Denoising digital breast tomosynthesis projections using deep learning with synthetic data as training set

Darlan M. Nakamura de Araújo; Denis Henrique Pinheiro Salvadeo; Davi D. de Paula

doi:10.1117/1.JMI.10.3.034001

22 May 2023 Denoising digital breast tomosynthesis projections using deep learning with synthetic data as training set

Darlan M. Nakamura de Araújo, Denis Henrique Pinheiro Salvadeo, Davi D. de Paula

Author Affiliations +

Journal of Medical Imaging, Vol. 10, Issue 3, 034001 (May 2023). https://doi.org/10.1117/1.JMI.10.3.034001

Abstract

Purpose

Image denoising based on deep neural networks (DNN) needs a big dataset containing digital breast tomosynthesis (DBT) projections acquired in different radiation doses to be trained, which is impracticable. Therefore, we propose extensively investigating the use of synthetic data generated by software for training DNNs to denoise DBT real data.

Approach

The approach consists of generating a synthetic dataset representative of the DBT sample space by software, containing noisy and original images. Synthetic data were generated in two different ways: (a) virtual DBT projections generated by OpenVCT and (b) noisy images synthesized from photography regarding noise models used in DBT (e.g., Poisson–Gaussian noise). Then, DNN-based denoising techniques were trained using a synthetic dataset and tested for denoising physical DBT data. Results were evaluated in quantitative (PSNR and SSIM measures) and qualitative (visual analysis) terms. Furthermore, a dimensionality reduction technique (t-SNE) was used for visualization of sample spaces of synthetic and real datasets.

Results

The experiments showed that training DNN models with synthetic data could denoise DBT real data, achieving competitive results to traditional methods in quantitative terms but showing a better balance between noise filtering and detail preservation in a visual analysis. T-SNE enables us to visualize if synthetic and real noises are in the same sample space.

Conclusion

We propose a solution for the lack of suitable training data to train DNN models for denoising DBT projections, showing that we just need the synthesized noise to be in the same sample space as the target image.

Citation Download Citation

Darlan M. Nakamura de Araújo, Denis Henrique Pinheiro Salvadeo, and Davi D. de Paula "Denoising digital breast tomosynthesis projections using deep learning with synthetic data as training set," Journal of Medical Imaging 10(3), 034001 (22 May 2023). https://doi.org/10.1117/1.JMI.10.3.034001

Received: 2 August 2022; Accepted: 1 May 2023; Published: 22 May 2023

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $24.00

Non-members: $28.00 ADD TO CART

JOURNAL ARTICLE
27 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Digital breast tomosynthesis

Education and training

Denoising

Data modeling

Breast

Tunable filters

Visualization

Purpose

Approach

Results

Conclusion

Show All Keywords

Keywords/Phrases

Search In:

Publication Years