DOI:
10.18413/2518-1092-2020-5-1-0-3
INCREASING ACCURACY CLASSIFICATION OF X-RAY IMAGES USING TRAINING OF COMPOSITE NEURAL NETWORK
This article is devoted to solving the problem of classifying chest x-ray images by using the retraining of a pre-trained convolutional neural network trained on small data sets. A trained binary classifier is used to detect the presence or absence of lower respiratory tract pathology. The paper presents the results of a computational experiment and shows an improvement in accuracy in solving the classification problem. The study aims to identify a qualitative improvement in the accuracy index when using a composite neural network.
Keywords: image classification,
chest x-rays,
composite neural networks,
neural networks,
convolutional neural networks,
keras,
tensorflow.
Number of views: 1114 (view statistics)
Количество скачиваний: 5159
While nobody left any comments to this publication.
You can be first.
The references will appear later