BMJ Open Ophthalmology, Год журнала: 2024, Номер 9(1), С. e001873 - e001873
Опубликована: Дек. 1, 2024
To evaluate the efficacy of automated machine learning (AutoML) models in detecting fundus diseases using ocular B-scan ultrasound images.
Язык: Английский
Alzheimer s & Dementia, Год журнала: 2025, Номер 21(3)
Опубликована: Март 1, 2025
The utility of retinal photography-derived aging biomarkers for predicting cognitive decline remains under-explored. A memory-clinic cohort in Singapore was followed-up 5 years. RetiPhenoAge, a biomarker, derived from photographs using deep-learning. Using competing risk analysis, we determined the associations RetiPhenoAge with and dementia, UK Biobank utilized as replication cohort. MRI markers(cerebral small vessel disease [CSVD] neurodegeneration) its underlying plasma proteomic profile were evaluated. Of 510 subjects(N = 155 decline), associated incident (subdistribution hazard ratio [SHR] 1.34, 95% confidence interval [CI] 1.10-1.64, p 0.004), dementia (SHR 1.43, CI 1.02-2.01, 0.036). In (N 33 495), similarly predicted 1.25, 1.09-1.41, 0.008). significantly CSVD, brain atrophy, signatures related to aging. may provide non-invasive prognostic screening tool dementia. marker, studied an Asian memory clinic Older future It also linked neuropathological markers, profiles found that 12-year Future studies should validate biomarker
Язык: Английский
Процитировано
0
Current Eye Research, Год журнала: 2025, Номер unknown, С. 1 - 10
Опубликована: Янв. 23, 2025
Purpose This study aimed to initially test whether machine learning approaches could categorically predict two simple biological features, mouse age and species, using the retinal segmentation metrics.
Язык: Английский
Процитировано
0
Journal of Alzheimer s Disease, Год журнала: 2025, Номер unknown
Опубликована: Апрель 21, 2025
Background Recent studies have explored optical coherence tomography (OCT) and OCT-angiography (OCT-A) as biomarkers for Alzheimer's disease (AD). However, correlations between OCT/OCT-A neurodegeneration metrics remain underexplored. Objective We performed a systematic review of structural brain imaging using MRI across various neurodegenerative disorders. Methods searched Medline, Embase, other databases from January to June 2023 keywords regarding conditions OCT/OCT-A. Out 2962 citations. 93 articles were reviewed, 28 met our inclusion criteria. Results Layer-or-region-specific retinal the most promising non-vascular neurodegeneration, while vascular parameters had unique capacity reflect lesions. Both types correlated with global atrophy. Microstructural alterations best layer-specific thinning retina. Conclusions A better understanding associations lesions could eventually lead clinical application early diagnosis conditions.
Язык: Английский
Процитировано
0
Diabetes Research and Clinical Practice, Год журнала: 2025, Номер unknown, С. 112221 - 112221
Опубликована: Май 1, 2025
Язык: Английский
Процитировано
0
Journal of Advanced Research, Год журнала: 2024, Номер unknown
Опубликована: Ноя. 1, 2024
Systemic diseases, such as cardiovascular and cerebrovascular conditions, pose significant global health challenges due to their high mortality rates. Early identification intervention in systemic diseases can substantially enhance prognosis. However, diagnosing often necessitates complex, expensive, invasive tests, posing timely detection. Therefore, simple, cost-effective, non-invasive methods for the management (such screening, diagnosis, monitoring) of are needed reduce associated comorbidities
Язык: Английский
Процитировано
3
Scientific Reports, Год журнала: 2024, Номер 14(1)
Опубликована: Окт. 28, 2024
Early detection and correct identification of the optic disc (OD) on scanned retinal images are significant for diagnosing treating several ophthalmic conditions, including glaucoma diabetic retinopathy. Conventional methods detecting OD often struggle with processing due to noise, changes in illumination, complex overlapping images. This study presents development effective accurate fixation using Bitterling Fish Optimization (BFO) algorithm, which enhances processes imaging speed precision. The proposed method begins image enhancement noise suppression preprocessing, followed by applying BFO algorithm locate delineate region. performance evaluation was conducted within public domain images, DRIVE, STARE, ORIGA, DRISHTI-GS, DiaRetDB0, DiaRetDB1 datasets about some internal metrics: sensitivity (SE), specificity (SP), accuracy (ACC), DICE overlap coefficient, time respectively. technique based provided better results, 99.33%, 99.94%, 98.22% achieved DiaRetDB 1, approach also demonstrated high overlaps good a coefficient 0.9501 DRISHTI-GS database. On average, per less than 2.5 s, proving approach's efficiency computations. has its effectiveness scalability discs an automated manner. It showed impressive levels terms computation variation resistant irrespective quality pathology present it. holds potential clinical use, providing meaningful way managing ocular disease at early stage.
Язык: Английский
Процитировано
2
The Visual Computer, Год журнала: 2024, Номер unknown
Опубликована: Сен. 12, 2024
Язык: Английский
Процитировано
1
Опубликована: Май 12, 2024
Язык: Английский
Процитировано
0
Mayo Clinic Proceedings Digital Health, Год журнала: 2024, Номер 2(4), С. 548 - 558
Опубликована: Авг. 27, 2024
To report the development and performance of 2 distinct deep learning models trained exclusively on retinal color fundus photographs to classify Alzheimer disease (AD).
Язык: Английский
Процитировано
0
Pharmaceuticals, Год журнала: 2024, Номер 17(11), С. 1440 - 1440
Опубликована: Окт. 28, 2024
Neovascular age-related macular degeneration (nAMD) is one of the major causes vision impairment that affect millions people worldwide. Early detection nAMD crucial because, if untreated, it can lead to blindness. Software and algorithms utilize artificial intelligence (AI) have become valuable tools for early detection, assisting doctors in diagnosing facilitating differential diagnosis. AI particularly important remote or isolated communities, as allows patients endure tests receive rapid initial diagnoses without necessity extensive travel long wait times medical consultations. Similarly, notable also big hubs because cutting-edge technologies networking help speed processes such diagnosis, follow-up times. The automatic retinal changes might be optimized by AI, allowing choose most effective treatment nAMD. complex tissue well-suited scanning easily accessible modern AI-assisted multi-imaging techniques. enables us enhance patient management effectively evaluating data, timely diagnosis long-term prognosis. Novel applications focused on image analysis, specifically automated segmentation, extraction, quantification imaging-based features included within optical coherence tomography (OCT) pictures. To date, we cannot state could accurately forecast therapy would necessary a single achieve best visual outcome. A small number large datasets with high-quality OCT, lack data about alternative strategies, absence OCT standards are challenges development models
Язык: Английский
Процитировано
0