S.V. Degtyarev - Dr.Sc. (Eng.), Professor, Southwest State University
S. A. Filist - Dr.Sc. (Eng.), Professor, Southwest State University
M.V. Dyudin - Post-graduate Student, Southwest State University

The article defines the importance of early detection and differential diagnosis of lung diseases. It is proposed to use the principles of multi-agent intelligent systems for solving of the problem. The principles of the analysis of the LMS Autonomous intelligent agents. Image classification is intelligent agent on the upper hierarchical level. As the main paradigms of classification LMS used contour analysis, fractal analysis and hybrid technology. The classification is based on the principles of fuzzy decision rules based on empirical knowledge of the doctor-radiologist. The article presents the diagram of the algorithm analysis fluorogram in multi-agent system. Characterized by a complex of tasks, which are solved by each agents at the appropriate level. Created database of classification models for specific pathological deviations images of fluorogram. For the implementation of image processing algorithms in the environment of the automated system of Express-diagnostics is proposed to use technology FPGA (field-programmable gate array). It is noted that the use of FPGA technologies will allow reducing the time required to process images. The offered principle of multi-agent systems intelligent support of decision making will allow to solving the main problem of diagnostics of lung diseases in LMS associated with limitation of diagnostics according to one projection.