-
Journal of Clinical Medicine May 2024: To design a novel anomaly detection and localization approach using artificial intelligence methods using optical coherence tomography (OCT) scans for retinal...
: To design a novel anomaly detection and localization approach using artificial intelligence methods using optical coherence tomography (OCT) scans for retinal diseases. : High-resolution OCT scans from the publicly available Kaggle dataset and a local dataset were used by four state-of-the-art self-supervised frameworks. The backbone model of all the frameworks was a pre-trained convolutional neural network (CNN), which enabled the extraction of meaningful features from OCT images. Anomalous images included choroidal neovascularization (CNV), diabetic macular edema (DME), and the presence of drusen. Anomaly detectors were evaluated by commonly accepted performance metrics, including area under the receiver operating characteristic curve, F1 score, and accuracy. : A total of 25,315 high-resolution retinal OCT slabs were used for training. Test and validation sets consisted of 968 and 4000 slabs, respectively. The best performing across all anomaly detectors had an area under the receiver operating characteristic of 0.99. All frameworks were shown to achieve high performance and generalize well for the different retinal diseases. Heat maps were generated to visualize the quality of the frameworks' ability to localize anomalous areas of the image. : This study shows that with the use of pre-trained feature extractors, the frameworks tested can generalize to the domain of retinal OCT scans and achieve high image-level ROC-AUC scores. The localization results of these frameworks are promising and successfully capture areas that indicate the presence of retinal pathology. Moreover, such frameworks have the potential to uncover new biomarkers that are difficult for the human eye to detect. Frameworks for anomaly detection and localization can potentially be integrated into clinical decision support and automatic screening systems that will aid ophthalmologists in patient diagnosis, follow-up, and treatment design. This work establishes a solid basis for further development of automated anomaly detection frameworks for clinical use.
PubMed: 38892804
DOI: 10.3390/jcm13113093 -
Journal of Clinical Medicine May 2024Depression has been shown to be associated with eye diseases, including dry eye disease (DED), cataracts, glaucoma, age-related macular degeneration (AMD), and diabetic... (Review)
Review
Depression has been shown to be associated with eye diseases, including dry eye disease (DED), cataracts, glaucoma, age-related macular degeneration (AMD), and diabetic retinopathy (DR). This narrative review explores potential pathophysiological connections between depression and eye disease, as well as its potential correlations with ocular parameters. : A literature search was conducted in August 2022 in PUBMED, EMBASE, and PsycINFO. Published articles related to the subject were consolidated and classified according to respective eye diseases and pathophysiological mechanisms. : The literature reviewed suggests that common pathophysiological states like inflammation and neurodegeneration may contribute to both depression and certain eye diseases, while somatic symptoms and altered physiology, such as disruptions in circadian rhythm due to eye diseases, can also influence patients' mood states. Grounded in the shared embryological, anatomical, and physiological features between the eye and the brain, depression is also correlated to changes observed in non-invasive ophthalmological imaging modalities, such as changes in the retinal nerve fibre layer and retinal microvasculature. : There is substantial evidence of a close association between depression and eye diseases. Understanding the underlying concepts can inform further research on treatment options and monitoring of depression based on ocular parameters.
PubMed: 38892791
DOI: 10.3390/jcm13113081 -
International Journal of Molecular... May 2024Wet age-related macular degeneration (wet AMD) is a primary contributor to visual impairment and severe vision loss globally, but the prevailing treatments are often... (Review)
Review
Wet age-related macular degeneration (wet AMD) is a primary contributor to visual impairment and severe vision loss globally, but the prevailing treatments are often unsatisfactory. The development of conventional treatment strategies has largely been based on the understanding that the angiogenic switch of endothelial cells (ECs) is mainly dictated by angiogenic growth factors. Even though treatments targeting vascular endothelial growth factor (VEGF), like ranibizumab, are widely administered, more than half of patients still exhibit inadequate or null responses, suggesting the involvement of other pathogenic mechanisms. With advances in research in recent years, it has become well recognized that EC metabolic regulation plays an active rather than merely passive responsive role in angiogenesis. Disturbances of these metabolic pathways may lead to excessive neovascularization in angiogenic diseases such as wet AMD, therefore targeted modulation of EC metabolism represents a promising therapeutic strategy for wet AMD. In this review, we comprehensively discuss the potential applications of EC metabolic regulation in wet AMD treatment from multiple perspectives, including the involvement of ECs in wet AMD pathogenesis, the major endothelial metabolic pathways, and novel therapeutic approaches targeting metabolism for wet AMD.
Topics: Humans; Endothelial Cells; Wet Macular Degeneration; Animals; Vascular Endothelial Growth Factor A; Ranibizumab; Angiogenesis Inhibitors; Metabolic Networks and Pathways; Neovascularization, Pathologic
PubMed: 38892113
DOI: 10.3390/ijms25115926 -
International Journal of Molecular... May 2024The ocular glymphatic system subserves the bidirectional polarized fluid transport in the optic nerve, whereby cerebrospinal fluid from the brain is directed along... (Review)
Review
The ocular glymphatic system subserves the bidirectional polarized fluid transport in the optic nerve, whereby cerebrospinal fluid from the brain is directed along periarterial spaces towards the eye, and fluid from the retina is directed along perivenous spaces following upon its axonal transport across the glial lamina. Fluid homeostasis and waste removal are vital for retinal function, making the ocular glymphatic fluid pathway a potential route for targeted manipulation to combat blinding ocular diseases such as age-related macular degeneration, diabetic retinopathy, and glaucoma. Several lines of work investigating the bidirectional ocular glymphatic transport with varying methodologies have developed diverging mechanistic models, which has created some confusion about how ocular glymphatic transport should be defined. In this review, we provide a comprehensive summary of the current understanding of the ocular glymphatic system, aiming to address misconceptions and foster a cohesive understanding of the topic.
Topics: Humans; Glymphatic System; Animals; Optic Nerve; Retina; Eye; Glaucoma
PubMed: 38891923
DOI: 10.3390/ijms25115734 -
Molecular Neurodegeneration Jun 2024Age-related macular degeneration (AMD) is the leading cause of blindness in elderly people in the developed world, and the number of people affected is expected to...
BACKGROUND
Age-related macular degeneration (AMD) is the leading cause of blindness in elderly people in the developed world, and the number of people affected is expected to almost double by 2040. The retina presents one of the highest metabolic demands in our bodies that is partially or fully fulfilled by mitochondria in the neuroretina and retinal pigment epithelium (RPE), respectively. Together with its post-mitotic status and constant photooxidative damage from incoming light, the retina requires a tightly-regulated housekeeping system that involves autophagy. The natural polyphenol Urolithin A (UA) has shown neuroprotective benefits in several models of aging and age-associated disorders, mostly attributed to its ability to induce mitophagy and mitochondrial biogenesis. Sodium iodate (SI) administration recapitulates the late stages of AMD, including geographic atrophy and photoreceptor cell death.
METHODS
A combination of in vitro, ex vivo and in vivo models were used to test the neuroprotective potential of UA in the SI model. Functional assays (OCT, ERGs), cellular analysis (flow cytometry, qPCR) and fine confocal microscopy (immunohistochemistry, tandem selective autophagy reporters) helped address this question.
RESULTS
UA alleviated neurodegeneration and preserved visual function in SI-treated mice. Simultaneously, we observed severe proteostasis defects upon SI damage induction, including autophagosome accumulation, that were resolved in animals that received UA. Treatment with UA restored autophagic flux and triggered PINK1/Parkin-dependent mitophagy, as previously reported in the literature. Autophagy blockage caused by SI was caused by severe lysosomal membrane permeabilization. While UA did not induce lysosomal biogenesis, it did restore upcycling of permeabilized lysosomes through lysophagy. Knockdown of the lysophagy adaptor SQSTM1/p62 abrogated viability rescue by UA in SI-treated cells, exacerbated lysosomal defects and inhibited lysophagy.
CONCLUSIONS
Collectively, these data highlight a novel putative application of UA in the treatment of AMD whereby it bypasses lysosomal defects by promoting p62-dependent lysophagy to sustain proteostasis.
Topics: Animals; Mice; Coumarins; Autophagy; Macular Degeneration; Retina; Mitophagy; Sequestosome-1 Protein; Lysosomes; Humans; Disease Models, Animal; Neuroprotective Agents; Mice, Inbred C57BL; Iodates
PubMed: 38890703
DOI: 10.1186/s13024-024-00739-3 -
Scientific Reports Jun 2024In this retrospective case series on neovascular age-related macular degeneration (nAMD), we aimed to improve Choroidal Neovascularization (CNV) visualization in Optical...
In this retrospective case series on neovascular age-related macular degeneration (nAMD), we aimed to improve Choroidal Neovascularization (CNV) visualization in Optical Coherence Tomography Angiography (OCTA) scans by addressing segmentation errors. Out of 198 eyes, 73 OCTA scans required manual segmentation correction. We compared uncorrected scans to those with minimal (2 corrections), moderate (10 corrections), and detailed (50 corrections) efforts targeting falsely segmented Bruch's Membrane (BM). Results showed that 55% of corrected OCTAs exhibited improved quality after manual correction. Notably, minimal correction (2 scans) already led to significant improvements, with additional corrections (10 or 50) not further enhancing expert grading. Reduced background noise and improved CNV identification were observed, with the most substantial improvement after two corrections compared to baseline uncorrected images. In conclusion, our approach of correcting segmentation errors effectively enhances image quality in OCTA scans of nAMD. This study demonstrates the efficacy of the method, with 55% of resegmented OCTA images exhibiting enhanced quality, leading to a notable increase in the proportion of high-quality images from 63 to 83%.
Topics: Humans; Choroidal Neovascularization; Tomography, Optical Coherence; Female; Male; Retrospective Studies; Aged; Macular Degeneration; Aged, 80 and over; Image Processing, Computer-Assisted; Middle Aged; Fluorescein Angiography
PubMed: 38886462
DOI: 10.1038/s41598-024-61551-z -
Scientific Reports Jun 2024Age-related macular degeneration (AMD) is one of the major causes of blindness in the elderly worldwide. Anti-vascular endothelial growth factor (VEGF) drugs have been...
Age-related macular degeneration (AMD) is one of the major causes of blindness in the elderly worldwide. Anti-vascular endothelial growth factor (VEGF) drugs have been widely used to treat the neovascular type of AMD (nAMD). However, VEGF acts not only as a pro-angiogenic factor but also as an anti-apoptotic factor in the eyes. In this study, we found that anti-VEGF drugs, including bevacizumab (Bev), ranibizumab (Ran), and aflibercept (Afl), induced epithelial-mesenchymal transition (EMT) in ARPE-19 cells in vitro, accompanied by the induction of CCN2, a potent pro-fibrotic factor. Similarly, intravitreal injection of Afl into mouse eyes resulted in EMT in the retinal pigmented epithelium (RPE). Co-treatment with CCN5, an anti-fibrotic factor that down-regulates CCN2 expression, significantly attenuated the adverse effects of the anti-VEGF drugs both in vitro and in vivo. Inhibition of the VEGF signaling pathway with antagonists of VEGF receptors, SU5416 and ZM323881, induced EMT and up-regulated CCN2 in ARPE-19 cells. Additionally, knock-down of CCN2 with siRNA abolished the adverse effects of the anti-VEGF drugs in ARPE-19 cells. Collectively, these results suggest that anti-VEGF drugs induce EMT in RPE through the induction of CCN2 and that co-treatment with CCN5 attenuates the adverse effects of anti-VEGF drugs in mouse eyes.
Topics: Epithelial-Mesenchymal Transition; Retinal Pigment Epithelium; Animals; Humans; Mice; Vascular Endothelial Growth Factor A; Macular Degeneration; Cell Line; Bevacizumab; CCN Intercellular Signaling Proteins; Angiogenesis Inhibitors; Ranibizumab; Recombinant Fusion Proteins; Signal Transduction; Repressor Proteins; Receptors, Vascular Endothelial Growth Factor
PubMed: 38886213
DOI: 10.1038/s41598-024-63565-z -
Investigative Ophthalmology & Visual... Jun 2024In age-related macular degeneration (AMD), choriocapillaris flow deficits (CCFDs) under soft drusen can be measured using established compensation strategies. This study...
PURPOSE
In age-related macular degeneration (AMD), choriocapillaris flow deficits (CCFDs) under soft drusen can be measured using established compensation strategies. This study investigated whether CCFDs can be quantified under calcified drusen (CaD).
METHODS
CCFDs were measured in normal eyes (n = 30) and AMD eyes with soft drusen (n = 30) or CaD (n = 30). CCFD density masks were generated to highlight regions with higher CCFDs. Masks were also generated for soft drusen and CaD based on both structural en face OCT images and corresponding B-scans. Dice similarity coefficients were calculated between the CCFD density masks and both the soft drusen and CaD masks. A phantom experiment was conducted to simulate the impact of light scattering that arises from CaD.
RESULTS
Area measurements of CCFDs were highly correlated with those of CaD but not soft drusen, suggesting an association between CaD and underlying CCFDs. However, unlike soft drusen, the detected optical coherence tomography (OCT) signals underlying CaD did not arise from the defined CC layer but were artifacts caused by the multiple scattering property of CaD. Phantom experiments showed that the presence of highly scattering material similar to the contents of CaD caused an artifactual scattering tail that falsely generated a signal in the CC structural layer but the underlying flow could not be detected. Similarly, CaD also caused an artifactual scattering tail and prevented the penetration of light into the choroid, resulting in en face hypotransmission defects and an inability to detect blood flow within the choriocapillaris. Upon resolution of the CaD, the CC perfusion became detectable.
CONCLUSIONS
The high scattering property of CaD leads to a scattering tail under these drusen that gives the illusion of a quantifiable optical coherence tomography angiography signal, but this signal does not contain the angiographic information required to assess CCFDs. For this reason, CCFDs cannot be reliably measured under CaD, and CaD must be identified and excluded from macular CCFD measurements.
Topics: Humans; Tomography, Optical Coherence; Choroid; Retinal Drusen; Female; Aged; Male; Fluorescein Angiography; Regional Blood Flow; Calcinosis; Aged, 80 and over; Macular Degeneration; Middle Aged; Phantoms, Imaging; Fundus Oculi
PubMed: 38884553
DOI: 10.1167/iovs.65.6.26 -
Translational Vision Science &... Jun 2024To establish the reliability and validity of five performance-based activities of daily living task tests (ADLTT), to correlate structure to function, to evaluate the...
PURPOSE
To establish the reliability and validity of five performance-based activities of daily living task tests (ADLTT), to correlate structure to function, to evaluate the impact of visual impairment (VI) on age-related macular degeneration (AMD), and to develop new outcome measures.
METHODS
A multidisciplinary team developed five ADLTTs: (1) reading test (RT); (2) facial expression (FE) recognition; (3) item search (IS) task; (4) money counting (MC) task; and (5) making a drink (MD), tested with binocular and monocular vision. ADLTTs were tested for known-group (i.e., difference between AMD group and controls) and convergent (i.e., correlation to other measures of visual function), validity metrics, and test-retest reliability in 36 patients with VI (visual acuity (logMAR VA > 0.4) in at least one eye caused by AMD versus 36 healthy controls without VI.
RESULTS
Compared to controls, AMD patients had a slower reading speed (-77.41 words/min; P < 0.001); took longer to complete MC using monocular worse eye and binocular vision (15.13 seconds and 4.06 seconds longer compared to controls, respectively; P < 0.001); and MD using monocular worse eye vision (9.37 sec; P = 0.033), demonstrating known-group validity. Only RT and MC demonstrated convergent validity, showing correlations with VA, contrast sensitivity, and microperimetry testing. Moderate to good test-retest reliability was observed for MC and MD (interclass correlation coefficient = 0.55 and 0.77; P < 0.001) using monocular worse eye vision.
CONCLUSIONS
Real-world ADL functioning associated with VI-related AMD can be assessed with our validated ADLTTs, particularly MC and MD.
TRANSLATIONAL RELEVANCE
This study validates visual function outcome measures that are developed for use in future clinical practice and clinical trials.
Topics: Humans; Activities of Daily Living; Macular Degeneration; Female; Male; Aged; Visual Acuity; Reproducibility of Results; Aged, 80 and over; Middle Aged; Vision Tests; Vision, Binocular; Reading
PubMed: 38884546
DOI: 10.1167/tvst.13.6.9 -
Medical Research Archives Oct 2023We briefly review our recently published approach to mining digenic genotype patterns, which consist of two genotypes each originating in a different DNA variant. We do...
We briefly review our recently published approach to mining digenic genotype patterns, which consist of two genotypes each originating in a different DNA variant. We do this for a genetic case-control study by evaluating all possible pairs of genotypes, distributing the workload over numerous CPUs (threads) in a high-performance computing environment and apply our methods to two known datasets, age-related macular degeneration (AMD) and Parkinson Disease (PD). Based on a list of (e.g., 100,000) genotype pairs with largest genotype pair frequency differences between cases and controls, we determine the number of unique variants occurring in this list. For each unique variant, we find the number of genotype pairs it participates in, which identifies a set of variants "connected" with the given unique variant. Among the total of variants "connected" with all unique variants, only a subset of variants is unique. The ratio of all connected variants divided by that subset of variants is a measure for the overall density or connectedness of variants interacting with each other. We find that variants for the AMD data are much more interconnected than those for PD, at least based on the 100,000 genotype pairs with largest chi-square we investigated. Further, for each of the unique variants, we use the number of variants connected with it as a test statistic, weighted by the inverse of the rank at which the unique variant first occurred in the original list of genotype patterns. This weighing scheme ties the number of connections to the genetics of the trait and allows us to obtain, for each of the unique variants, an empirical significance level by permuting ranks. We find 12 and 8 significant, highly connected variants for AMD and PD, respectively, some of which have previously been identified by other machine learning methods, thus providing credence to our approach. Among the 100,000 genotype pairs investigated for each of AMD and PD, significant variants showed connections with up to 7,093 and 3,777 other variants, respectively. Our approach has been implemented in a freely available piece of software, the . Thus, our statistical genetics method can provide important information on the genetic architecture of polygenic traits.
PubMed: 38882238
DOI: 10.18103/mra.v11i10.4604