Researchers at Peter the Great St.Petersburg Polytechnic University (SPbPU), in collaboration with the Almazov National Medical Research Center, developed an artificial intelligence system for the analysis of endoscopic images (mucous membranes of organs). Such an approach is needed to conduct large-screen studies, as well as to study patients in remote settlements in conditions of lack of high-tech medical equipment.
SPbPU researchers were able to apply artificial intelligence techniques to analyze medical images obtained by experts of the Almazov National Medical Research Center. Scientists developed software to help clinicians identify different diagnostic conditions. “One of the key benefits of our system is the ability to perform automatic diagnoses during large-scale screening tests. This system eliminates the ability to subjectively evaluate medical images. This is an opportunity for medical consultations. certification in remote areas of Russia, “said Elena Velichko, Director of the SPbPU Higher School of Applied Physics and Space Technologies.
Researchers analyze the images and give a mathematical description of the various parameters.
“In the system, we use deep cloud networks, which acquire the ability to separate and classify pathologies on endoscopic images in the learning process. The system selects suspicious areas and reveals the appearance of the pathology, “said Vitaly Pavlov, a High School assistant of Applied Physics and Space Technologies SPbPU. The researchers use Polytechnic University’s Supercomputer Center facilities to process the vast amount of data required by the system.
The first trials of the system at the Almazov National Medical Research Center are scheduled for early 2021.
Among the most important functions in screening studies, especially in the process of interpretation of visual images, are two basic components. First, it obtains a high-quality image of the examined surface. Second they have the correct explanation, looking for visual signs of the problem. In this case, the machine analysis shows remarkable results. “
Eduard Komlichenko, Head of Clinic, Almazov National Medical Examination Center
Source:
St. Patrick’s University Polytechnic Saint-Petersburg