CLINICAL DECISIONSUPPORT SYSTEM WITH PROCESSING OF MULTIMODAL MEDICAL DATA FOR RADIOLOGIST EFFICIENCY IMPROVEMENT PRACTICE
Annotation
Subject of Research.The paper proposes a clinical decision support system using multimodal data. Method. The system is based on neural network models. The author proposes the methods of transfer learning with domain adaptation techniques, training on multimodal data and taking into account the negative knowledge transfer for the quality improvement of preliminary analysis of medical data with application of neural network models. Algorithms of neural networks for preliminary analysis of the patient study provide the analysis of multimodal data with consideration of the combination peculiarities of modalities, training of neural networks with specific domain adaptation techniques, and taking into account the phenomenon of the knowledge negative transfer for the increase of the neural network robustness to the natural equipment noise. Main Results. The proposed system is implemented as a web-platform. The implemented system effectiveness was assessed by involving 30 experts: doctors, students, and patients. A comparative assessment of the problems solution in various scenarios was carried out with the proposed system and without it. Experiments have shown that the proposed system application reduces the execution time of the most critical stages of scenarios. Practical Relevance. The proposed system is located in the ITMO domain at the uniform resource locatoraddress: http://mcp.itmo.ru and is used in the practice of the Almazov National Medical Research Centre of the Ministry of Health of Russia, and the “City Children's Infectious Disease Clinical Hospital” Healthcare Institution in Minsk. The system is recommended for the application in clinical hospitals, individual practitioners and teaching radiologists.
Keywords
Постоянный URL
Articles in current issue
- APPLICATION OF INDUCED MECHANICAL STRESSES IN FORMATION OF SPHERICAL SURFACES OF INTERFERENCE MIRROR SUBSTRATES
SENSITIVITY VARIATION RESEARCH OF TILTED FIBER BRAGG GRATING DURING CHEMICAL ETCHING
- APLICATION FEATURES OF OPTICAL POLYMERS IN OPTICAL SYSTEMS DESIGN
- EFFECT OF PLANT EXTRACTS ON ACTIVITY OF STAPHYLOCOCCUS AUREUS BY ELECTROCHEMICAL BIOTESTING
- FAST MOTION ESTIMATION ALGORITHM FOR HEVC VIDEO CODEC
- METHOD OF JOINT CLUSTERING IN NETWORK AND CORRELATION SPACES
- CONCEPT OF DIGITAL TWINS AT LIFE CYCLE STAGES OF PRODUCTION SYSTEMS
- HYPERPARAMETER OPTIMIZATION BASED ON APRIORI AND A POSTERIORI KNOWLEDGE ABOUT CLASSIFICATION PROBLEM
- INFERRING OF REGULATORY NETWORKS FROM EXPRESSION DATA USING BAYESIAN NETWORKS
- APPLICATION OF INCREMENTAL SATISFIABILITY PROBLEM SOLVERS FOR NON-DETERMINISTIC POLYNOMIAL-TIME HARD PROBLEMS AS ILLUSTRATED BY MINIMAL BOOLEAN FORMULA SYNTHESIS PROBLEM
- DISTRIBUTION EVALUATION OF REFLECTIVE CHARACTERISTICS WITH QUASI-CONTINUOUS ULTRA-WIDEBAND PROBING SIGNAL
- ADAPTIVE PROBLEM OF EXTENDED REPRODUCTION WITH MINIMIZATION OF GENERALIZED COSTS
- PREDICTION OF REACTION CONDITIONS BY DEEP LEARNING TECHNIQUES
- MODELING OF VERTICAL LIGHT PIPES FOR DAYLIGHT ILLUMINATION OF INDOOR INDUSTRIAL BUILDINGS(in English)
- CONDITION EQUATION OF POLYMER FILAMENTS
- PREDICTION OF MECHANICAL PROPERTIES FOR ONE-DIMENSIONAL POLYMER STRUCTURES
- INDEPENDENT COMPONENT ANALYSIS FOR INITIAL APPROXIMATION DETERMINATION IN IDENTIFICATION OF ACTIVE MODULES IN BIOLOGICAL GRAPHS