TELKOMNIKA Telecommunication, Computing, Electronics and Control
Evaluation of deep neural network architectures in the identification of bone fissures
Dublin Core
Title
TELKOMNIKA Telecommunication, Computing, Electronics and Control
Evaluation of deep neural network architectures in the identification of bone fissures
Evaluation of deep neural network architectures in the identification of bone fissures
Subject
Biomedical computing, Deep neural network, Fissures recognition, Image processing
Description
Automated medical image processing, particularly of radiological images, can reduce the number of diagnostic errors, increase patient care and reduce medical costs. This paper seeks to evaluate the performance of three recent convolutional neural networks in the autonomous identification of fissures over two-dimensional radiological images. These architectures have been proposed as deep neural network types specially designed for image classification, which allows their integration with traditional image processing strategies for automatic analysis of medical images. In particular, we use three convolutional networks: ResNet (residual neural network), DenseNet (dense convolutional network), and NASNet (neural architecture search
network) to learn information from a set of 200 images labeled half as fissured bones and half as seamless bones. All three networks are trained and adjusted under the same conditions, and their performance was evaluated with the same metrics. The final results consider not only the model's ability to predict the characteristics of an unknown image but also its internal complexity. The three neural models were optimized to reduce classification errors without producing network over-adjustment. In all three cases, generalization of behavior was observed, and the ability of the models to identify the images with fissures, however the expected performance was only achieved with the NASNet model.
network) to learn information from a set of 200 images labeled half as fissured bones and half as seamless bones. All three networks are trained and adjusted under the same conditions, and their performance was evaluated with the same metrics. The final results consider not only the model's ability to predict the characteristics of an unknown image but also its internal complexity. The three neural models were optimized to reduce classification errors without producing network over-adjustment. In all three cases, generalization of behavior was observed, and the ability of the models to identify the images with fissures, however the expected performance was only achieved with the NASNet model.
Creator
Fredy Martínez, César Hernández, Fernando Martínez
Source
DOI: 10.12928/TELKOMNIKA.v18i2.14754
Publisher
Universitas Ahmad Dahlan
Date
April 2020
Contributor
Sri Wahyuni
Rights
ISSN: 1693-6930
Relation
http://journal.uad.ac.id/index.php/TELKOMNIKA
Format
PDF
Language
English
Type
Text
Coverage
TELKOMNIKA Telecommunication, Computing, Electronics and Control
Files
Collection
Citation
Fredy Martínez, César Hernández, Fernando Martínez, “TELKOMNIKA Telecommunication, Computing, Electronics and Control
Evaluation of deep neural network architectures in the identification of bone fissures,” Repository Horizon University Indonesia, accessed November 22, 2024, https://repository.horizon.ac.id/items/show/3683.
Evaluation of deep neural network architectures in the identification of bone fissures,” Repository Horizon University Indonesia, accessed November 22, 2024, https://repository.horizon.ac.id/items/show/3683.