Lightweight CNN for Detecting Microcalcifications Clusters in Digital Mammograms

Authors

  • Ricardo Salvador Luna-Lozoya Universidad Autónoma de Ciudad Juárez
  • Humberto de Jesús Ochoa-Domínguez Universidad Autónoma de Ciudad Juárez
  • Juan Humberto Sossa-Azuela Instituto Politécnico Nacional
  • Vianey Guadalupe Cruz-Sánchez Universidad Autónoma de Ciudad Juárez
  • Osslan Osiris Vergara-Villegas Universidad Autónoma de Ciudad Juárez

DOI:

https://doi.org/10.13053/cys-28-1-4892

Keywords:

Microcalcifications clusters detection, shallow convolutional neural network, deep learning

Abstract

Digital mammogram plays a key role inbreast cancer screening, with microcalcifications beingan important indicator of an early stage. However,these injuries are difficult to detect. In this paper,we propose a lightweight Convolutional Neural Network(CNN) for detecting microcalcifications clusters indigital mammograms. The architecture comprises twoconvolutional layers with 6 and 16 filters of 9×9,respectively at a full scale, a global pooling layer thateliminates the flattening and dense layers, and a sigmoidfunction as the output layer for binary classification. Totrain the model, we utilize the public INbreast databaseof digital mammograms with labeled microcalcificationclusters. We used data augmentation techniques toartificially increase the training set. Furthermore, wepresent a case study that encompasses the utilizationof a software application. After training, the resultingmodel yielded an accuracy of 99.3% with only 8,301parameters. This represents a considerable parameterreduction as compared to the 67,797,505 used inMobileNetV2 with 99.8 % accuracy.

Downloads

Published

2024-03-20

Issue

Vol. 28 No. 1 (2024): 28(1) 2024

Section

Articles of the Thematic Section

License 

Hereby I transfer exclusively to the Journal "Computación y 
Sistemas", published by the Computing Research Center (CIC-IPN),
the Copyright of the aforementioned paper. I also accept that these 
rights will not be transferred to any other publication, in any other 
format, language or other existing means of developing.
I certify that the paper has not been previously disclosed or simultaneo
usly submitted to any other publication, and that it does not contain 
material whose publication would violate the Copyright or other 
proprietary rights of any person, company or institution. I certify that 
I have the permission from the institution or company where I work or 
study to publish this work.
The representative author accepts the responsibility for the publication
of this paper on behalf of each and every one of the authors. 
This transfer is subject to the following conditions:
  • The authors retain all ownership rights (such as patent rights) of this work, except for the publishing rights transferred to the CIC, through this document.
  • Authors retain the right to publish the work in whole or in part in any book they are the authors or publishers. They can also make use of this work in conferences, courses, personal web pages, and so on.
  • Authors may include working as part of his thesis, for non-profit distribution only.