Abstract
The problem of generating training data for setting up the convolutional neural networks is considered, which is of great importance in the construction of intelligent medical diagnostic systems, where due to the lack of elements of the training sample, it is proposed to use the approaches of artificial data multiplication based on the initial training sample of a fixed size for the image processing (the results of the ultrasound, CT and MRI). It shows that the increase of the training sample resulted in less informative and poor quality elements, which can introduce extra errors in the goal achievement. To eliminate this situation the algorithm for assessing the quality of a sample element with the subsequent removal of uninformative elements is proposed.
Highlights
Neural networks have been actively developing in the last decade
Neural networks contributed actively to image processing which became widely used throughout different applications
Convolutional neural networks (CNNs) are efficient image processing tools. They are actively used in intelligent medical diagnostic systems for processing the results of the ultrasound, CT, and MRI images
Summary
Neural networks have been actively developing in the last decade. They demonstrate excellent quality of solving classification problems, forecasting, etc. versus other machine learning algorithms. Convolutional neural networks (CNNs) are efficient image processing tools. The CNN training issue consists of the importance to create a training dataset, which, on the one hand, must have the optimum size, and, on the other hand, be informative in order to train the convolutional neural network to mark the mean image parameters. The existing sampling techniques suffer from many shortcomings, making them either very slow processed, or resource-demanded, or undefined quality criteria for the sample to be formed. These efforts aim to create the improving samples quality algorithm, due to the introduction of quality criteria, reducing computing resources use, as well as time reduction for the formation process
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
