Investigation of the Use of Neural Networks for Diagnosing Breast Cancer on Mammograms

(E-pub Abstract Ahead of Print)

Author(s): Galina S. Ivanova*, Alexander A. Golovkov, Iana S. Petrova, Alexander A. Borodin, Anastasia O. Shakhlan, Alexander V. Umnov, Kristina A. Lonshakova, Vladimir V. Kelenin

Journal Name: Current Medical Imaging
Formerly: Current Medical Imaging Reviews

Become EABM
Become Reviewer
Call for Editor


Introduction: This study demonstrates the possibility of detecting tumors on mammograms with high accuracy (more than 72%) using neural networks and studies the characteristics of machine learning models for improving their efficiency.

Methods: We proposed image preprocessing methods that enable high classification accuracy, as well as methods of increasing the training set and balancing the distribution of diagnostic classes when the training set is small. The classification has been done for four diagnostic classes: dysplasia, pre-cancer state (ductal carcinoma in situ), cancer state (invasive carcinoma), and benign tumor.

Results and Conclusion: We conducted experiments to compare different models based on convolution neural networks and proposed methods for estimating the model quality. We obtained a base model that can be used to make recommendations to establish a diagnosis. We studied the characteristics of the base model and identified promising directions of modification for further improving the quality estimates.

Keywords: Cancer diagnostics, deep machine learning, neural networks, mammogram, breast cancer, ductal carcinoma.

Rights & PermissionsPrintExport Cite as

Article Details

Published on: 07 July, 2021
(E-pub Abstract Ahead of Print)
DOI: 10.2174/1573405617666210707155835
Price: $95