Diabetes can lead to a number of serious complications, in particular, diabetic retinopathy, which occurs in patients with diabetes and can lead to vision loss. In this regard, the development of an information system for the diagnosis of diabetic retinopathy is an important task in the medical field. Such a system can greatly facilitate the diagnostic process and help doctors detect and treat diabetic retinopathy in time. As a result of the conducted research, the urgent task of increasing the accuracy of diagnosis of fundus diseases was solved by using methods of pre-processing images to improve their informative characteristics, statistical analysis and differentiation of pathologies with the help of a decision support system based on neural network technologies. A comparative analysis of the existing methods of diagnosing diabetic retinopathy and other eye diseases was carried out, according to which it is clear that intellectual analysis and pre-processing of the received images of the fundus can significantly improve the results of diagnostics, especially early screening, which is important for preventing severe stages of the disease.
Periodic fiber structures generally referred to as fiber Bragg gratings are of increasing interest to sensor designers. In recent years, structures in which the phase planes are not perpendicular to the fiber axis have appeared. The paper is devoted to modeling the dependence of the TFBG spectral response on the phase plane tilt angle. The article also contains measurement results of gratings produced on the basis of the model.
The Jones matrix mapping of blood plasma films was considered in this paper. The statistical analysis (statistical moments of the 1st - 4th orders) of the obtained elements was carried out. To increase the accuracy and reliability of the diagnosis, the number of informative indicators was increased due to the correlation analysis. which increased the number of inputs to 8. The differentiation of nosologies was based on the rules of fuzzy logic.
A fibroadenoma diagnosing of breast using statistical analysis (determination and analysis of statistical moments of the 1st-4th order) of the obtained polarization images of Jones matrix imaginary elements of the optically thin (attenuation coefficient τ ≤ 0,1 ) blood plasma films with further intellectual differentiation based on the method of “fuzzy” logic and discriminant analysis were proposed. The accuracy of the intellectual differentiation of blood plasma samples to the "norm" and "fibroadenoma" of breast was 82.7% by the method of linear discriminant analysis, and by the "fuzzy" logic method is 95.3%. The obtained results allow to confirm the potentially high level of reliability of the method of differentiation by "fuzzy" analysis.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.