Performance comparison of convolutional neural network based denoising in low dose CT images for various loss functions

Byeongjoon Kim, Minah Han, Hyunjung Shim, Jongduk Baek

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Convolutional neural network (CNN) is now the most promising denoising methods for low-dose computed tomography (CT) images. The goal of denoising is to restore original details as well as to reduce noise, and the performance is largely determined by the loss function of the CNN. In this work, we investigate the denoising performance of CNN for three different loss functions in low dose CT images: mean squared error (MSE), perception loss using the pretrained VGG network (VGG loss), and the weighted summation of MSE and VGG losses (VGGMSE loss). CNNs are trained to map the quarter dose CT images to normal dose CT images in a supervised fashion. The image quality of denoised images is evaluated by normalized root mean squared error (NRMSE), structural similarity index (SSIM), mean and standard deviation (SD) of HU values, and the task SNR of non-prewhitening eye filter observer model (NPWE). Our results show that the CNN trained with MSE loss achieves the best performance in NRMSE and SSIM despite significant image blurs. On the other hand, the CNN trained with VGG loss reports the best score in the SD with well-preserved details but has the worst accuracy in the mean HU value. CNN trained with VGGMSE loss shows the best performance in terms of tSNR and the mean HU value and consistently high performance in other metrics. In conclusion, VGGMSE loss can subside the drawbacks of MSE or VGG loss, thus much more effective than them for CT denoising tasks.

Original languageEnglish
Title of host publicationMedical Imaging 2019
Subtitle of host publicationPhysics of Medical Imaging
EditorsTaly Gilat Schmidt, Guang-Hong Chen, Hilde Bosmans
PublisherSPIE
ISBN (Electronic)9781510625433
DOIs
Publication statusPublished - 2019 Jan 1
EventMedical Imaging 2019: Physics of Medical Imaging - San Diego, United States
Duration: 2019 Feb 172019 Feb 20

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume10948
ISSN (Print)1605-7422

Conference

ConferenceMedical Imaging 2019: Physics of Medical Imaging
CountryUnited States
CitySan Diego
Period19/2/1719/2/20

    Fingerprint

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Atomic and Molecular Physics, and Optics
  • Radiology Nuclear Medicine and imaging

Cite this

Kim, B., Han, M., Shim, H., & Baek, J. (2019). Performance comparison of convolutional neural network based denoising in low dose CT images for various loss functions. In T. G. Schmidt, G-H. Chen, & H. Bosmans (Eds.), Medical Imaging 2019: Physics of Medical Imaging [1094849] (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 10948). SPIE. https://doi.org/10.1117/12.2512183