Purpose: To assess the performance of deep learning algorithms for different tasks in retinal fundus images: (1) detection of retinal fundus images versus optical coherence tomography (OCT) or other images, (2) evaluation of good quality retinal fundus images, (3) distinction between right eye (OD) and left eye (OS) retinal fundus images,(4) detection of age-related macular degeneration (AMD) and (5) detection of referable glaucomatous optic neuropathy (GON). Patients and Methods: Five algorithms were designed. Retrospective study from a database of 306,302 images, Optretina's tagged dataset. Three different ophthalmologists, all retinal specialists, classified all images. The dataset was split per patient in a training (80%) and testing (20%) splits. Three different CNN architectures were employed, two of which were custom designed to minimize the number of parameters with minimal impact on its accuracy. Main outcome measure was area under the curve (AUC) with accuracy, sensitivity and specificity. Results: Determination of retinal fundus image had AUC of 0.979 with an accuracy of 96% (sensitivity 97.7%, specificity 92.4%). Determination of good quality retinal fundus image had AUC of 0.947, accuracy 91.8% (sensitivity 96.9%, specificity 81.8%). Algorithm for OD/OS had AUC 0.989, accuracy 97.4%. AMD had AUC of 0.936, accuracy 86.3% (sensitivity 90.2% specificity 82.5%), GON had AUC of 0.863, accuracy 80.2% (sensitivity 76.8%, specificity 83.8%). Conclusion: Deep learning algorithms can differentiate a retinal fundus image from other images. Algorithms can evaluate the quality of an image, discriminate between right or left eye and detect the presence of AMD and GON with a high level of accuracy, sensitivity and specificity.
Conjunctivitis is a frequent ocular disorder caused by human adenoviruses (HAdVs). Only a few of the 45 HAdV‐D species are associated with epidemic keratoconjunctivitis, including HAdV‐D8. Nosocomial outbreaks due to HAdV‐D8 have been rarely described, because keratoconjunctivitis cases are clinically diagnosed and treated without having to characterize the causative agent. Moreover, molecular typing is tedious when using classical techniques. In this study, a hospital outbreak of conjunctivitis caused by HAdV‐D8 was characterized using the recently developed whole‐genome sequencing (WGS) method. Of the 363 patients attending the Ophthalmology Department between July 13 and August 13, 2018, 36 may have acquired intrahospital conjunctivitis. Also, 11 of 22 samples sent to the Virology section were selected for WGS analysis. The WGS results revealed that 10 out of 11 HAdV‐D8 strains were closely related. The remaining strain (Case 28) was more similar to a strain from an outbreak in Germany obtained from a public sequence database. WGS results showed that outbreak HAdV‐D8 strains had a minimum percentage of identity of 94.3%. WGS is useful in a clinical setting, because it avoids carrying out viral culture or specific polymerase chain reaction sequencing. The public availability of sequence reads makes it easier to compare clusters in circulation. In conclusion, WGS can play an important role in standard routines to describe viral outbreaks.
BackgroundUveitis can be a clinical manifestation of different systemic processes, known is the association of anterior uveitis in patients with spondyloarthritis (SpA)ObjectivesTo describe the prevalence, characteristics and course of ocular inflammatory pathology from a cohort of patients with SpAMethodsRetrospective descriptive study made in a cohort of 451 SpA patients according to the ASAS classification criteria in a a tertiary university hospital from Barcelona. Were selected patients who presented or had presented uveítis (defined according to the SUN1 classification criteria) Demographic, clinical, radiological and serological data of the joint disease and characteristics of the ocular affectation were collected, as well as the treatment of bothResultsOf the 451 patients reviewed, 43 (9.53%) patients with a history of uveitis were included in the study. From the cohort, the average age at diagnosis of SPA was 37 (± 27) years and 38 (88.4%) had positive HLAB27. The most prevalent subtypes of SPA were Ankylosing Spondylitis (AS): 27 (62.8%) and Psoriatic Arthritis (APSo): 8 (18.6%). The characteristics of the sample are summarized in Table 1 The average age at the first uveitis outbreak was 45 ± 23 years. The anterior location was more prevalent (n: 39, 90.7%), unilateral (n: 35, 81.4%) and acute onset (n: 42, 97.6%)Two of patients with anterior uveítis had other associated complications, one had macular edema and other retinal vasculitis. The treatment of uveitis was topical corticosteroids in 39 (90.6%) patients, 2 (4.6%) treatment with oral sulfasalazine. Despite the treatment, 22 (51.2%) patients presented a recurrent course. Table 2 shows the ocular clinical featuresTable 1 Clinical characteristics of SpA cohort.Sex, n% (men/women)24/19 (55.81/44.18)Diagnoses SpA, years ± DE37 ± 27Subtype SpA, n (%)EA, n (%)EII, n (%)APSo, n (%)PreRx, n (%)27 (62.8)2 (4.6)8 (18.6)6 (13.9)HLAB27, n (%)38 (88,4) Affectation SpAAxial, n (%)Periferic, n (%)Mixed, n (%)25 (58.1)4(9,3)11(25,6) Treatment SpAFAMEsMetotrexate, n (%)Sulfasalazine, n(%)Azatioprine, n (%)Leflunomide, n (%)ANTI- TNFEtarnecept, n (%)Adalimumab, n (%)Golimumab, n (%)Infliximab, n (%)Certolizumab, n(%)Secukinumab, n (%)Ustekinumab, n (%)14 (32)5 (11.6)2 (4.6)5 (11.6)9 (20)17 (39.5)6 (13.9)6 (13.9)2 (4.6)1 (2.3)2 (4.6)Table 2 Clinical characteristics of uveítis from SUN criteria.Uveitis, n(%)43 (9,53)Age 1° outbreak, years ± DE45 ± 23TypeAnterior, n (%)Intermedite, n (%)Posterior, n (%)Panuveitis, n (%)39 (90.7)2(4.6)02(4.6)Unilateral, n (%)Bilateral, n (%)35(81.4)8 (18.6) OnsetSudden, n (%)Insidious, n (%)DurationLimited (<=3 meses) n (%)Persistent (>3 meses) n(%)CourseAcute * n(%)Recurrent ** n (%)Chronic *** n (%)42 (97.6)1 (2.3)38 (88.3)5(11.6)13 (30.2)22(51.2)8(18.6) Treatment UveitisCorticosteroids topics, n (%)FAME (sulfasalazine), n (%)39 (90.6)2 (4.6)* Episode sudden onset and limited duration ** Repeated episodes separated by periods of inactivity without treatment 3 months in duration ***Persistent uveitis with relapse in 3 months after disc...
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.