Back to articles
Proceedings Paper
Volume: 36 | Article ID: MWSF-342
Image
DeepMammo: Deep Learning Algorithm for Digital Mammogram Source Identification
  DOI :  10.2352/EI.2024.36.4.MWSF-342  Published OnlineJanuary 2024
Abstract
Abstract

Advances in AI allow for fake image creation. These techniques can be used to fake mammograms. This could impact patient care and medicolegal cases. One method to verify that an image is original is to confirm the source of the image. A deep-learning algorithm(DeepMammo)-based on CNNs and FCNNs, used to identify the machine that created any mammogram. We analyze mammograms of 1574 patients obtained on 7-different mammography machines and randomly split the dataset by patient into training/validation(80%) and test(20%) datasets. DeepMammo has an accuracy of 98.09%, AUC of 95.96% in the test dataset.

Subject Areas :
Views 56
Downloads 16
 articleview.views 56
 articleview.downloads 16
  Cite this article 

Farid Ghareh Mohammadi, Ronnie Sebro, "DeepMammo: Deep Learning Algorithm for Digital Mammogram Source Identificationin Electronic Imaging,  2024,  pp 342-1 - 342-5,  https://doi.org/10.2352/EI.2024.36.4.MWSF-342

 Copy citation
  Copyright statement 
Copyright © 2024, Society for Imaging Science and Technology 2024
ei
Electronic Imaging
2470-1173
2470-1173
Society for Imaging Science and Technology
IS&T 7003 Kilworth Lane, Springfield, VA 22151 USA