The automatic detection of exudates in color eye fundus images is an important task in applications such as diabetic retinopathy screening. The presented work has been undertaken in the framework of the TeleOphta project, whose main objective is to automatically detect normal exams in a tele-ophthalmology network, thus reducing the burden on the readers. A new clinical database, e-ophtha EX, containing precisely manually contoured exudates, is introduced. As opposed to previously available databases, e-ophtha EX is very heterogeneous. It contains images gathered within the OPHDIAT telemedicine network for diabetic retinopathy screening. Image definition, quality, as well as patients condition or the retinograph used for the acquisition, for example, are subject to important changes between different examinations. The proposed exudate detection method has been designed for this complex situation. We propose new preprocessing methods, which perform not only normalization and denoising tasks, but also detect reflections and artifacts in the image. A new candidates segmentation method, based on mathematical morphology, is proposed. These candidates are characterized using classical features, but also novel contextual features. Finally, a random forest algorithm is used to detect the exudates among the candidates. The method has been validated on the e-ophtha EX database, obtaining an AUC of 0.95. It has been also validated on other databases, obtaining an AUC between 0.93 and 0.95, outperforming state-of-the-art methods.
Objectives
Molecular assays on nasopharyngeal swabs remain the cornerstone of COVID-19 diagnostic. The high technicalities of nasopharyngeal sampling and molecular assays, as well as scarce resources of reagents, limit our testing capabilities. Several strategies failed, to date, to fully alleviate this testing process (e.g. saliva sampling or antigen testing on nasopharyngeal samples). We assessed the clinical performances of SARS-CoV-2 nucleocapsid antigen (N-antigen) ELISA detection in serum or plasma using the COVID-19 Quantigene® (AAZ, France) assay.
Methods
Performances were determined on 63 sera from 63 non-COVID patients and 227 serum samples (165 patients) from the French COVID and CoV-CONTACT cohorts with RT-PCR confirmed SARS-CoV-2 infection, including 142 serum (114 patients) obtained within 14 days after symptoms’ onset.
Results
Specificity was 98.4% (95% confidence interval [CI], 95.3 to 100). Sensitivity was 79.3% overall (180/227, 95% CI, 74.0 to 84.6) and 93.0% (132/142, 95% CI, 88.7 to 97.2) within 14 days after symptoms onset. 91 included patients had a sera and nasopharyngeal swabs collected in the same 24 hours. Among those with high nasopharyngeal viral loads, i.e. Ct value below 30 and 33, only 1/50 and 4/67 tested negative for N-antigenemia, respectively. Among those with a negative nasopharyngeal RT-PCR, 8/12 presented positive N-antigenemia; the lower respiratory tract was explored for 6 of these 8 patients, showing positive RT-PCR in 5 cases.
Conclusion
This is the first evaluation of a commercially available serum N-antigen detection assay. It presents a robust specificity and sensitivity within the first 14 days after symptoms onset. This approach provides a valuable new option for COVID-19 diagnosis, only requiring a blood draw and easily scalable in all clinical laboratories.
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.