The Repository of VNAU

MAIN | BY YEARS | COLLECTIONS| BY TYPES| BY DEPS | SEARCH| LOGIN | ABOUT| RSS |

id: 33688
Title: Convolutional neural networks for early computer diagnosis of child dysplasia
Authors: Bilynsky Y., Nikolskyy A., Revenok V., Pogorilyi V., Smailova S., Voloshina O., Kumargazhanova S.
Keywords: convolutional neural networks, computer diagnosis, ultrasound image child dysplasia
Date of publication: 2023-08-08 10:46:20
Last changes: 2023-08-08 10:46:20
Year of publication: 2023
Summary: The problem in ultrasound diagnostics hip dysplasia is the lack of experience of the doctor in case of incorrect orientation of the hip joint and ultrasound head. The aim of this study was to evaluate the ability of the convolutional neural network (CNN) to classify and recognize ultrasound imaging of the hip joint obtained at the correct and incorrect position of the ultrasound sensor head in the computer diagnosis of pediatric dysplasia. CNN`s such as GoogleNet, SqueezeNet, and AlexNet were selected for the study. The most optimal for the task is the use of CNN GoogleNet showed. In this CNN used transfer learning. At the same time, fine-tuning of the network and additional training on the database of 97 standards of ultrasonic images of the hip joint were applied. Image type RGB 32 bit, 210 × 300 pixels are used. Fine-tuning has been performed the lower layers of the structure CNN, in which 5 classes are allocated, respectively 4 classes of hip dysplasia types according to the Graf, and the Type ERROR ultrasound image, where position of the ultrasound sensor head and of the hip joint in ultrasound diagnostics are incorrect orientation. It was found that the authenticity of training and testing is the highest for the GoogleNet network: when classified in the training group accuracy is up to 100%, when classified in the test group accuracy – 84.5%.

URI: http://socrates.vsau.org/repository/getfile.php/33688.pdf
Publication type: Статті Scopus
Publication: Informatyka, Automatyka, Pomiary w Gospodarce I Ochronie Srodowiska. 2023 Vol. 13, № 2. P. 56-63. DOI: http://doi.org/10.35784/iapgos.3499
In the collections :
Published by: Адміністратор
File : 33688.pdf Size : 4922095 byte Format : Adobe PDF Access : For all

Enlarge

"Socrates" System  |   VNAU official site Copyright © 2013, coding by Y.Palamarchuck, design by R.Yatskovska