Impact of loss functions on the performance of a deep neural network designed to restore low-dose digital mammography

11/12/2021
by   Hongming Shan, et al.
9

Digital mammography is still the most common imaging tool for breast cancer screening. Although the benefits of using digital mammography for cancer screening outweigh the risks associated with the x-ray exposure, the radiation dose must be kept as low as possible while maintaining the diagnostic utility of the generated images, thus minimizing patient risks. Many studies investigated the feasibility of dose reduction by restoring low-dose images using deep neural networks. In these cases, choosing the appropriate training database and loss function is crucial and impacts the quality of the results. In this work, a modification of the ResNet architecture, with hierarchical skip connections, is proposed to restore low-dose digital mammography. We compared the restored images to the standard full-dose images. Moreover, we evaluated the performance of several loss functions for this task. For training purposes, we extracted 256,000 image patches from a dataset of 400 images of retrospective clinical mammography exams, where different dose levels were simulated to generate low and standard-dose pairs. To validate the network in a real scenario, a physical anthropomorphic breast phantom was used to acquire real low-dose and standard full-dose images in a commercially avaliable mammography system, which were then processed through our trained model. An analytical restoration model for low-dose digital mammography, previously presented, was used as a benchmark in this work. Objective assessment was performed through the signal-to-noise ratio (SNR) and mean normalized squared error (MNSE), decomposed into residual noise and bias. Results showed that the perceptual loss function (PL4) is able to achieve virtually the same noise levels of a full-dose acquisition, while resulting in smaller signal bias compared to other loss functions.

READ FULL TEXT

page 4

page 5

page 8

page 9

page 10

research
03/22/2022

Convolutional Neural Network to Restore Low-Dose Digital Breast Tomosynthesis Projections in a Variance Stabilization Domain

Digital breast tomosynthesis (DBT) exams should utilize the lowest possi...
research
12/12/2017

200x Low-dose PET Reconstruction using Deep Learning

Positron emission tomography (PET) is widely used in various clinical ap...
research
08/24/2023

Full-dose PET Synthesis from Low-dose PET Using High-efficiency Diffusion Denoising Probabilistic Model

To reduce the risks associated with ionizing radiation, a reduction of r...
research
02/11/2020

FastPET: Near Real-Time PET Reconstruction from Histo-Images Using a Neural Network

Direct reconstruction of positron emission tomography (PET) data using d...
research
06/26/2020

Cascaded Convolutional Neural Networks with Perceptual Loss for Low Dose CT Denoising

Low Dose CT Denoising research aims to reduce the risks of radiation exp...
research
09/14/2020

Simultaneous Denoising and Motion Estimation for Low-dose Gated PET using a Siamese Adversarial Network with Gate-to-Gate Consistency Learning

Gating is commonly used in PET imaging to reduce respiratory motion blur...
research
06/03/2021

Fast improvement of TEM image with low-dose electrons by deep learning

Low-electron-dose observation is indispensable for observing various sam...

Please sign up or login with your details

Forgot password? Click here to reset