Hasil untuk "Ophthalmology"

Varun Gulshan, L. Peng, Marc Coram et al.

C. Wilkinson, Frederick L. Ferris, R. Klein et al.

N. Newman

Pu-Ying Wei, Xi-Zhe Wang, Jin-Ming Han

AIM: To assess the current research status and emerging trends of the choriocapillaris (CC) by bibliometric analysis. METHODS: Publications spanning from January 2013 to May 2023 were retrieved on June 27th, 2023, using the Web of Science Core Collection. Bibliometric and visualized analyses were performed employing the bibliometrix, CiteSpace and VOSviewer. RESULTS: A total of 1563 papers met the inclusion criteria, and a publication growth trend was observed. The United States was the leading country in the CC field. Retina and Investigative Ophthalmology & Visual Science stood out as highly impactful and prolific journals. Research topics in the CC field encompassed choroidal neovascularization, choroidal thickness, central serous chorioretinopathy, age-related macular degeneration, myopia, choroidal vascularity index, and diabetic retinopathy, based on the co-citation analysis. The keyword “high myopia” experienced a burst lasting until 2023. CONCLUSION: In the past decade, research in the field of CC has flourished due to recent advancements in choroidal imaging; with focus shifting towards elucidating its role in various diseases. This will provide novel insights into managing chorioretinal diseases and vision-preserving interventions.

Dmitry Ryabtsev, Boris Vasilyev, Sergey Shershakov

This paper introduces an innovative software system for fundus image analysis that deliberately diverges from the conventional screening approach, opting not to predict specific diagnoses. Instead, our methodology mimics the diagnostic process by thoroughly analyzing both normal and pathological features of fundus structures, leaving the ultimate decision-making authority in the hands of healthcare professionals. Our initiative addresses the need for objective clinical analysis and seeks to automate and enhance the clinical workflow of fundus image examination. The system, from its overarching architecture to the modular analysis design powered by artificial intelligence (AI) models, aligns seamlessly with ophthalmological practices. Our unique approach utilizes a combination of state-of-the-art deep learning methods and traditional computer vision algorithms to provide a comprehensive and nuanced analysis of fundus structures. We present a distinctive methodology for designing medical applications, using our system as an illustrative example. Comprehensive verification and validation results demonstrate the efficacy of our approach in revolutionizing fundus image analysis, with potential applications across various medical domains.

Jia Zhou, Chang-Xing Ma

In clinical trials involving paired organs such as eyes, ears, and kidneys, binary outcomes may be collected bilaterally or unilaterally. In such combined datasets, bilateral outcomes exhibit intra-subject correlation, while unilateral outcomes are assumed independent. We investigate the generalized Estimating Equations (GEE) approach for testing homogeneity of proportions across multiple groups for the combined unilateral and bilateral data, and compare it with three likelihood-based statistics (likelihood ratio, Wald-type, and score) under Rosner's constant $R$ model and Donner's equal correlation $ρ$ model. Monte Carlo simulations evaluate empirical type I error and power under varied sample sizes and parameter settings. The GEE and score tests show superior type I error control, outperforming likelihood ratio and Wald-type tests. Applications to two real datasets in otolaryngologic and ophthalmologic studies illustrate the methods. We recommend the GEE and score tests for homogeneity testing, and suggest GEE for more complex models with covariates, while favoring the score statistic for small sample exact tests due to its computational efficiency.

Shiv Garg, Ginny Berkemeier

Ocular disease affects billions of individuals unevenly worldwide. It continues to increase in prevalence with trends of growing populations of diabetic people, increasing life expectancies, decreasing ophthalmologist availability, and rising costs of care. We present EyeAI, a system designed to provide artificial intelligence-assisted detection of ocular diseases, thereby enhancing global health. EyeAI utilizes a convolutional neural network model trained on 1,920 retinal fundus images to automatically diagnose the presence of ocular disease based on a retinal fundus image input through a publicly accessible web-based application. EyeAI performs a binary classification to determine the presence of any of 45 distinct ocular diseases, including diabetic retinopathy, media haze, and optic disc cupping, with an accuracy of 80%, an AUROC of 0.698, and an F1-score of 0.8876. EyeAI addresses barriers to traditional ophthalmologic care by facilitating low-cost, remote, and real-time diagnoses, particularly for equitable access to care in underserved areas and for supporting physicians through a secondary diagnostic opinion. Results demonstrate the potential of EyeAI as a scalable, efficient, and accessible diagnostic tool. Future work will focus on expanding the training dataset to enhance the accuracy of the model further and improve its diagnostic capabilities.

Dilermando Queiroz, Anderson Carlos, Maíra Fatoretto et al.

Foundation models have emerged as robust models with label efficiency in diverse domains. In medical imaging, these models contribute to the advancement of medical diagnoses due to the difficulty in obtaining labeled data. However, it is unclear whether using a large amount of unlabeled data, biased by the presence of sensitive attributes during pre-training, influences the fairness of the model. This research examines the bias in the Foundation model (RetFound) when it is applied to fine-tune the Brazilian Multilabel Ophthalmological Dataset (BRSET), which has a different population than the pre-training dataset. The model evaluation, in comparison with supervised learning, shows that the Foundation Model has the potential to reduce the gap between the maximum AUC and minimum AUC evaluations across gender and age groups. However, in a data-efficient generalization, the model increases the bias when the data amount decreases. These findings suggest that when deploying a Foundation Model in real-life scenarios with limited data, the possibility of fairness issues should be considered.

Ameya Uppina, S Navaneetha Krishnan, Talluri Krishna Sai Teja et al.

Diabetic Retinopathy DR is a severe complication of diabetes. Damaged or abnormal blood vessels can cause loss of vision. The need for massive screening of a large population of diabetic patients has generated an interest in a computer-aided fully automatic diagnosis of DR. In the realm of Deep learning frameworks, particularly convolutional neural networks CNNs, have shown great interest and promise in detecting DR by analyzing retinal images. However, several challenges have been faced in the application of deep learning in this domain. High-quality, annotated datasets are scarce, and the variations in image quality and class imbalances pose significant hurdles in developing a dependable model. In this paper, we demonstrate the proficiency of two Convolutional Neural Networks CNNs based models, UNET and Stacked UNET utilizing the APTOS Asia Pacific Tele-Ophthalmology Society Dataset. This system achieves an accuracy of 92.81% for the UNET and 93.32% for the stacked UNET architecture. The architecture classifies the images into five categories ranging from 0 to 4, where 0 is no DR and 4 is proliferative DR.

Marawan Elbatel, Konstantinos Kamnitsas, Xiaomeng Li

Generative modeling seeks to approximate the statistical properties of real data, enabling synthesis of new data that closely resembles the original distribution. Generative Adversarial Networks (GANs) and Denoising Diffusion Probabilistic Models (DDPMs) represent significant advancements in generative modeling, drawing inspiration from game theory and thermodynamics, respectively. Nevertheless, the exploration of generative modeling through the lens of biological evolution remains largely untapped. In this paper, we introduce a novel family of models termed Generative Cellular Automata (GeCA), inspired by the evolution of an organism from a single cell. GeCAs are evaluated as an effective augmentation tool for retinal disease classification across two imaging modalities: Fundus and Optical Coherence Tomography (OCT). In the context of OCT imaging, where data is scarce and the distribution of classes is inherently skewed, GeCA significantly boosts the performance of 11 different ophthalmological conditions, achieving a 12% increase in the average F1 score compared to conventional baselines. GeCAs outperform both diffusion methods that incorporate UNet or state-of-the art variants with transformer-based denoising models, under similar parameter constraints. Code is available at: https://github.com/xmed-lab/GeCA.

Yu Tian, Congcong Wen, Min Shi et al.

Addressing fairness in artificial intelligence (AI), particularly in medical AI, is crucial for ensuring equitable healthcare outcomes. Recent efforts to enhance fairness have introduced new methodologies and datasets in medical AI. However, the fairness issue under the setting of domain transfer is almost unexplored, while it is common that clinics rely on different imaging technologies (e.g., different retinal imaging modalities) for patient diagnosis. This paper presents FairDomain, a pioneering systemic study into algorithmic fairness under domain shifts, employing state-of-the-art domain adaptation (DA) and generalization (DG) algorithms for both medical segmentation and classification tasks to understand how biases are transferred between different domains. We also introduce a novel plug-and-play fair identity attention (FIA) module that adapts to various DA and DG algorithms to improve fairness by using self-attention to adjust feature importance based on demographic attributes. Additionally, we curate the first fairness-focused dataset with two paired imaging modalities for the same patient cohort on medical segmentation and classification tasks, to rigorously assess fairness in domain-shift scenarios. Excluding the confounding impact of demographic distribution variation between source and target domains will allow clearer quantification of the performance of domain transfer models. Our extensive evaluations reveal that the proposed FIA significantly enhances both model performance accounted for fairness across all domain shift settings (i.e., DA and DG) with respect to different demographics, which outperforms existing methods on both segmentation and classification. The code and data can be accessed at https://ophai.hms.harvard.edu/datasets/harvard-fairdomain20k.

Yu Han, Aaron Ceross, Sarim Ather et al.

Artificial intelligence (AI) in medical device software (MDSW) represents a transformative clinical technology, attracting increasing attention within both the medical community and the regulators. In this study, we leverage a data-driven approach to automatically extract and analyze AI-enabled medical devices (AIMD) from the National Medical Products Administration (NMPA) regulatory database. The continued increase in publicly available regulatory data requires scalable methods for analysis. Automation of regulatory information screening is essential to create reproducible insights that can be quickly updated in an ever changing medical device landscape. More than 4 million entries were assessed, identifying 2,174 MDSW registrations, including 531 standalone applications and 1,643 integrated within medical devices, of which 43 were AI-enabled. It was shown that the leading medical specialties utilizing AIMD include respiratory (20.5%), ophthalmology/endocrinology (12.8%), and orthopedics (10.3%). This approach greatly improves the speed of data extracting providing a greater ability to compare and contrast. This study provides the first extensive, data-driven exploration of AIMD in China, showcasing the potential of automated regulatory data analysis in understanding and advancing the landscape of AI in medical technology.

Danling Liao, Shijia Wei, Jianzhang Hu

Abstract Background Autophagy has recently been shown to be critical for protecting peripheral nerve regeneration. This study explored the impact of miR-542-3p on diabetic corneal nerve regeneration and epithelial healing through the regulation of autophagy. Methods A type 1 diabetes model was established in male mice through streptozotocin administration. Immunofluorescence staining of β-Tubulin III and sodium fluorescein staining were performed to observe corneal nerve fiber density and corneal epithelial healing, respectively. Western blotting, immunofluorescence and transmission electron microscopy were used to determine autophagy levels. Subconjunctival injection of RAPA and 3-MA altered autophagy levels; with them, we evaluated the role of autophagy in diabetic keratopathy. miRNA sequencing and bioinformatics analysis were performed to identify miRNA-mRNA networks with potential autophagy-regulating roles, and miR-542-3p was measured by quantitative real-time polymerase chain reaction (qRT-PCR). miR-542-3p antagomir was injected subconjunctivally to assess the role in diabetic corneal neuropathy. Results Our data suggest that autophagy is suppressed in the diabetic corneal nerve and that activation of autophagy promotes diabetic corneal wound healing. We identified a potential autophagy-regulating miRNA-mRNA network in the diabetic trigeminal ganglion, in which miR-542-3p expression was significantly upregulated. Inhibition of miR-542-3p significantly enhanced the level of autophagy in trigeminal ganglion by upregulating ATG4D expression, thereby accelerating diabetic corneal nerve regeneration and epithelial healing. Conclusions Dysregulated autophagy is an important contributor to delayed diabetic corneal injury healing. Inhibiting miR-542-3p promotes diabetic corneal nerve regeneration and epithelial healing through autophagy activation by ATG4D.

Zi-Yi Zhou, Ya-Ting Ye, Jing-Ting Zhu et al.

Gaia Bonassi, Mingqi Zhao, Jessica Samogin et al.

Walking encompasses a complex interplay of neuromuscular coordination and cognitive processes. Disruptions in gait can impact personal independence and quality of life, especially among the elderly and neurodegenerative patients. While traditional biomechanical analyses and neuroimaging techniques have contributed to understanding gait control, they often lack the temporal resolution needed for rapid neural dynamics. This study employs a mobile brain/body imaging (MoBI) platform with high-density electroencephalography (hd-EEG) to explore event-related desynchronization and synchronization (ERD/ERS) during overground walking. Simultaneous to hdEEG, we recorded gait spatiotemporal parameters. Participants were asked to walk under usual walking and dual-task walking conditions. For data analysis, we extracted ERD/ERS in α, β, and γ bands from 17 selected regions of interest encompassing not only the sensorimotor cerebral network but also the cognitive and affective networks. A correlation analysis was performed between gait parameters and ERD/ERS intensities in different networks in the different phases of gait. Results showed that ERD/ERS modulations across gait phases in the α and β bands extended beyond the sensorimotor network, over the cognitive and limbic networks, and were more prominent in all networks during dual tasks with respect to usual walking. Correlation analyses showed that a stronger α ERS in the initial double-support phases correlates with shorter step length, emphasizing the role of attention in motor control. Additionally, β ERD/ERS in affective and cognitive networks during dual-task walking correlated with dual-task gait performance, suggesting compensatory mechanisms in complex tasks. This study advances our understanding of neural dynamics during overground walking, emphasizing the multidimensional nature of gait control involving cognitive and affective networks.

Lin Y, Luo S, Lu Q et al.

Ye Lin, Shuke Luo, Qiang Lu, Xueke Pan Department of Ophthalmology, The Second People’s Hospital of Foshan, Foshan, Guangdong Province, People’s Republic of ChinaCorrespondence: Shuke Luo, Department of Ophthalmology, The Second People’s Hospital of Foshan, Foshan, Guangdong Province, 528000, People’s Republic of China, Tel +86 13679830510, Email 542377993@qq.comPurpose: To investigate the psychological changes in patients pre and post implantable collamer lens (ICL, EVO) implantation surgery in the posterior chamber.Patients and methods: Self-rating anxiety scale (SAS) and self-rating depression scale (SDS) were used to assess the mental states of 43 patients who underwent ICL implantation surgery performed by the same surgeon between January 2021 and December 2022.Results: Comparing the results before and one week after the operation, there is a significant difference in both the SAS scale (P< 0.05) and the SDS scale (P< 0.05). Similarly, when comparing the pre-operation and one-month post-operation results, there is also a significant difference in both the SAS scale (P< 0.05) and the SDS scale (P< 0.05). However, when comparing the one-week post-operation and one-month post-operation results, there is no significant difference in either the SAS scale (P> 0.05) or the SDS scale (P> 0.05). Moving on to the comparison between the pre-operation results and the national norm level, there is a significant difference in both the SAS scale (P< 0.05) and the SDS scale (P< 0.05). When comparing the one-week post-operation results and the national norm level, there is a significant difference in the SAS scale (P< 0.05). Similarly, when comparing the one-month post-operation results and the national norm level, there is a significant difference in the SAS scale (P< 0.05).Conclusion: After undergoing ICL implantation surgery, patients typically experience a notable decrease in anxiety (SAS) and depression (SDS) scales. These improvements gradually stabilize and enhance during the postoperative recovery period. However, it may require a significant amount of time for patients to fully restore their psychological well-being to levels comparable to the national norm, particularly in terms of anxiety levels.Keywords: implantable collamer lens implantation, myopia, mental state, self-rating anxiety scale, self-rating depression scale

Jamie Burke, Dan Pugh, Tariq Farrah et al.

Purpose: To evaluate the performance of an automated choroid segmentation algorithm in optical coherence tomography (OCT) data using a longitudinal kidney donor and recipient cohort. Methods: We assessed 22 donors and 23 patients requiring renal transplantation over up to 1 year post-transplant. We measured choroidal thickness (CT) and area and compared our automated CT measurements to manual ones at the same locations. We estimated associations between choroidal measurements and markers of renal function (estimated glomerular filtration rate (eGFR), serum creatinine and urea) using correlation and linear mixed-effects (LME) modelling. Results: There was good agreement between manual and automated CT. Automated measures were more precise because of smaller measurement error over time. External adjudication of major discrepancies were in favour of automated measures. Significant differences were observed in the choroid pre- and post-transplant in both cohorts, and LME modelling revealed significant linear associations observed between choroidal measures and renal function in recipients. Significant associations were mostly stronger with automated CT (eGFR P<0.001, creatinine P=0.004, urea P=0.04) compared to manual CT (eGFR P=0.002, creatinine P=0.01, urea P=0.03). Conclusions: Our automated approach has greater precision than human-performed manual measurements, which may explain stronger associations with renal function compared to manual measurements. To improve detection of meaningful associations with clinical endpoints in longitudinal studies of OCT, reducing measurement error should be a priority, and automated measurements help achieve this. Translational relevance: We introduce a novel choroid segmentation algorithm which can replace manual grading for studying the choroid in renal disease, and other clinical conditions.

Natalia Mathá, Klaus Schoeffmann, Konstantin Schekotihin et al.

In the last decade, the need for storing videos from cataract surgery has increased significantly. Hospitals continue to improve their imaging and recording devices (e.g., microscopes and cameras used in microscopic surgery, such as ophthalmology) to enhance their post-surgical processing efficiency. The video recordings enable a lot of user-cases after the actual surgery, for example, teaching, documentation, and forensics. However, videos recorded from operations are typically stored in the internal archive without any domain-specific compression, leading to a massive storage space consumption. In this work, we propose a relevance-based compression scheme for videos from cataract surgery, which is based on content specifics of particular cataract surgery phases. We evaluate our compression scheme with three state-of-the-art video codecs, namely H.264/AVC, H.265/HEVC, and AV1, and ask medical experts to evaluate the visual quality of encoded videos. Our results show significant savings, in particular up to 95.94% when using H.264/AVC, up to 98.71% when using H.265/HEVC, and up to 98.82% when using AV1.

Yu Tian, Min Shi, Yan Luo et al.

Fairness in artificial intelligence models has gained significantly more attention in recent years, especially in the area of medicine, as fairness in medical models is critical to people's well-being and lives. High-quality medical fairness datasets are needed to promote fairness learning research. Existing medical fairness datasets are all for classification tasks, and no fairness datasets are available for medical segmentation, while medical segmentation is an equally important clinical task as classifications, which can provide detailed spatial information on organ abnormalities ready to be assessed by clinicians. In this paper, we propose the first fairness dataset for medical segmentation named Harvard-FairSeg with 10,000 subject samples. In addition, we propose a fair error-bound scaling approach to reweight the loss function with the upper error-bound in each identity group, using the segment anything model (SAM). We anticipate that the segmentation performance equity can be improved by explicitly tackling the hard cases with high training errors in each identity group. To facilitate fair comparisons, we utilize a novel equity-scaled segmentation performance metric to compare segmentation metrics in the context of fairness, such as the equity-scaled Dice coefficient. Through comprehensive experiments, we demonstrate that our fair error-bound scaling approach either has superior or comparable fairness performance to the state-of-the-art fairness learning models. The dataset and code are publicly accessible via https://ophai.hms.harvard.edu/datasets/harvard-fairseg10k.

Aline Sindel, Bettina Hohberger, Andreas Maier et al.

In ophthalmological imaging, multiple imaging systems, such as color fundus, infrared, fluorescein angiography, optical coherence tomography (OCT) or OCT angiography, are often involved to make a diagnosis of retinal disease. Multi-modal retinal registration techniques can assist ophthalmologists by providing a pixel-based comparison of aligned vessel structures in images from different modalities or acquisition times. To this end, we propose an end-to-end trainable deep learning method for multi-modal retinal image registration. Our method extracts convolutional features from the vessel structure for keypoint detection and description and uses a graph neural network for feature matching. The keypoint detection and description network and graph neural network are jointly trained in a self-supervised manner using synthetic multi-modal image pairs and are guided by synthetically sampled ground truth homographies. Our method demonstrates higher registration accuracy as competing methods for our synthetic retinal dataset and generalizes well for our real macula dataset and a public fundus dataset.