Optimizing hyperparameters in multiview convolutional neural network for improved breast cancer detection in mammograms

According to data from the World Health Organization (WHO) in 2020, 7.8 million women were diagnosed with breast cancer, and the same year witnessed 684,996 deaths attributed to breast cancer [1], [2]. [...]automatic breast cancer detection with the aid of computers is necessary to assist doctors an...

Full description

Saved in:
Bibliographic Details
Published in:Telkomnika 2024-08, Vol.22 (4), p.921-930
Main Authors: Anggraini, Sisilia, Sardjono, Tri, Hikmah, Nada Fitrieyatul
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
Artificial neural networks
Breast cancer
Classification
Datasets
Deep learning
Image enhancement
Machine learning
Mammography
Medical imaging
Neural networks
Tomography
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:According to data from the World Health Organization (WHO) in 2020, 7.8 million women were diagnosed with breast cancer, and the same year witnessed 684,996 deaths attributed to breast cancer [1], [2]. [...]automatic breast cancer detection with the aid of computers is necessary to assist doctors and radiologists in the diagnostic process. Furthermore, machine learning performance is highly dependent on various hyperparameters such as architecture, the number of filters, kernel size, and stride in convolution and pooling layers. [...]this study aims to classify mammography images by combining the use of an image preprocessing framework and enhancing classification performance by finding the best hyperparameters. [...]the MVCNN is employed to classify breast cancer. 2.1.
ISSN:1693-6930
2302-9293
DOI:10.12928/TELKOMNIKA.v22i4.25846