-
BMC Ophthalmology Jun 2024Glaucoma is a worldwide eye disease that can cause irreversible vision loss. Early detection of glaucoma is important to reduce vision loss, and retinal fundus image...
BACKGROUND
Glaucoma is a worldwide eye disease that can cause irreversible vision loss. Early detection of glaucoma is important to reduce vision loss, and retinal fundus image examination is one of the most commonly used solutions for glaucoma diagnosis due to its low cost. Clinically, the cup-disc ratio of fundus images is an important indicator for glaucoma diagnosis. In recent years, there have been an increasing number of algorithms for segmentation and recognition of the optic disc (OD) and optic cup (OC), but these algorithms generally have poor universality, segmentation performance, and segmentation accuracy.
METHODS
By improving the YOLOv8 algorithm for segmentation of OD and OC. Firstly, a set of algorithms was designed to adapt the REFUGE dataset's result images to the input format of the YOLOv8 algorithm. Secondly, in order to improve segmentation performance, the network structure of YOLOv8 was improved, including adding a ROI (Region of Interest) module, modifying the bounding box regression loss function from CIOU to Focal-EIoU. Finally, by training and testing the REFUGE dataset, the improved YOLOv8 algorithm was evaluated.
RESULTS
The experimental results show that the improved YOLOv8 algorithm achieves good segmentation performance on the REFUGE dataset. In the OD and OC segmentation tests, the F1 score is 0.999.
CONCLUSIONS
We improved the YOLOv8 algorithm and applied the improved model to the segmentation task of OD and OC in fundus images. The results show that our improved model is far superior to the mainstream U-Net model in terms of training speed, segmentation performance, and segmentation accuracy.
Topics: Optic Disk; Humans; Algorithms; Fundus Oculi; Glaucoma
PubMed: 38943095
DOI: 10.1186/s12886-024-03532-4 -
Frontiers in Veterinary Science 2024A spayed, 8-year-old female Poodle, weighing 5.7 kg, was presented with the chief complaint of vision impairment. Vision assessment, including pupillary light...
Case report: Unilateral papilledema in a dog with a large suprasellar mass and suspected intracranial hypertension: insights from funduscopy, optical coherence tomography, and magnetic resonance imaging.
A spayed, 8-year-old female Poodle, weighing 5.7 kg, was presented with the chief complaint of vision impairment. Vision assessment, including pupillary light reflexes, menace response, dazzle reflex, and maze navigation in photopic and scotopic circumstances, revealed a negative response in both eyes except for positive direct pupillary light reflex in the right eye and positive consensual pupillary light reflex from the right eye to the left eye. Systemic evaluation, including neurologic status, blood profile, and thoracic radiographs, did not reveal any abnormalities. Complete ophthalmic examinations, ocular ultrasonography, and electroretinography did not identify a cause of blindness. Upon funduscopy, the left eye exhibited an increased optic disk diameter, blurred optic disk borders, and loss of the physiologic pit, as well as an increase in vascular tortuosity. In the right eye, there were multifocal depigmented areas in the non-tapetal fundus and several pigmented spots surrounded by a region of dull tapetal reflection in the tapetal fundus. The optical coherence tomography revealed severe anterior deformation of the optic nerve head and Bruch's membrane in the peripapillary region of the left eye. Magnetic resonance imaging revealed an irregular, broad-based suprasellar mass, with features suggestive of intracranial hypertension, including dorsal displacement of third ventricles, a rightward shift of the falx cerebri, -tentorial herniation, perilesional edema, flattening/protrusion of the posterior sclera, and lager optic nerve sheath diameter in left side than right side. This is the first comprehensive report that describes unilateral papilledema in a dog with a brain tumor, using advanced ophthalmic and neuro-imaging modalities.
PubMed: 38933701
DOI: 10.3389/fvets.2024.1372802 -
Visual Field Prognosis From Macula and Circumpapillary Spectral Domain Optical Coherence Tomography.Translational Vision Science &... Jun 2024To explore the structural-functional loss relationship from optic-nerve-head- and macula-centred spectral-domain (SD) Optical Coherence Tomography (OCT) images in the...
PURPOSE
To explore the structural-functional loss relationship from optic-nerve-head- and macula-centred spectral-domain (SD) Optical Coherence Tomography (OCT) images in the full spectrum of glaucoma patients using deep-learning methods.
METHODS
A cohort comprising 5238 unique eyes classified as suspects or diagnosed with glaucoma was considered. All patients underwent ophthalmologic examination consisting of standard automated perimetry (SAP), macular OCT, and peri-papillary OCT on the same day. Deep learning models were trained to estimate G-pattern visual field (VF) mean deviation (MD) and cluster MD using retinal thickness maps from seven layers: retinal nerve fiber layer (RNFL), ganglion cell layer and inner plexiform layer (GCL + IPL), inner nuclear layer and outer plexiform layer (INL + OPL), outer nuclear layer (ONL), photoreceptors and retinal pigmented epithelium (PR + RPE), choriocapillaris and choroidal stroma (CC + CS), total retinal thickness (RT).
RESULTS
The best performance on MD prediction is achieved by RNFL, GCL + IPL and RT layers, with R2 scores of 0.37, 0.33, and 0.31, respectively. Combining macular and peri-papillary scans outperforms single modality prediction, achieving an R2 value of 0.48. Cluster MD predictions show promising results, notably in central clusters, reaching an R2 of 0.56.
CONCLUSIONS
The combination of multiple modalities, such as optic-nerve-head circular B-scans and retinal thickness maps from macular SD-OCT images, improves the performance of MD and cluster MD prediction. Our proposed model demonstrates the highest level of accuracy in predicting MD in the early-to-mid stages of glaucoma.
TRANSLATIONAL RELEVANCE
Objective measures recorded with SD-OCT can optimize the number of visual field tests and improve individualized glaucoma care by adjusting VF testing frequency based on deep-learning estimates of functional damage.
Topics: Tomography, Optical Coherence; Humans; Female; Middle Aged; Male; Visual Fields; Macula Lutea; Prognosis; Deep Learning; Aged; Retinal Ganglion Cells; Glaucoma; Nerve Fibers; Visual Field Tests; Optic Disk
PubMed: 38884547
DOI: 10.1167/tvst.13.6.10 -
BMC Ophthalmology Jun 2024Quantitative analysis of retinal nerve fibers is important for the diagnosis and treatment of optic nerve diseases. Peripapillary retinal nerve fiber layer (RNFL)...
BACKGROUND
Quantitative analysis of retinal nerve fibers is important for the diagnosis and treatment of optic nerve diseases. Peripapillary retinal nerve fiber layer (RNFL) cross-sectional area may give a more accurate quantitative assessment of retinal nerve fibers than RNFL thickness but there have been no previous reports of the peripapillary RNFL cross-sectional area or other parameters. The purpose of the current study was to determine peripapillary RNFL cross-sectional area and its association with other factors in an adult Chinese population.
METHODS
RNFL cross-sectional area was measured during peripapillary circular optical coherence tomography (OCT) scan with a diameter of 12° centered on the optic disc. Correlation between RNFL cross-sectional area and other parameters was evaluated by linear regression analysis in a cross-sectional study of an adult Chinese population.
RESULTS
A total of 2404 eyes from 2404 subjects were examined. Multivariate linear regression analysis showed that larger RNFL cross-sectional area correlated with younger age (p < 0.001), female gender (p = 0.001), no history of diabetes (p = 0.012) and larger optic disc area (p < 0.001).
CONCLUSIONS
Peripapillary RNFL cross-sectional area is correlated positively with optic disc area, suggesting that eyes with larger optic discs have thicker RNFL. Further studies are needed to confirm whether this correlation is due to differences in the numbers of retinal nerve fibers or other factors.
Topics: Adult; Aged; Female; Humans; Male; Middle Aged; Young Adult; China; Cross-Sectional Studies; East Asian People; Nerve Fibers; Optic Disk; Retinal Ganglion Cells; Tomography, Optical Coherence
PubMed: 38880871
DOI: 10.1186/s12886-024-03481-y -
Mathematical Biosciences and... Mar 2024Glaucoma is a chronic neurodegenerative disease that can result in irreversible vision loss if not treated in its early stages. The cup-to-disc ratio is a key criterion...
Glaucoma is a chronic neurodegenerative disease that can result in irreversible vision loss if not treated in its early stages. The cup-to-disc ratio is a key criterion for glaucoma screening and diagnosis, and it is determined by dividing the area of the optic cup (OC) by that of the optic disc (OD) in fundus images. Consequently, the automatic and accurate segmentation of the OC and OD is a pivotal step in glaucoma detection. In recent years, numerous methods have resulted in great success on this task. However, most existing methods either have unsatisfactory segmentation accuracy or high time costs. In this paper, we propose a lightweight deep-learning architecture for the simultaneous segmentation of the OC and OD, where we have adopted fuzzy learning and a multi-layer perceptron to simplify the learning complexity and improve segmentation accuracy. Experimental results demonstrate the superiority of our proposed method as compared to most state-of-the-art approaches in terms of both training time and segmentation accuracy.
Topics: Deep Learning; Humans; Optic Disk; Glaucoma; Algorithms; Fuzzy Logic; Neural Networks, Computer; Image Processing, Computer-Assisted; Reproducibility of Results; Image Interpretation, Computer-Assisted; Fundus Oculi
PubMed: 38872528
DOI: 10.3934/mbe.2024225 -
BMC Ophthalmology Jun 2024Peripapillary hyperreflective ovoid mass-like structures (PHOMS) are newly characterized lesions wedged around the optic discs, which used to be misdiagnosed. Better...
BACKGROUND
Peripapillary hyperreflective ovoid mass-like structures (PHOMS) are newly characterized lesions wedged around the optic discs, which used to be misdiagnosed. Better understanding and identifying PHOMS are important for monitoring the condition of optic nerve.
CASE PRESENTATION
A young female presented to the ophthalmic clinic with blurred vision of both eyes. Protrusions resembling "C-shaped donut" were found circling the optic discs bilaterally. These lesions were homogenous hyperreflective on OCT, while they were also hypoautofluorescent and hypoechogenic. Meanwhile, cystoid macular edema (CME) was also identified in both eyes. The patient was then diagnosed as PHOMS with CME. A short-term glucocorticoids therapy was prescribed systemically. The logMAR best-corrected visual acuity (BCVA) of both eyes reached 0.0 in 4 months with recovery of CME, while the PHOMS remained.
CONCLUSIONS
There is currently no report on PHOMS with CME. More attentions should be paid to PHOMS, for they are potential biomarkers for axoplasmic stasis involved in different diseases of the optic nerve.
Topics: Humans; Macular Edema; Female; Tomography, Optical Coherence; Visual Acuity; Optic Disk; Adult; Glucocorticoids; Fluorescein Angiography; Optic Nerve Diseases
PubMed: 38862962
DOI: 10.1186/s12886-024-03509-3 -
Optics Express Jun 2024As the core sensing elements of ultra-long fiber interferometer, the distributed thermal strain difference of the fiber rings can cause extra noise of the flexural disk,...
As the core sensing elements of ultra-long fiber interferometer, the distributed thermal strain difference of the fiber rings can cause extra noise of the flexural disk, resulting in a penalty of the deterioration accuracy. In this paper, the thermal strain distribution characteristics of the fiber ring are firstly analyzed by the finite element method (FEM), and the distribution result is consistent with that demonstrated by the Rayleigh optical frequency-domain reflectometry (R-OFDR) strain measurement. The interferometer phase noise caused by the distributed strain difference is further studied by constructing a fully symmetric polarization-maintaining fiber-ring Mach-Zehnder interferometer (MZI) with an arm length of over 100 meters. The results show that the distributed thermal strain difference of two fiber rings will cause additional phase fluctuation, which leads to higher low-frequency noise. Therefore, a dual-fiber-ring MZI with matched distributed thermal strains is proposed to suppress the phase noise caused by the thermal strain, and the best suppression is as high as 45.6 dB. This is very important for the research and design of low noise fiber seismometer.
PubMed: 38859470
DOI: 10.1364/OE.521147 -
Investigative Ophthalmology & Visual... Jun 2024Optical coherence tomography (OCT) representations in clinical practice are static and do not allow for a dynamic visualization and quantification of blood flow. This...
PURPOSE
Optical coherence tomography (OCT) representations in clinical practice are static and do not allow for a dynamic visualization and quantification of blood flow. This study aims to present a method to analyze retinal blood flow dynamics using time-resolved structural OCT.
METHODS
We developed novel imaging protocols to acquire video-rate time-resolved OCT B-scans (1024 × 496 pixels, 10 degrees field of view) at four different sensor integration times (integration time of 44.8 µs at a nominal A-scan rate of 20 kHz, 22.4 µs at 40 kHz, 11.2 µs at 85 kHz, and 7.24 µs at 125 kHz). The vessel centers were manually annotated for each B-scan and surrounding subvolumes were extracted. We used a velocity model based on signal-to-noise ratio (SNR) drops due to fringe washout to calculate blood flow velocity profiles in vessels within five optic disc diameters of the optic disc rim.
RESULTS
Time-resolved dynamic structural OCT revealed pulsatile SNR changes in the analyzed vessels and allowed the calculation of potential blood flow velocities at all integration times. Fringe washout was stronger in acquisitions with longer integration times; however, the ratio of the average SNR to the peak SNR inside the vessel was similar across all integration times.
CONCLUSIONS
We demonstrated the feasibility of estimating blood flow profiles based on fringe washout analysis, showing pulsatile dynamics in vessels close to the optic nerve head using structural OCT. Time-resolved dynamic OCT has the potential to uncover valuable blood flow information in clinical settings.
Topics: Tomography, Optical Coherence; Humans; Retinal Vessels; Blood Flow Velocity; Regional Blood Flow; Optic Disk; Signal-To-Noise Ratio; Male; Female; Adult; Middle Aged
PubMed: 38837167
DOI: 10.1167/iovs.65.6.9 -
Translational Vision Science &... Jun 2024Deep learning architectures can automatically learn complex features and patterns associated with glaucomatous optic neuropathy (GON). However, developing robust...
PURPOSE
Deep learning architectures can automatically learn complex features and patterns associated with glaucomatous optic neuropathy (GON). However, developing robust algorithms requires a large number of data sets. We sought to train an adversarial model for generating high-quality optic disc images from a large, diverse data set and then assessed the performance of models on generated synthetic images for detecting GON.
METHODS
A total of 17,060 (6874 glaucomatous and 10,186 healthy) fundus images were used to train deep convolutional generative adversarial networks (DCGANs) for synthesizing disc images for both classes. We then trained two models to detect GON, one solely on these synthetic images and another on a mixed data set (synthetic and real clinical images). Both the models were externally validated on a data set not used for training. The multiple classification metrics were evaluated with 95% confidence intervals. Models' decision-making processes were assessed using gradient-weighted class activation mapping (Grad-CAM) techniques.
RESULTS
Following receiver operating characteristic curve analysis, an optimal cup-to-disc ratio threshold for detecting GON from the training data was found to be 0.619. DCGANs generated high-quality synthetic disc images for healthy and glaucomatous eyes. When trained on a mixed data set, the model's area under the receiver operating characteristic curve attained 99.85% on internal validation and 86.45% on external validation. Grad-CAM saliency maps were primarily centered on the optic nerve head, indicating a more precise and clinically relevant attention area of the fundus image.
CONCLUSIONS
Although our model performed well on synthetic data, training on a mixed data set demonstrated better performance and generalization. Integrating synthetic and real clinical images can optimize the performance of a deep learning model in glaucoma detection.
TRANSLATIONAL RELEVANCE
Optimizing deep learning models for glaucoma detection through integrating DCGAN-generated synthetic and real-world clinical data can be improved and generalized in clinical practice.
Topics: Deep Learning; Humans; Optic Disk; Optic Nerve Diseases; ROC Curve; Glaucoma; Female; Male; Middle Aged; Algorithms
PubMed: 38829624
DOI: 10.1167/tvst.13.6.1 -
Journal of AAPOS : the Official... May 2024A nearly 3-year-old boy on nightly dialysis presented emergently with sudden loss of vision. On examination, his visual acuity was light perception in the right eye and...
A nearly 3-year-old boy on nightly dialysis presented emergently with sudden loss of vision. On examination, his visual acuity was light perception in the right eye and no light perception in the left eye. There was bilateral optic disk edema, diffuse pallor of posterior poles, and a cherry red spot in the left fundus. The patient was subsequently found to be hemodynamically unstable and admitted to the pediatric intensive care unit with presumed septic shock. Optical coherence tomography revealed paracentral acute middle maculopathy lesions in the right eye and diffusely thick retina in the left eye. Magnetic resonance imaging and magnetic resonance angiography of the brain and vessels did not reveal any acute findings. The patient's presentation was most consistent with bilateral nonarteritic ischemic optic neuropathy and unilateral central retinal artery occlusion. On repeat evaluation 9 months later, vision was largely unchanged.
PubMed: 38825070
DOI: 10.1016/j.jaapos.2024.103948