In this paper we consider method, proposed by the authors, for pre-processing X-ray images based on the convolutional neural network. Multilayer computed tomography scans of the lungs are ubiquitous, used to detect pathology, such as covid-19 diseases. The proposed method consists of computed tomography lung image segmentation, the volume of interest localization at these scans, distinguishing between denser structures, such as bones, and less dense ones, such as blood vessels. A comparison of the pathological formations classification quality was made on images with different degrees of preprocessing on large data sets. Image Classifier software was developed for demonstration of x-rays preliminary processing opportunities in the context of their class association forecasting. The developed software showed quite good results. Maximum value of the average probability reached 77.5%. The number of epochs required to achieve the specified quality level is four.
Nowadays the multi-layer computed tomography (CT) shots with contrast dye used for detection of small pathological growths regions are widely spread in medical clinics. Although, CT study with contrast dye use has contraindications and is much more expensive for patients than study without use of dye. This article proposes the algorithm based on segmentation of three-dimensional signal received from CT (without dye use). The algorithm allows to identify a pathological growths automatically and to detect studying object regions with the help of 3D graph model based on received data. Algorithm also evaluates parameters of small objects and sinuses, which occupy only small part of initial CT layers, with high accuracy.
Nowadays the multilayer computed tomography shots with contrast dye used for detection of small pathological growth are widespread in medical clinics. Although, tomography study with contrast dye use has contraindications and is much more expensive for patients than study without use of dye. This article proposes data processing method based on segmentation of multilayer computed tomography shots without use of dye. The method allows to automatically identify pathological growths and to detect studying object areas. The software, developed according to this method, evaluates parameters of small objects and sinuses, which occupy only small part of initial computed tomography layers, with high accuracy.
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.