RESUMEN
Purpose: This study aimed to investigate the impact of distinctive capillary-large vessel (CLV) analysis in optical coherence tomography angiography (OCTA) on the classification performance of diabetic retinopathy (DR). Methods: This multicenter study analyzed 212 OCTA images from 146 patients, including 28 controls, 36 diabetic patients without DR (NoDR), 31 with mild non-proliferative DR (NPDR), 28 with moderate NPDR, and 23 with severe NPDR. Quantitative features were derived from the whole image as well as the parafovea and perifovea regions. A support vector machine classifier was employed for DR classification. The accuracy and area under the receiver operating characteristic curve were used to evaluate the classification performance, utilizing features derived from the whole image and specific regions, both before and after CLV analysis. Results: Differential CLV analysis significantly improved OCTA classification of DR. In binary classifications, accuracy improved by 11.81%, rising from 77.45% to 89.26%, when utilizing whole image features. For multiclass classifications, accuracy increased by 7.55%, from 78.68% to 86.23%. Incorporating features from the whole image, parafovea, and perifovea further improved binary classification accuracy from 83.07% to 93.80%, and multiclass accuracy from 82.64% to 87.92%. Conclusions: This study demonstrated that feature changes in capillaries are more sensitive during DR progression, and CLV analysis can significantly improve DR classification performance by extracting features that are specific to large vessels and capillaries in OCTA. Incorporating regional features further improves DR classification accuracy. Differential CLV analysis promises better disease screening, diagnosis, and treatment outcome assessment.
Asunto(s)
Capilares , Retinopatía Diabética , Angiografía con Fluoresceína , Curva ROC , Vasos Retinianos , Tomografía de Coherencia Óptica , Humanos , Retinopatía Diabética/clasificación , Retinopatía Diabética/diagnóstico , Retinopatía Diabética/diagnóstico por imagen , Tomografía de Coherencia Óptica/métodos , Femenino , Capilares/patología , Capilares/diagnóstico por imagen , Masculino , Vasos Retinianos/diagnóstico por imagen , Vasos Retinianos/patología , Persona de Mediana Edad , Angiografía con Fluoresceína/métodos , Anciano , Estudios Retrospectivos , Fondo de Ojo , AdultoRESUMEN
This study investigates the impact of differential artery-vein (AV) analysis in optical coherence tomography angiography (OCTA) on machine learning classification of diabetic retinopathy (DR). Leveraging deep learning for arterial-venous area (AVA) segmentation, six quantitative features, including perfusion intensity density (PID), blood vessel density (BVD), vessel area flux (VAF), blood vessel caliber (BVC), blood vessel tortuosity (BVT), and vessel perimeter index (VPI) features, were derived from OCTA images before and after AV differentiation. A support vector machine (SVM) classifier was utilized to assess both binary and multiclass classifications of control, diabetic patients without DR (NoDR), mild DR, moderate DR, and severe DR groups. Initially, one-region features, i.e., quantitative features extracted from the entire OCTA, were evaluated for DR classification. Differential AV analysis improved classification accuracies from 78.86% to 87.63% and from 79.62% to 85.66% for binary and multiclass classifications, respectively. Additionally, three-region features derived from the entire image, parafovea, and perifovea, were incorporated for DR classification. Differential AV analysis further enhanced classification accuracies from 84.43% to 93.33% and from 83.40% to 89.25% for binary and multiclass classifications, respectively. These findings highlight the potential of differential AV analysis in augmenting disease diagnosis and treatment assessment using OCTA.
RESUMEN
Significance: Retinopathy of prematurity (ROP) poses a significant global threat to childhood vision, necessitating effective screening strategies. This study addresses the impact of color channels in fundus imaging on ROP diagnosis, emphasizing the efficacy and safety of utilizing longer wavelengths, such as red or green for enhanced depth information and improved diagnostic capabilities. Aim: This study aims to assess the spectral effectiveness in color fundus photography for the deep learning classification of ROP. Approach: A convolutional neural network end-to-end classifier was utilized for deep learning classification of normal, stage 1, stage 2, and stage 3 ROP fundus images. The classification performances with individual-color-channel inputs, i.e., red, green, and blue, and multi-color-channel fusion architectures, including early-fusion, intermediate-fusion, and late-fusion, were quantitatively compared. Results: For individual-color-channel inputs, similar performance was observed for green channel (88.00% accuracy, 76.00% sensitivity, and 92.00% specificity) and red channel (87.25% accuracy, 74.50% sensitivity, and 91.50% specificity), which is substantially outperforming the blue channel (78.25% accuracy, 56.50% sensitivity, and 85.50% specificity). For multi-color-channel fusion options, the early-fusion and intermediate-fusion architecture showed almost the same performance when compared to the green/red channel input, and they outperformed the late-fusion architecture. Conclusions: This study reveals that the classification of ROP stages can be effectively achieved using either the green or red image alone. This finding enables the exclusion of blue images, acknowledged for their increased susceptibility to light toxicity.
Asunto(s)
Aprendizaje Profundo , Fotograbar , Retinopatía de la Prematuridad , Retinopatía de la Prematuridad/diagnóstico por imagen , Retinopatía de la Prematuridad/clasificación , Humanos , Recién Nacido , Fotograbar/métodos , Fondo de Ojo , Interpretación de Imagen Asistida por Computador/métodos , Redes Neurales de la Computación , ColorRESUMEN
The flexible and conformal interconnects for electronic systems as a potential signal transmission device have great prospects in body-worn or wearable applications. High-efficiency wave propagation and conformal structure deformation around human body at radio communication are still confronted with huge challenges due to the lack of methods to control the wave propagation and achieve the deformable structure simultaneously. Here, inspired by the kirigami technology, a new paradigm to construct spoof plasmonic interconnects (SPIs) that support radiofrequency (RF) surface plasmonic transmission is proposed, together with high elasticity, strong robustness, and multifunction performance. Leveraging the strong field-confinement characteristic of spoof surface plasmons polaritons, the Type-I SPI opens its high-efficiency transmission band after stretching from a simply connected metallic surface. Meanwhile, the broadband transmission of the kirigami-based SPI exhibits strong robustness and excellent stability undergoing complex deformations, i.e., bending, twisting, and stretching. In addition, the prepared Type-II SPI consisting of 2 different subunit cells can achieve band-stop transmission characteristics, with its center frequency dynamically tunable by stretching the buckled structure. Experimental measurements verify the on-off switching performance in kirigami interconnects triggered by stretching. Overcoming the mechanical limitation of rigid structure with kirigami technology, the designer SPIs exhibit high stretchability through out-of-plane structure deformation. Such kirigami-based interconnects can improve the elastic functionality of wearable RF electronics and offer high compatibility to large body motion in future body network systems.
RESUMEN
BACKGROUND: Reliable differentiation of uveal melanoma and choroidal nevi is crucial to guide appropriate treatment, preventing unnecessary procedures for benign lesions and ensuring timely treatment for potentially malignant cases. The purpose of this study is to validate deep learning classification of uveal melanoma and choroidal nevi, and to evaluate the effect of colour fusion options on the classification performance. METHODS: A total of 798 ultra-widefield retinal images of 438 patients were included in this retrospective study, comprising 157 patients diagnosed with UM and 281 patients diagnosed with choroidal naevus. Colour fusion options, including early fusion, intermediate fusion and late fusion, were tested for deep learning image classification with a convolutional neural network (CNN). F1-score, accuracy and the area under the curve (AUC) of a receiver operating characteristic (ROC) were used to evaluate the classification performance. RESULTS: Colour fusion options were observed to affect the deep learning performance significantly. For single-colour learning, the red colour image was observed to have superior performance compared to green and blue channels. For multi-colour learning, the intermediate fusion is better than early and late fusion options. CONCLUSION: Deep learning is a promising approach for automated classification of uveal melanoma and choroidal nevi. Colour fusion options can significantly affect the classification performance.
RESUMEN
The purpose of this study is to verify the effect of anisotropic property of retinal biomechanics on vasodilation measurement. A custom-built optical coherence tomography (OCT) was used for time-lapse imaging of flicker stimulation-evoked vessel lumen changes in mouse retinas. A comparative analysis revealed significantly larger (18.21%) lumen dilation in the axial direction compared to the lateral (10.77%) direction. The axial lumen dilation predominantly resulted from the top vessel wall movement toward the vitreous direction, whereas the bottom vessel wall remained stable. This observation indicates that the traditional vasodilation measurement in the lateral direction may result in an underestimated value.
Asunto(s)
Tomografía de Coherencia Óptica , Vasodilatación , Animales , Ratones , Vasodilatación/fisiología , Tomografía de Coherencia Óptica/métodos , Estimulación Luminosa/métodos , Retina/diagnóstico por imagen , Retina/fisiología , Vasos Retinianos/diagnóstico por imagen , Vasos Retinianos/fisiologíaRESUMEN
Dysfunction of cerebral endothelial cells (CECs) has been implicated in the pathology of Alzheimer's disease (AD). Despite evidence showing cytotoxic effects of oligomeric amyloid-ß (oAß) and Tau (oTau) in the central nervous system, their direct effects on CECs have not been fully investigated. In this study, we examined the direct effects of oAß, oTau, and their combination on cell adhesion properties and inflammatory responses in CECs. We found that both oAß and oTau increased cell stiffness, as well as the p-selectin/Sialyl-LewisX (sLeX) bonding-mediated membrane tether force and probability of adhesion in CECs. Consistent with these biomechanical alterations, treatments with oAß or oTau also increased actin polymerization and the expression of p-selectin at the cell surface. These toxic oligomeric peptides also triggered inflammatory responses, including upregulations of p-NF-kB p65, IL-1ß, and TNF-α. In addition, they rapidly activated the RhoA/ROCK pathway. These biochemical and biomechanical changes were further enhanced by the treatment with the combination of oAß and oTau, which were significantly suppressed by Fasudil, a specific inhibitor for the RhoA/ROCK pathway. In conclusion, our data suggest that oAß, oTau, and their combination triggered subcellular mechanical alterations and inflammatory responses in CECs through the RhoA/ROCK pathway.
RESUMEN
Purpose: The purpose of this study was to investigate the spectral characteristics of choroidal nevi and assess the feasibility of quantifying the basal diameter of choroidal nevi using multispectral fundus images captured with trans-palpebral illumination. Methods: The study used a widefield fundus camera with multispectral (625 nm, 780 nm, 850 nm, and 970 nm) trans-palpebral illumination to examine eight subjects diagnosed with choroidal nevi. Geometric features of nevi, including border clarity, overlying drusen, and lesion basal diameter, were characterized. Clinical imagers, including scanning laser ophthalmoscopy (SLO), autofluorescence (AF), and optical coherence tomography (OCT), were utilized for comparative assessment. Results: Fundus images depicted nevi as dark regions with high contrast against the background. Near-infrared (NIR) fundus images provided enhanced visibility of lesion borders compared to visible fundus images and SLO images. Lesion-background contrast measurements revealed 635 nm SLO at 11% and 625 nm fundus at 42%. Significantly enhanced contrasts were observed in NIR fundus images at 780 nm (73%), 850 nm (63%), and 970 nm (67%). For quantifying the diameter of nevi, NIR fundus images at 780 nm and 850 nm yielded a deviation of less than 10% when compared to OCT measurements. Conclusions: NIR fundus photography with trans-palpebral illumination enhances nevi visibility and boundary definition compared to SLO. Agreement in diameter measurements with OCT validates the accuracy and reliability of this method for choroidal nevi assessment. Translational Relevance: Multispectral fundus imaging with trans-palpebral illumination improves choroidal nevi visibility and accurately measures basal diameter, promising to enhance clinical practices in screening, diagnosis, and monitoring of choroidal nevi.
Asunto(s)
Neoplasias de la Coroides , Nevo Pigmentado , Nevo , Neoplasias Cutáneas , Humanos , Iluminación , Reproducibilidad de los Resultados , Nevo Pigmentado/diagnóstico por imagen , Nevo Pigmentado/patología , Neoplasias de la Coroides/diagnóstico por imagen , Neoplasias de la Coroides/patología , Nevo/diagnóstico por imagen , FotograbarRESUMEN
Ultrasound A-scan is an important tool for quantitative assessment of ocular lesions. However, its usability is limited by the difficulty of accurately localizing the ultrasound probe to a lesion of interest. In this study, a transparent LiNbO3 single crystal ultrasound transducer was fabricated, and integrated with a widefield fundus camera to guide the ultrasound local position. The electrical impedance, phase spectrum, pulse-echo performance, and optical transmission spectrum of the ultrasound transducer were validated. The novel fundus camera-guided ultrasound probe was tested for in vivo measurement of rat eyes. Anterior and posterior segments of the rat eye could be unambiguously differentiated with the fundus photography-guided ultrasound measurement. A model eye was also used to verify the imaging performance of the prototype device in the human eye. The prototype shows the potential of being used in the clinic to accurately measure the thickness and echogenicity of ocular lesions in vivo.
Asunto(s)
Angiografía con Fluoresceína , Ratas , Animales , Humanos , Angiografía con Fluoresceína/métodos , UltrasonografíaRESUMEN
This research aims to investigate the potential of using intrinsic optical signal (IOS) optoretinography (ORG) to objectively detect dark adaptation (DA) abnormalities related to rod photoreceptor degeneration. Functional optical coherence tomography (OCT) was employed in both wild-type (WT) and retinal degeneration 10 (rd10) mice to conduct this assessment. Dynamic OCT measurements captured the changes in retinal thickness and reflectance from light-to-dark transition. Comparative analysis revealed significant IOS alterations within the outer retina. Specifically, a reduction in thickness from external limiting membrane (ELM) peak to retinal pigment epithelium (RPE) peak was observed (WT: 1.13 ± 0.69 µm, 30 min DA; rd10: 2.64 ± 0.86 µm, 30 min DA), as well as a decrease in the intensity of the inner segment ellipsoid zone (EZ) in 30 min DA compared to light adaptation (LA). The reduction of relative EZ intensity was notable in rd10 after 5 min DA and in WT after 15 min DA, with a distinguishable difference between rd10 and WT after 10 min DA. Furthermore, our findings indicated a significant decrease in the relative intensity of the hypo-reflective band between EZ and RPE in rd10 retinas during DA, which primarily corresponds to the outer segment (OS) region. In conclusion, the observed DA-IOS abnormalities, including changes in ELM-RPE thickness, EZ, and OS intensity, hold promise as differentiators between WT and rd10 mice before noticeable morphological abnormalities occur. These findings suggest the potential of this non-invasive imaging technique for the early detection of dysfunction in retinal photoreceptors.
Asunto(s)
Degeneración Retiniana , Ratones , Animales , Degeneración Retiniana/diagnóstico por imagen , Adaptación a la Oscuridad , Retina , Epitelio Pigmentado de la Retina/diagnóstico por imagen , Células Fotorreceptoras Retinianas BastonesRESUMEN
Vanadium-based materials, due to their diverse valence states and open-framework lattice, are promising cathodes for aqueous zinc ion batteries (AZIBs), but encounters the major challenges of in situ electrochemical activation process, potent polarity of the aqueous electrolyte and periodic expansion/contraction for efficient Zn2+ storage. Herein, architecting vanadium nitride (VN) nanosheets over titanium-based hollow nanoarrays skeletal host (denoted VNTONC) can simultaneously modulate address those challenges by creating multiple interfaces and maintaining the (1 1 1) phase of VN, which optimizes the Zn2+ storage and the stability of VN. Benefiting from the modulated crystalline thermodynamics during the electrochemical activation of VN, two outcomes are achieved; I) the cathode transforms into a nanocrystalline structure with increased active sites and higher conductivity and; II) a significant portion of the (1 1 1) crystal facets is retained in the process leading to the additional Zn2+ storage capacity. As a result, the as-prepared VNTONC electrode demonstrates remarkable discharge capacities of 802.5 and 331.8 mAh g-1 @ 0.5 and 6.0 A g-1, respectively, due to the enhanced kinetics as validated by theoretical calculations. The assembled VNTONC||Zn flexible ZIB demonstrates excellent Zn storage properties up to 405.6 mAh g-1, and remarkable robustness against extreme operating conditions.
RESUMEN
Purpose: To investigate the spectral characteristics of choroidal nevi and assess the feasibility of quantifying the basal diameter of choroidal nevi using multispectral fundus images captured with trans-palpebral illumination. Methods: The study employed a widefield fundus camera with multispectral (625 nm, 780 nm, 850 nm, and 970 nm) trans-palpebral illumination. Geometric features of choroidal nevi, including border clarity, overlying drusen, and lesion basal diameter, were characterized. Clinical imagers, including scanning laser ophthalmoscopy (SLO), autofluorescence (AF), and optical coherence tomography (OCT), were utilized for comparative assessment. Results: Fundus images captured with trans-palpebral illumination depicted nevi as dark regions with high contrast against the background. Near-infrared (NIR) fundus images provided enhanced visibility of lesion borders compared to visible light fundus images and SLO images. Lesion-background contrast measurements revealed 635 nm SLO at 11% and 625 nm fundus at 42%. Significantly enhanced contrasts were observed in NIR fundus images at 780 nm (73%), 850 nm (63%), and 970 nm (67%). For quantifying the basal diameter of nevi, NIR fundus images at 780 nm and 850 nm yielded a deviation of less than 10% when compared to OCT B-scan measurements. Conclusion: NIR fundus photography with trans-palpebral illumination enhances nevi visibility and boundary definition compared to SLO. Agreement in basal diameter measurements with OCT validates the accuracy and reliability of this method for choroidal nevi assessment.
RESUMEN
Flexible lithium-ion batteries (FLIBs) are intensively studied using free-standing transition metal oxides (TMOs)-based anode materials. However, achieving high areal capacity TMO-based anode materials is yet to be effectively elucidated owing to the poor adhesion of the active materials to the flexible substrate resulting in low active mass loading, and hence low areal capacity is realized. Herein, a novel monolithic rutile TiO2 microparticles on carbon cloth (ATO/CC) that facilitate the flower-like arrangement of TiO2 nanowires (denoted ATO/CC/OTO) is demonstrated as high areal capacity anode for FLIBs. The optimized ATO/CC/OTO anode exhibits high areal capacity (5.02 mAh cm-2@0.4 mA cm-2) excellent rate capability (1.17 mAh cm-2@5.0 mA cm-2) and remarkable cyclic stability (over 500 cycles). A series of morphological, kinetic, electrochemical, in situ Raman, and theoretical analyses reveal that the rational phase boundaries between the microparticles and nanowires contribute to promoting the Li storage activity. Furthermore, a 16.0 cm2 all-FLIB pouch cell assembled based on the ATO/CC/OTO anode and LiNiCoMnO2 cathode coated on ATO/CC (ATO/CC/LNCM) exhibits impressive flexibility under different folding conditions, creating opportunity for the development of high areal capacity anodes in future flexible energy storage devices.
RESUMEN
The current development of single electrocatalyst with multifunctional applications in overall water splitting (OWS) and zinc-air batteries (ZABs) is crucial for sustainable energy conversion and storage systems. However, exploring new and efficient low-cost trifunctional electrocatalysts is still a significant challenge. Herein, the antiperovskite CuNCo3 prototype, that is proved to be highly efficient in oxygen evolution reaction but severe hydrogen evolution reaction (HER) performance, is endowed with optimum HER catalytic properties by in situ-derived interfacial engineering via incorporation of molybdenum (Mo). The as-prepared Mo-CuNCo3 @CoN nanowires achieve a low HER overpotential of 58 mV@10 mA cm-2 , which is significantly higher than the pristine CuNCo3 . The assembled CuNCo3 -antiperovskite-based OWS not only entails a low overall voltage of 1.56 V@10 mA cm-2 , comparable to most recently reported metal-nitride-based OWS, but also exhibits excellent ZAB cyclic stability up to 310 h, specific capacity of 819.2 mAh g-1 , and maximum power density of 102 mW cm-2 . The as-designed antiperovskite-based ZAB could self-power the OWS system generating a high hydrogen rate, and creating opportunity for developing integrated portable multifunctional energy devices.
RESUMEN
Background: Reliable differentiation of uveal melanoma and choroidal nevi is crucial to guide appropriate treatment, preventing unnecessary procedures for benign lesions and ensuring timely treatment for potentially malignant cases. The purpose of this study is to validate deep learning classification of uveal melanoma and choroidal nevi, and to evaluate the effect of color fusion options on the classification performance. Methods: A total of 798 ultra-widefield retinal images of 438 patients were included in this retrospective study, comprising 157 patients diagnosed with UM and 281 patients diagnosed with choroidal nevus. Color fusion options, including early fusion, intermediate fusion and late fusion, were tested for deep learning image classification with a convolutional neural network (CNN). Specificity, sensitivity, F1-score, accuracy, and the area under the curve (AUC) of a receiver operating characteristic (ROC) were used to evaluate the classification performance. The saliency map visualization technique was used to understand the areas in the image that had the most influence on classification decisions of the CNN. Results: Color fusion options were observed to affect the deep learning performance significantly. For single-color learning, the red color image was observed to have superior performance compared to green and blue channels. For multi-color learning, the intermediate fusion is better than early and late fusion options. Conclusion: Deep learning is a promising approach for automated classification of uveal melanoma and choroidal nevi, and color fusion options can significantly affect the classification performance.
RESUMEN
Multi-spectral widefield fundus photography is valuable for the clinical diagnosis and management of ocular conditions that may impact both central and peripheral regions of the retina and choroid. Trans-palpebral illumination has been demonstrated as an alternative to transpupillary illumination for widefield fundus photography without requiring pupil dilation. However, spectral efficiency can be complicated due to the spatial variance of the light property through the palpebra and sclera. This study aims to investigate the effect of light delivery location on spectral efficiency in trans-palpebral illumination. Four narrow-band light sources, covering both visible and near infrared (NIR) wavelengths, were used to evaluate spatial dependency of spectral illumination efficiency. Comparative analysis indicated a significant dependence of visible light efficiency on spatial location, while NIR light efficiency is only slightly affected by the illumination location. This study confirmed the pars plana as the optimal location for delivering visible light to achieve color imaging of the retina. Conversely, spatial location is not critical for NIR light imaging of the choroid.
RESUMEN
The purpose of this study is to demonstrate the feasibility of using polarization maintaining photons for enhanced contrast imaging of the retina. Orthogonal-polarization control has been frequently used in conventional fundus imaging systems to minimize reflection artifacts. However, the orthogonal-polarization configuration also rejects the directly reflected photons, which preserve the polarization condition of incident light, from the superficial layer of the fundus, i.e., the retina, and thus reduce the contrast of retinal imaging. We report here a portable fundus camera which can simultaneously perform orthogonal-polarization control to reject back-reflected light from the ophthalmic lens and parallel-polarization control to preserve the backscattered light from the retina which partially maintains the polarization state of the incoming light. This portable device utilizes miniaturized indirect ophthalmoscopy illumination to achieve non-mydriatic imaging, with a snapshot field of view of 101° eye-angle (67° visual-angle). Comparative analysis of retinal images acquired with a traditional orthogonal-polarization fundus camera from both normal and diseased eyes was conducted to validate the usefulness of the proposed design. The parallel-polarization control for enhanced contrast in high dynamic range imaging has also been validated.
RESUMEN
The purpose of this study is to evaluate layer fusion options for deep learning classification of optical coherence tomography (OCT) angiography (OCTA) images. A convolutional neural network (CNN) end-to-end classifier was utilized to classify OCTA images from healthy control subjects and diabetic patients with no retinopathy (NoDR) and non-proliferative diabetic retinopathy (NPDR). For each eye, three en-face OCTA images were acquired from the superficial capillary plexus (SCP), deep capillary plexus (DCP), and choriocapillaris (CC) layers. The performances of the CNN classifier with individual layer inputs and multi-layer fusion architectures, including early-fusion, intermediate-fusion, and late-fusion, were quantitatively compared. For individual layer inputs, the superficial OCTA was observed to have the best performance, with 87.25% accuracy, 78.26% sensitivity, and 90.10% specificity, to differentiate control, NoDR, and NPDR. For multi-layer fusion options, the best option is the intermediate-fusion architecture, which achieved 92.65% accuracy, 87.01% sensitivity, and 94.37% specificity. To interpret the deep learning performance, the Gradient-weighted Class Activation Mapping (Grad-CAM) was utilized to identify spatial characteristics for OCTA classification. Comparative analysis indicates that the layer data fusion options can affect the performance of deep learning classification, and the intermediate-fusion approach is optimal for OCTA classification of DR.
RESUMEN
Neuronal hyperexcitability promises an early biomarker of Alzheimer's disease (AD). However, in vivo detection of neuronal hyperexcitability in the brain is technically challenging. The retina, one part of the central nervous system, presents a unique window for noninvasive monitoring of the brain function. This study aims to test the feasibility of using intrinsic signal optoretinography (ORG) for mapping retinal hyperexcitability associated with early-stage AD. Custom-designed optical coherence tomography (OCT) was employed for both morphological measurement and functional ORG of wild-type mice and 3xTg-AD mice. Comparative analysis revealed AD-induced retinal photoreceptor hyperexcitability prior to detectable structural degeneration.
Asunto(s)
Enfermedad de Alzheimer , Ratones , Animales , Enfermedad de Alzheimer/diagnóstico por imagen , Retina/diagnóstico por imagen , Células Fotorreceptoras de Vertebrados , Encéfalo , Tomografía de Coherencia ÓpticaRESUMEN
Major retinopathies can differentially impact the arteries and veins. Traditional fundus photography provides limited resolution for visualizing retinal vascular details. Optical coherence tomography (OCT) can provide improved resolution for retinal imaging. However, it cannot discern capillary-level structures due to the limited image contrast. As a functional extension of OCT modality, optical coherence tomography angiography (OCTA) is a non-invasive, label-free method for enhanced contrast visualization of retinal vasculatures at the capillary level. Recently differential artery-vein (AV) analysis in OCTA has been demonstrated to improve the sensitivity for staging of retinopathies. Therefore, AV classification is an essential step for disease detection and diagnosis. However, current methods for AV classification in OCTA have employed multiple imagers, that is, fundus photography and OCT, and complex algorithms, thereby making it difficult for clinical deployment. On the contrary, deep learning (DL) algorithms may be able to reduce computational complexity and automate AV classification. In this article, we summarize traditional AV classification methods, recent DL methods for AV classification in OCTA, and discuss methods for interpretability in DL models.