 0.03), whereas microvascular arteriolar function (FIDart) did not differ (0.99 ± 1.43% vs. 1.1 ± 1.7%, p = 0.78). The arterio-venous ratio (AVR) was higher in the VAD group (0.90 ± 0.06 vs 0.85 ± 0.09, p = 0.01), reflecting wider retinal arteriolar and narrower venular diameters. There was no difference in vascular function between patients with CF-LVAD and pulsatile Bi-VAD. CONCLUSION: In patients with advanced heart failure, VAD implantation was associated with better endothelial function at the level of large arteries, but not in the microcirculation.
RESUMEN
This study aimed to evaluate the effect of magnification error and axial length (AL) on circumpapillary capillary density (cpCD) and circumpapillary retinal nerve fiber layer thickness (cpRNFLT) in healthy eyes. Seventy-two healthy eyes of 72 subjects with AL 24.7 ± 1.5 mm (range: 20.9-28.0 mm) were enrolled in this retrospective cross-sectional study and underwent optical coherence tomography angiography scanning. Magnification corrected measurement areas were obtained using AL upon which corrected cpCD, cpRNFLT values were determined. Relationships between AL and the percentage difference between corrected and uncorrected values (ΔcpCD, ΔcpRNFLT) as well as the effect of AL on magnification corrected cpCD, cpRNFLT were evaluated. ΔcpCD significantly increased with AL in the global, inferior nasal and superior nasal sectors (all p < 0.001). ΔcpRNFLT significantly increased with AL in global and all sectors (all p < 0.001) and the correlations were significantly stronger than that of ΔcpCD-AL in all sectors (all p < 0.001). Corrected cpCD did not associate with AL while corrected cpRNFLT demonstrated a significant positive association with AL in the global (p = 0.005) and temporal sector (p < 0.001). Magnification error led to a significant underestimation of cpCD in eyes with longer AL although its underestimation and the effect of AL was smaller in comparison to that of cpRNFLT.
Asunto(s)
Longitud Axial del Ojo , Fibras Nerviosas , Tomografía de Coherencia Óptica , Humanos , Masculino , Femenino , Tomografía de Coherencia Óptica/métodos , Adulto , Estudios Transversales , Fibras Nerviosas/fisiología , Estudios Retrospectivos , Persona de Mediana Edad , Longitud Axial del Ojo/diagnóstico por imagen , Vasos Retinianos/diagnóstico por imagen , Capilares/diagnóstico por imagen , Adulto Joven , Retina/diagnóstico por imagenRESUMEN
Background: Skin-derived advanced glycation end products (sAGEs) have been associated with cardiovascular (CV) risk and mortality in adults. We hypothesize that cardiorespiratory fitness (CRF), body mass index (BMI) and vascular health are associated with development of sAGEs during childhood. Methods: In our prospective cohort study, 1171 children aged 6-8 years were screened for sAGEs, BMI, retinal arteriolar diameters (CRAE) and pulse wave velocity (PWV), using standardized procedures. To determine CRF a 20 m shuttle run was performed. After four 4 years, all parameters were assessed in 675 children using the same protocols. Results: Higher initial CRF levels were significantly associated with lower sAGEs (ß [95 CI] -0.02 [-0.03 to -0.002] au, p = 0.022) levels at follow-up, although they showed a greater change from baseline to follow-up (ß [95 CI] 0.02 [0.002 to 0.03] au, p = 0.027). Moreover, individuals with higher sAGEs at baseline showed narrower CRAE (ß [95% CI] -5.42 [-8.76 to -2.08] µm, p = 0.001) at follow-up and showed a greater change in CRAE (ß [95% CI] -3.99 [-7.03 to -0.96] µm, p = 0.010) from baseline to follow-up. Conclusion: Exercise and higher CRF may help mitigate the formation of AGEs during childhood, thereby reducing the risk for development of CV disease associated with AGEs-induced damage. Preventive strategies may need to target CRF early in life to achieve improvement of CV risk factors and may counteract the development of CV disease later in life.
RESUMEN
Retinal vessel segmentation is crucial for the diagnosis of ophthalmic and cardiovascular diseases. However, retinal vessels are densely and irregularly distributed, with many capillaries blending into the background, and exhibit low contrast. Moreover, the encoder-decoder-based network for retinal vessel segmentation suffers from irreversible loss of detailed features due to multiple encoding and decoding, leading to incorrect segmentation of the vessels. Meanwhile, the single-dimensional attention mechanisms possess limitations, neglecting the importance of multidimensional features. To solve these issues, in this paper, we propose a detail-enhanced attention feature fusion network (DEAF-Net) for retinal vessel segmentation. First, the detail-enhanced residual block (DERB) module is proposed to strengthen the capacity for detailed representation, ensuring that intricate features are efficiently maintained during the segmentation of delicate vessels. Second, the multidimensional collaborative attention encoder (MCAE) module is proposed to optimize the extraction of multidimensional information. Then, the dynamic decoder (DYD) module is introduced to preserve spatial information during the decoding process and reduce the information loss caused by upsampling operations. Finally, the proposed detail-enhanced feature fusion (DEFF) module composed of DERB, MCAE and DYD modules fuses feature maps from both encoding and decoding and achieves effective aggregation of multi-scale contextual information. The experiments conducted on the datasets of DRIVE, CHASEDB1, and STARE, achieving Sen of 0.8305, 0.8784, and 0.8654, and AUC of 0.9886, 0.9913, and 0.9911 on DRIVE, CHASEDB1, and STARE, respectively, demonstrate the performance of our proposed network, particularly in the segmentation of fine retinal vessels.
RESUMEN
OBJECTIVES: The effects of HIV and antiretroviral therapy (ART) on microvascular function are poorly explored. We compared retinal vessel functional responses to flicker light-induced provocation (FLIP) in people living with HIV (PLWH) and people living without HIV (PLWoutH). METHODS: We included 115 PLWH and 51 PLWoutH with a median age of 41 years. Treated PLWH received similar first-line fixed-dose combination ART. Clinical characteristics and retinal vessels functional responses to FLIP were compared in (a) PLWH and PLWoutH; and (b) PLWH groups stratified by the median of (i) CD4-count (511 cells/mm3), (ii) viral load (50 copies/mL), and (iii) ART duration (57.6 months). RESULTS: PLWH were older, smoked more, and had a lower prevalence of hypertension than PLWoutH (p < 0.05). Almost 64% of PLWH were infected for more than 5 years. Retinal vessel responses to FLIP were similar between PLWH and PLWoutH after taking confounders into account. In addition, PLWH subgroups stratified according to immuno-virological status by CD4-count, viral load, and ART duration showed no differences in retinal vessel responses to FLIP. CONCLUSION: Living with HIV and receiving ART were not associated with altered microvascular function as assessed with dynamic retinal vessel analysis in a South African case-control study.
RESUMEN
Deep learning plays a pivotal role in retinal blood vessel segmentation for medical diagnosis. Despite their significant efficacy, these techniques face two major challenges. Firstly, they often neglect the severe class imbalance in fundus images, where thin vessels in the foreground are proportionally minimal. Secondly, they are susceptible to poor image quality and blurred vessel edges, resulting in discontinuities or breaks in vascular structures. In response, this paper proposes the Skeleton-guided Multi-scale Dual-coordinate Attention Aggregation (SMDAA) network for retinal vessel segmentation. SMDAA comprises three innovative modules: Dual-coordinate Attention (DCA), Unbalanced Pixel Amplifier (UPA), and Vessel Skeleton Guidance (VSG). DCA, integrating Multi-scale Coordinate Feature Aggregation (MCFA) and Scale Coordinate Attention Decoding (SCAD), meticulously analyzes vessel structures across various scales, adept at capturing intricate details, thereby significantly enhancing segmentation accuracy. To address class imbalance, we introduce UPA, dynamically allocating more attention to misclassified pixels, ensuring precise extraction of thin and small blood vessels. Moreover, to preserve vessel structure continuity, we integrate vessel anatomy and develop the VSG module to connect fragmented vessel segments. Additionally, a Feature-level Contrast (FCL) loss is introduced to capture subtle nuances within the same category, enhancing the fidelity of retinal blood vessel segmentation. Extensive experiments on three public datasets (DRIVE, STARE, and CHASE_DB1) demonstrate superior performance in comparison to current methods. The code is available at https://github.com/wangwxr/SMDAA_NET.
RESUMEN
PURPOSE: To reveal changes in choroidal thickness, retinal vessel density, and serum HIF-1α and TNF-α levels in obstructive sleep apnea syndrome (OSAS) and their correlation. METHODS: This prospective case-control study included 118 patients divided into mild-to-moderate OSAS (n = 40), severe OSAS (n = 39), and a control group (n = 39). Choroidal thickness was evaluated with OCT, vessel density with OCTA, AHI index with polysomnography, and serum HIF-1α and TNF-α levels were analyzed using the enzyme-linked immunosorbent assay. RESULTS: The serum HIF-1α values of the participants in the mild-moderate OSAS and severe OSAS groups were [893.25(406.7-2068) and 1027(453-2527), respectively], and were both significantly higher than the control group [(521.5(231.6-2741))] (p < 0.001). Serum TNF-α levels did not differ significantly between the groups (p = 0.051).). Subfoveal choroidal thickness (SFCT) values of the severe OSAS groups were significantly lower than the control group (p < 0.05). The superficial and deep capillary plexus vascular density (SVD and DVD) values of the severe OSAS group were lower than the control group (p < 0.05). Serum HIF-1α and TNF-α levels of all participants were negatively correlated with both their SVD values (p < 0.05, r: -0.220 and p < 0.05, r: -0.252, respectively) and their DVD values (p < 0.001, r: -0.324 and p = 0.001, r: -0.299, respectively). CONCLUSIONS: Increased serum levels of inflammatory mediators (HIF-1α ve TNF-α) in OSAS cause a decrease in SFCT, SVD, and DVD, which is an indication of systemic vascular damage. Further research on developing treatment strategies to modulate TNF-α ve HIF-1α may help recede vascular morbidity in OSAS patients.
RESUMEN
BACKGROUND: Hypertension is the leading risk factor for subclinical target-organ damage (TOD) and cardiovascular disease (CVD). Little is known about the relationship between different pressure measures and subclinical TOD, especially in young populations. We compared the strength of associations of subclinical TOD markers with perfusion and pulsatile pressure in young adults. METHODS: A total of 1 187 young adults from the African-PREDICT study were included. Ambulatory mean arterial pressure (MAP) and pulse pressure (PP) was obtained. Markers of subclinical TOD were measured and included left ventricular mass index (LVMi), carotid intimamedia thickness (cIMT), carotidfemoral pulse wave velocity (cfPWV), central retinal arteriolar equivalent (CRAE) and albumin to creatinine ratio (ACR). RESULTS: Measures of sub-clinical TOD (cIMT, cfPWV and CRAE), associated stronger with perfusion pressure (all p < 0.001) than pulsatile pressure in unadjusted models. Stronger associations were found between cfPWV (adjusted R2 = 0.26), CRAE (adjusted R2 = 0.12) and perfusion pressure (all p ≤ 0.001) than pulsatile pressure independent of several non-modifiable and modifiable risk factors. CONCLUSIONS: In young, healthy adults, perfusion pressure is more strongly associated with subclinical TOD markers than pulsatile pressure. These findings contribute to the understanding of the development of early cardiovascular changes and may guide future intervention strategies.
Asunto(s)
Presión Arterial , Humanos , Masculino , Femenino , Adulto , Adulto Joven , Sudáfrica/epidemiología , Hipertensión/fisiopatología , Hipertensión/diagnóstico , Hipertensión/epidemiología , Análisis de la Onda del Pulso , Estudios Transversales , Velocidad de la Onda del Pulso Carotídeo-Femoral , Medición de Riesgo , Grosor Intima-Media Carotídeo , Factores de Riesgo , Factores de Edad , Monitoreo Ambulatorio de la Presión Arterial , Valor Predictivo de las Pruebas , Rigidez Vascular , Flujo Pulsátil , Población Negra , AdolescenteRESUMEN
PURPOSE: To investigate the effects of topically applied 1% tropicamide, 2.5% phenylephrine and 1% cyclopentolate on retinal vessel calliper (VC) using optical coherence tomography (OCT). METHODS: Patients who came to the ophthalmology clinic for routine examination and whose OCT films were taken before dilatation and after 30 min of last dilatation drop were included in the study. 90 ophthalmologically healthy subjects were divided into 3 groups of 30 subject each according to the application of the drops as follows: Tropicamide group (Group 1), Phenylephrine group (Group 2), Cyclopentolate group (Group 3). The right eyes of the subjects were dilated with drops and the left eyes were taken as the control group. VC of retinal artery and vein passing through an area one-half to one-disc diameter from the optic disc margin were measured from OCT films. The mean of the sum of superior retinal artery (SRA) and inferior retinal artery (IRA) VC and the mean of the sum of superior retinal vein (SRV) and inferior retinal vein (IRV) VC before and after the drop were compared. RESULTS: There was no statistically significant change in the mean sum of SRA and IRA VC and the mean sum of SRV and IRV VC before and after dilatation drops in all three groups. CONCLUSION: Dilatation drops have no statistically significant effect on retinal artery and vein VC.
Asunto(s)
Ciclopentolato , Midriáticos , Soluciones Oftálmicas , Fenilefrina , Vasos Retinianos , Tomografía de Coherencia Óptica , Tropicamida , Humanos , Midriáticos/administración & dosificación , Soluciones Oftálmicas/administración & dosificación , Tropicamida/administración & dosificación , Masculino , Femenino , Adulto , Ciclopentolato/administración & dosificación , Vasos Retinianos/efectos de los fármacos , Vasos Retinianos/diagnóstico por imagen , Fenilefrina/administración & dosificación , Adulto Joven , Persona de Mediana EdadRESUMEN
BACKGROUND: To establish a normative database for macular vessel density (VD) measured by optical coherence tomography angiography (OCTA) and explore the parameters related to the VD. METHODS: An observational study in epidemiology. 5840 healthy elderly participants in Beichen district, Tianjin, China underwent detailed ophthalmic and systemic examinations. OCTA was performed in all subjects using a 6 × 6-mm line scan mode centered on the macula and the built-in software was used to quantify VD and stratify the retina. RESULTS: One thousand four hundred sixty-one healthy elderly citizens (30.4% men) were included, with a median age of 60.0 years (8.0 years) and an age range of 50 to 87 years.VDs in the different plexuses: superficial capillary plexus (SCP) 43.9% (3.2%), deep capillary plexus (DCP) 44.3% (2.8%), outer capillary plexus (OCP) 21.9% (5.9%), choriocapillaris (CC) 52.1% (1.4%). 90% medical reference range of the VDs at different plexuses was reported. Age was correlated with the VDs of each capillary plexus. Sex was correlated with the VDs of DCP and OCP, and the VDs of DCP (p < 0.001) and OCP (p = 0.015) in women were higher than that in men. After age and sex adjustment, choroid average thickness was positively correlated with VDs of SCP (R = 0.067, p = 0.010) and DCP (R = 0.108, p < 0.001), ganglion cell layer (GCL) average thickness (R = 0.072, p = 0.006) was positively correlated with the VD of OCP, best-corrected visual acuity (BCVA) (R = 0.082, p = 0.002) was positively correlated with the VD of CC. CONCLUSIONS: In this study, the normative VD database of the Chinese urban healthy elderly population measured by the OCTA was established, and parameters related to the VD of each capillary plexus were analyzed, providing new ideas for the future study of the relationship between macular VD and disease. TRIAL REGISTRATION: The Beichen Eye Study had been registered on the Chinese Clinical Trial Registry website (registry number: ChiCTR2000032280) on April 25, 2020.
Asunto(s)
Angiografía con Fluoresceína , Vasos Retinianos , Tomografía de Coherencia Óptica , Humanos , Tomografía de Coherencia Óptica/métodos , Anciano , Masculino , Femenino , Vasos Retinianos/diagnóstico por imagen , Persona de Mediana Edad , Anciano de 80 o más Años , China/epidemiología , Angiografía con Fluoresceína/métodos , Valores de Referencia , Población Urbana , Mácula Lútea/diagnóstico por imagen , Mácula Lútea/irrigación sanguínea , Voluntarios Sanos , Fondo de Ojo , Densidad Microvascular , Pueblos del Este de AsiaRESUMEN
PURPOSE: To evaluate the retinal vessel density (VD) with optical coherence tomography angiography (OCTA) in asymptomatic patients affected by Waldenström macroglobulinemia (WM) without hyperviscosity syndrome (HVS) and to highlight the presence of microvascular damage in theese clinically asymptomatic WD patients. DESIGN: Prospective study. METHODS: A total of 43 eyes from 43 WM patients (24 females, 19 males, mean age 55.1 ± 13.6 years) were enrolled from January 2023 to December 2023 in the Eye Clinic of the University of Naples Federico II. Along with WM patients, 40 healthy subjects (HS) (20 females, 20 males, mean age 52.3 ± 15.6 years) with a normal ophthalmic examination and no history of intraocular surgery or retinal pathologic features were included as control group All patients and controls underwent OCTA RESULTS: The two groups were not significantly different for age and sex Visual acuity examination showed no statistically significant difference in BCVA between controls and patients Compared to HS, WD patients showed lower VD values in the SCP in the whole image (47.95 ± 5.17% vs. 52.99 ± 2.52 %; p < 0.001), as well as in the parafovea (53.01 ± 6.69% vs. 55.30 ± 2.61 %; p = 0.002), and fovea (21.38 ± 9.01% vs. 30.31 ± 5.84 %; p < 0.0001). On the other hand, in the DCP VD values were significantly higher in patients compared to controls in the whole image (55.82 ± 8.07% vs. 50.83 ± 5.46 %; p = 0.005), as well as in the parafovea (56.76 ± 6.26% vs. 52.59 ± 5.46 %; p = 0.0001), and fovea (38.75 ± 8.59% vs. 33.43 ± 8.68 %; p < 0.0001). CONCLUSION: The finding that OCTA confirmed the presence of widespread microvascular damage in WD patients clinically silent. Thus, OCTA is a safe rapid imaging technique that could represent a valid biomarker of systemic vascular dysfunction.
Asunto(s)
Tomografía de Coherencia Óptica , Macroglobulinemia de Waldenström , Humanos , Masculino , Femenino , Macroglobulinemia de Waldenström/diagnóstico por imagen , Persona de Mediana Edad , Proyectos Piloto , Estudios Prospectivos , Tomografía de Coherencia Óptica/métodos , Vasos Retinianos/diagnóstico por imagen , Viscosidad Sanguínea , Anciano , Angiografía con Fluoresceína/métodos , Adulto , Estudios de Casos y Controles , Agudeza VisualRESUMEN
PURPOSE: Aimed to create a nomogram using clinical and eye-specific metrics to predict the efficacy of intravenous glucocorticoid (IVGC) therapy in patients with active and moderate-to-severe Thyroid-Associated Ophthalmopathy (TAO). METHODS: This study was conducted on 84 eyes from 42 moderate-to-severe TAO patients who received systemic IVGC therapy, and 42 eyes from 21 controls. Data were collected retrospectively from June 2020 to December 2021. The least absolute shrinkage and selection operator (LASSO) method was used to identify predictive factors for "unresponsiveness" to IVGC therapy. These factors were then analyzed using logistic regression to create a nomogram. The model's discriminative ability was robustly assessed using a Bootstrap resampling method with 1000 iterations for receiver operating characteristic (ROC) curve analysis. RESULTS: The LASSO analysis identified six factors with non-zero coefficients as significant, including Schirmer I test values, Meibomian gland (MG) diameter, MG length, disease duration, whole capillary vessel density (VD) in the radial peripapillary capillary (RPC), and whole macular VD for the superficial retinal capillary plexus (SRCP). The subsequent logistic regression model highlighted MG length, whole macular VD for SRCP, and disease duration as independent predictors of IVGC therapy response. The constructed nomogram demonstrated an area under the curve (AUC) of 0.82 (95% CI: 0.73-0.91), affirming the model's consistent and reliable ability to distinguish between responsive and non-responsive TAO patients. CONCLUSION: Our nomogram, combining MG length (<4.875 mm), SRCP VD (<50.25%), and disease duration (>5.5 months), reliably predicts lower IVGC therapy effectiveness in active, moderate-to-severe TAO patients.
RESUMEN
Retinal vessel segmentation is crucial for diagnosing and monitoring various eye diseases such as diabetic retinopathy, glaucoma, and hypertension. In this study, we examine how sharpness-aware minimization (SAM) can improve RF-UNet's generalization performance. RF-UNet is a novel model for retinal vessel segmentation. We focused our experiments on the digital retinal images for vessel extraction (DRIVE) dataset, which is a benchmark for retinal vessel segmentation, and our test results show that adding SAM to the training procedure leads to notable improvements. Compared to the non-SAM model (training loss of 0.45709 and validation loss of 0.40266), the SAM-trained RF-UNet model achieved a significant reduction in both training loss (0.094225) and validation loss (0.08053). Furthermore, compared to the non-SAM model (training accuracy of 0.90169 and validation accuracy of 0.93999), the SAM-trained model demonstrated higher training accuracy (0.96225) and validation accuracy (0.96821). Additionally, the model performed better in terms of sensitivity, specificity, AUC, and F1 score, indicating improved generalization to unseen data. Our results corroborate the notion that SAM facilitates the learning of flatter minima, thereby improving generalization, and are consistent with other research highlighting the advantages of advanced optimization methods. With wider implications for other medical imaging tasks, these results imply that SAM can successfully reduce overfitting and enhance the robustness of retinal vessel segmentation models. Prospective research avenues encompass verifying the model on vaster and more diverse datasets and investigating its practical implementation in real-world clinical situations.
Asunto(s)
Algoritmos , Vasos Retinianos , Humanos , Vasos Retinianos/diagnóstico por imagen , Procesamiento de Imagen Asistido por Computador/métodos , Retinopatía Diabética/diagnóstico por imagenRESUMEN
Accurate segmentation of retinal vessels is of great significance for computer-aided diagnosis and treatment of many diseases. Due to the limited number of retinal vessel samples and the scarcity of labeled samples, and since grey theory excels in handling problems of "few data, poor information", this paper proposes a novel grey relational-based method for retinal vessel segmentation. Firstly, a noise-adaptive discrimination filtering algorithm based on grey relational analysis (NADF-GRA) is designed to enhance the image. Secondly, a threshold segmentation model based on grey relational analysis (TS-GRA) is designed to segment the enhanced vessel image. Finally, a post-processing stage involving hole filling and removal of isolated pixels is applied to obtain the final segmentation output. The performance of the proposed method is evaluated using multiple different measurement metrics on publicly available digital retinal DRIVE, STARE and HRF datasets. Experimental analysis showed that the average accuracy and specificity on the DRIVE dataset were 96.03% and 98.51%. The mean accuracy and specificity on the STARE dataset were 95.46% and 97.85%. Precision, F1-score, and Jaccard index on the HRF dataset all demonstrated high-performance levels. The method proposed in this paper is superior to the current mainstream methods.
Asunto(s)
Algoritmos , Procesamiento de Imagen Asistido por Computador , Vasos Retinianos , Vasos Retinianos/diagnóstico por imagen , Humanos , Procesamiento de Imagen Asistido por Computador/métodosRESUMEN
PURPOSE: To analyze the characteristics of macular retinal vessel density and thickness in children with myopia. METHODS: A cross-sectional study was conducted. A total of 228 children aged 4-16 years who visited the Ineye Hospital of Chengdu University of Traditional Chinese Medicine from September 2022 to November 2023 were included. Those with -0.5D < spherical equivalent (SE) < +2.0D were included in the non-myopia group (150 eyes), those with -3.0D < SE ≤ -0.5D were included in the low myopia group (246 eyes), and those with SE ≤ -3.0D were included in the moderate-to-high myopia group (60 eyes). All subjects underwent cycloplegic refraction, IOLmaster500, and Wide-field SS-OCTA (to exclude some peripheral retinal degeneration). Multiple linear regression analysis was used to analyze the correlation between macular ETDRS subfield of full retinal thickness (FRT), outer, inner retinal thickness (ORT, IRT), retinal vessel density (VD), deep and superficial retinal vessel density (DVD, SVD), and SE, axial length (AL). RESULTS: There were statistically significant differences (P < 0.05) in FRT in the central fovea (1 mm diameter)and perifovea (Diameter 3 to 6 mm) among the non-myopia group, low myopia group, and moderate-to-high myopia group. The three groups also showed statistically significant differences (P < 0.05) in VD in the central fovea and parafovea with a diameter of 1 to 3 mm (except the lower part). In multiple linear regression analysis adjusted for gender and age, SE and AL were found to be correlated with FRT in all ETDRS regions (except the central fovea) (P < 0.01), and SE and AL were correlated with IRT in the central fovea and perifovea, respectively (ß range -2.302 to 1.652; P < 0.05). SE and AL were also correlated with ORT in the parafovea and perifovea, respectively (ß range -4.371 to -2.344; P < 0.05). AL was negatively correlated with VD in the central fovea and parafovea (except the inferior region) (P < 0.05), as well as with DVD in all ETDRS regions (ß range -1.314 to -1.031; P < 0.05). AL was only negatively correlated with SVD in the parafoveal nasal region (ß = -0.633, P < 0.05). Additionally, the correlation between AL and DVD, ORT was higher than that with SVD, IRT. CONCLUSION: The more severe the myopia, the longer the AL, the thinner the FRT in the perifovea, and the lower the VD in both the fovea and parafovea in children. In addition, DVD and ORT were more significantly correlated with AL, suggesting that they may be more closely related to the growth of AL.
Asunto(s)
Miopía , Vasos Retinianos , Tomografía de Coherencia Óptica , Humanos , Estudios Transversales , Adolescente , Tomografía de Coherencia Óptica/métodos , Niño , Masculino , Femenino , Miopía/fisiopatología , Preescolar , Vasos Retinianos/diagnóstico por imagen , Vasos Retinianos/patología , Angiografía con Fluoresceína/métodosRESUMEN
PURPOSE: This cross-sectional optical coherence tomography angiography (OCTA) study aimed to assess the macular and optic nerve head (ONH) vascular density, foveal avascular zone, and outer retina and choriocapillaris flow in oligoarticular juvenile idiopathic arthritis (oJIA). STUDY DESIGN: Prospective. METHODS: Twenty-two eyes of 22 oJIA patients with uveitis (oJIA-U), 20 eyes of 20 oJIA patients without uveitis (isolated oJIA), and 26 healthy volunteers of similar ages and sexes were investigated. The superficial capillary plexus (SCP) and deep capillary plexus (DCP), ONH, foveal avascular zone (FAZ) parameters, the flow area of the outer retina, and choriocapillaris were evaluated. RESULTS: Compared with the control group, both the oJIA-U group and isolated oJIA group showed significantly decreased vessel density of parafovea (p = 0.031 and p = 0.047, respectively) in DCP. Choriocapillaris flow area at 1 mm radius was significantly lower in the oJIA-U group compared to the control group (p = 0.001). Choriocapillaris flow area at 2- and 3-mm radius were significantly lower in the oJIA-U group compared to the control group (p < 0.001, for both) and isolated oJIA-U group compared to the control group (p = 0.008 and p = 0.001, respectively). The VD and thickness parameters of SCP and ONH, FAZ, and outer retina flow area were similar between the groups. CONCLUSIONS: oJIA patients with and without uveitis revealed a decreased vessel density in the deep parafoveal region and choriocapillaris flow. Our findings suggest that retinal choroidal microvascular changes could be evident in oJIA-U patients without posterior segment involvement as well as oJIA patients without uveitis.
Asunto(s)
Artritis Juvenil , Coroides , Angiografía con Fluoresceína , Fondo de Ojo , Vasos Retinianos , Tomografía de Coherencia Óptica , Uveítis , Humanos , Femenino , Masculino , Artritis Juvenil/fisiopatología , Artritis Juvenil/complicaciones , Coroides/irrigación sanguínea , Coroides/diagnóstico por imagen , Tomografía de Coherencia Óptica/métodos , Vasos Retinianos/fisiopatología , Vasos Retinianos/diagnóstico por imagen , Vasos Retinianos/patología , Estudios Prospectivos , Angiografía con Fluoresceína/métodos , Estudios Transversales , Uveítis/fisiopatología , Uveítis/diagnóstico , Adolescente , Niño , Flujo Sanguíneo Regional/fisiología , Disco Óptico/irrigación sanguínea , Adulto Joven , Agudeza Visual/fisiología , AdultoRESUMEN
Accurate segmentation of retinal vessels in fundus images is of great importance for the diagnosis of numerous ocular diseases. However, due to the complex characteristics of fundus images, such as various lesions, image noise and complex background, the pixel features of some vessels have significant differences, which makes it easy for the segmentation networks to misjudge these vessels as noise, thus affecting the accuracy of the overall segmentation. Therefore, accurately segment retinal vessels in complex situations is still a great challenge. To address the problem, a partial class activation mapping guided graph convolution cascaded U-Net for retinal vessel segmentation is proposed. The core idea of the proposed network is first to use the partial class activation mapping guided graph convolutional network to eliminate the differences of local vessels and generate feature maps with global consistency, and subsequently these feature maps are further refined by segmentation network U-Net to achieve better segmentation results. Specifically, a new neural network block, called EdgeConv, is stacked multiple layers to form a graph convolutional network to realize the transfer an update of information from local to global, so as gradually enhance the feature consistency of graph nodes. Simultaneously, in an effort to suppress the noise information that may be transferred in graph convolution and thus reduce adverse effects of noise on segmentation results, the partial class activation mapping is introduced. The partial class activation mapping can guide the information transmission between graph nodes and effectively activate vessel feature through classification labels, thereby improving the accuracy of segmentation. The performance of the proposed method is validated on four different fundus image datasets. Compared with existing state-of-the-art methods, the proposed method can improve the integrity of vessel to a certain extent when the pixel features of local vessels are significantly different, caused by objective factors such as inappropriate illumination and exudates. Moreover, the proposed method shows robustness when segmenting complex retinal vessels.