Lecture notes in networks and systems, Journal Year: 2024, Volume and Issue: unknown, P. 505 - 519
Published: Jan. 1, 2024
Language: Английский
Journal of Medicinal Chemistry, Journal Year: 2024, Volume and Issue: 67(4), P. 3066 - 3089
Published: Jan. 24, 2024
Glaucoma, a leading cause of irreversible vision loss worldwide, is characterized by elevated intraocular pressure (IOP), well-established risk factor across all its forms. We present the design and synthesis 39 novel carbonic anhydrase inhibitors dual-tailed approach, strategically crafted to interact with distinct hydrophobic hydrophilic pockets CA active sites. The series was investigated against isoforms implicated in glaucoma (hCA II, hCA IV, XII), X-ray crystal structures compounds
Language: Английский
Citations
15
npj Digital Medicine, Journal Year: 2025, Volume and Issue: 8(1)
Published: Jan. 20, 2025
Language: Английский
Citations
1
Eye and Vision, Journal Year: 2024, Volume and Issue: 11(1)
Published: Oct. 1, 2024
Abstract Background In recent years, ophthalmology has emerged as a new frontier in medical artificial intelligence (AI) with multi-modal AI garnering significant attention across interdisciplinary research. This integration of various types and data models holds paramount importance it enables the provision detailed precise information for diagnosing eye vision diseases. By leveraging techniques, clinicians can enhance accuracy efficiency diagnoses, thus reduce risks associated misdiagnosis oversight while also enabling more management health. However, widespread adoption poses challenges. Main text this review, we first summarize comprehensively concept modalities field ophthalmology, forms fusion between modalities, progress ophthalmic technology. Finally, discuss challenges current technology applications future feasible research directions. Conclusion AI, evidence suggests that when utilizing data, deep learning-based exhibits excellent diagnostic efficacy assisting diagnosis Particularly, era marked by proliferation large-scale models, techniques represent most promising advantageous solution addressing diseases from comprehensive perspective. must be acknowledged there are still numerous application before they effectively employed clinical setting.
Language: Английский
Citations
7
Expert Systems with Applications, Journal Year: 2024, Volume and Issue: 256, P. 124888 - 124888
Published: Aug. 1, 2024
Glaucoma, a leading cause of irreversible blindness worldwide, poses significant diagnostic challenges due to its reliance on subjective evaluation. Recent advances in computer vision and deep learning have demonstrated the potential for automated assessment. This paper provides comprehensive survey studies AI-based glaucoma diagnosis using fundus, optical coherence tomography, visual field images, with focus learning-based methods. We searched Web Science, PubMed, IEEE Xplore, Google Scholar, applying specific selection criteria identify relevant published from 2017 2023. Our analysis structured overview architectural paradigms, including convolutional neural networks, autoencoders, attention generative adversarial geometric models. Additionally, we discuss approaches extracting informative features, such as structural, statistical, hybrid techniques. Furthermore, outline key research future directions, emphasizing need larger, more diverse datasets, strategies early disease detection, multi-modal data integration, model explainability, clinical translation. is expected be useful Artificial Intelligence (AI) researchers seeking translate into practice ophthalmologists aiming improve workflows latest AI outcomes.
Language: Английский
Citations
6
Progress in Retinal and Eye Research, Journal Year: 2024, Volume and Issue: 103, P. 101291 - 101291
Published: Aug. 25, 2024
Language: Английский
Citations
6
Scientific Data, Journal Year: 2023, Volume and Issue: 10(1)
Published: Aug. 5, 2023
As one of the leading causes irreversible blindness worldwide, glaucoma is characterized by structural damage and functional loss. Glaucoma patients often have a long follow-up prognosis prediction an important part in treatment. However, existing public datasets are almost cross-sectional, concentrating on segmentation optic disc (OD) diagnosis. With development artificial intelligence (AI), deep learning model can already provide accurate future visual field (VF) its progression with support longitudinal datasets. Here, we proposed real-world appraisal ensemble (GRAPE) dataset. The GRAPE dataset contains 1115 records from 263 eyes, VFs, fundus images, OCT measurements clinical information, OD VF annotated. Two baseline models demonstrated feasibility progression. This will advance AI research management.
Language: Английский
Citations
12
Scientific Data, Journal Year: 2024, Volume and Issue: 11(1)
Published: May 27, 2024
Abstract Image-based artificial intelligence (AI) systems stand as the major modality for evaluating ophthalmic conditions. However, most of currently available AI are designed experimental research using single-central datasets. Most them fell short application in real-world clinical settings. In this study, we collected a dataset 1,099 fundus images both normal and pathologic eyes from 483 premature infants intelligent retinopathy prematurity (ROP) system development validation. Dataset diversity was visualized with spatial scatter plot. Image classification conducted by three annotators. To best our knowledge, is one largest datasets on ROP, believe it conducive to systems.
Language: Английский
Citations
4
Acta Pharmaceutica Sinica B, Journal Year: 2025, Volume and Issue: unknown
Published: March 1, 2025
Language: Английский
Citations
0
Journal of Glaucoma, Journal Year: 2024, Volume and Issue: 33(8S), P. S26 - S32
Published: March 20, 2024
To provide an overview of novel technologies in telemedicine and artificial intelligence (AI) approaches for cost-effective glaucoma screening.
Language: Английский
Citations
3
Investigative Ophthalmology & Visual Science, Journal Year: 2024, Volume and Issue: 65(6), P. 10 - 10
Published: June 6, 2024
Purpose: To investigate whether fractal dimension (FD)–based oculomics could be used for individual risk prediction by evaluating repeatability and robustness. Methods: We two datasets: "Caledonia," healthy adults imaged multiple times in quick succession research (26 subjects, 39 eyes, 377 color fundus images), GRAPE, glaucoma patients with baseline follow-up visits (106 196 392 images). Mean time was 18.3 months GRAPE; thus it provides a pessimistic lower bound because vasculature change. FD computed DART AutoMorph. Image quality assessed QuickQual, but no images were initially excluded. Pearson, Spearman, intraclass correlation (ICC) population-level repeatability. For individual-level repeatability, we introduce measurement noise parameter λ, which is within-eye standard deviation (SD) of measurements units between-eyes SD. Results: In Caledonia, ICC 0.8153 0.5779 AutoMorph, Pearson/Spearman (first last image) 0.7857/0.7824 DART, 0.3933/0.6253 next visit) 0.7479/0.7474 0.7109/0.7208 AutoMorph (all P < 0.0001). Median λ Caledonia without exclusions 3.55% 12.65% improved to up 1.67% 6.64% quality-based exclusions, respectively. Quality primarily mitigated large outliers. Worst an eye correlated strongly (Pearson 0.5350–0.7550, depending on dataset method, all Conclusions: Repeatability sufficient predictions heterogeneous populations. performed better metrics might able detect small, longitudinal changes, highlighting the potential robust methods.
Language: Английский
Citations
2