Journal
Scientific and Technical Journal of Information Technologies, Mechanics and Optics
UDK004.891
Issue:4 (156)
Method of muscle tissue segmentation in computed tomography images based on preprocessed three-channel images
Annotation
The results of a study of a preprocessing influence method based on the formation of three-channel images on the accuracy of muscle tissue segmentation models on the computed tomography scans corresponding to the levels of the vertebrae of the thoracic and lumbar spine are presented. Ten models have been trained and tested on the Sparsely Annotated Region and Organ Segmentation dataset. The values of the Dice similarity coefficient and the Intersection over Union in the ranges of 0.9353–0.9421 and 0.8737–0.8885 were obtained. The use of a three-channel approach to the formation of input data increased the accuracy of models of four of the five architectures considered. Trained models can be used to quickly and accurately annotate muscle tissue during the diagnostic process.
Keywords
Постоянный URL
Articles in current issue
- Organic-inorganic light-absorbing composites for near infrared part of spectrum
- Study of pyroelectric effect and creation of modified design of phase modulator based on lithium niobate
- Contrast change of the test object image in single-pixel and focal-plane array imaging through a scattering medium
- Synthesis of adaptive observer for nonlinear nonstationary systems
- Automation of search for optimal values of the ethylene oligomerization process parameters
- Electroluminescence of new coordination compounds of europium ions with β-diketones, acetic and butyric acids
- Method for generating multimedia files for the tasks of facial biometrics and its applications
- Advanced methods for knowledge injection in large language models
- Predicting gene-disease associations using a heterogeneous graph neural network
- Computer simulation of the interaction between a shock wave and a wall shielded by an inhomogeneous gas suspension layer
- Flexible and tractable modeling of multivariate data using composite Bayesian networks
- Method for obtaining two-component composite materials with a given thermal conductivity
- Computer simulation of heat and mass transfer processes during water vapor condensation from natural gas combustion products on smooth cylindrical tubes
- Instability of a rectangular CCCC-nanoplate
- Using genetic algorithms to solve the problem of finding the optimal composition of the reaction mixture
- Configurable combustion models of combustion chamber of microturbine engine with possibility of connecting various physico-chemical processes
- Multilevel splitting for rare events estimation in permutation tests
- Model of adsorption on epitaxial graphene: analytical results