en
Scientific article
English

Robust-Deep: A Method for Increasing Brain Imaging Datasets to Improve Deep Learning Models' Performance and Robustness

First online date2022-02-08
Abstract

A small dataset commonly affects generalization, robustness, and overall performance of deep neural networks (DNNs) in medical imaging research. Since gathering large clinical databases is always difficult, we proposed an analytical method for producing a large realistic/diverse dataset. Clinical brain PET/CT/MR images including full-dose (FD), low-dose (LD) corresponding to only 5 % of events acquired in the FD scan, non-attenuated correction (NAC) and CT-based measured attenuation correction (MAC) PET images, CT images and T1 and T2 MR sequences of 35 patients were included. All images were registered to the Montreal Neurological Institute (MNI) template. Laplacian blending was used to make a natural presentation using information in the frequency domain of images from two separate patients, as well as the blending mask. This classical technique from the computer vision and image processing communities is still widely used and unlike modern DNNs, does not require the availability of training data. A modified ResNet DNN was implemented to evaluate four image-to-image translation tasks, including LD to FD, LD+MR to FD, NAC to MAC, and MRI to CT, with and without using the synthesized images. Quantitative analysis using established metrics, including the peak signal-to-noise ratio (PSNR), structural similarity index metric (SSIM), and joint histogram analysis was performed for quantitative evaluation. The quantitative comparison between the registered small dataset containing 35 patients and the large dataset containing 350 synthesized plus 35 real dataset demonstrated improvement of the RMSE and SSIM by 29% and 8% for LD to FD, 40% and 7% for LD+MRI to FD, 16% and 8% for NAC to MAC, and 24% and 11% for MRI to CT mapping task, respectively. The qualitative/quantitative analysis demonstrated that the proposed model improved the performance of all four DNN models through producing images of higher quality and lower quantitative bias and variance compared to reference images.

eng
Keywords
  • Attenuation correction
  • Brain PET
  • Data augmentation
  • Deep learning
  • Low-dose
Citation (ISO format)
SANAAT, Amirhossein et al. Robust-Deep: A Method for Increasing Brain Imaging Datasets to Improve Deep Learning Models” Performance and Robustness. In: Journal of digital imaging, 2022. doi: 10.1007/s10278-021-00536-0
Main files (1)
Article (Published version)
Identifiers
ISSN of the journal0897-1889
138views
0downloads

Technical informations

Creation02/09/2022 9:26:00 AM
First validation02/09/2022 9:26:00 AM
Update time03/16/2023 2:39:15 AM
Status update03/16/2023 2:39:15 AM
Last indexation05/06/2024 9:55:17 AM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack