Low-dose ct denoising via cnn with an observer loss function

Minah Han, Jongduk Baek

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

Abstract

Convolutional neural network (CNN) based low-dose CT denoising is effective to deal with complex CT noise. However, CNN denoiser with pixel-level loss functions (e.g., mean-squared-error (MSE) and mean-absolute- error (MAE)) often produces image blur. To overcome this limitation, perceptual loss function (e.g., VGG loss) is adapted to train CNN denoiser. CNN denoiser with VGG loss preserves structural details in denoised images better. However, because VGG network is trained with natural RGB images, which have different image properties from CT images, extracted features would not be related to diagnosis. Also, CNN denoiser with VGG loss introduces a bias of CT number in denoised images. In this work, we propose observer loss to train CNN denoiser. Observer network (i.e., feature extractor in observer loss) is trained with CT images to classify lesion-present and lesion-absent cases. We conduct two binary classification tasks, signal-known-exactly (SKE) and signal-known-statistically (SKS) tasks. Because it is hard to obtain labeled CT images, we insert simulated lesions. CNN denoiser with observer loss preserves small structures and edges in denoised images without introducing bias in CT number.

Original languageEnglish
Title of host publicationMedical Imaging 2021
Subtitle of host publicationPhysics of Medical Imaging
EditorsHilde Bosmans, Wei Zhao, Lifeng Yu
PublisherSPIE
ISBN (Electronic)9781510640191
DOIs
Publication statusPublished - 2021
EventMedical Imaging 2021: Physics of Medical Imaging - Virtual, Online, United States
Duration: 2021 Feb 152021 Feb 19

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume11595
ISSN (Print)1605-7422

Conference

ConferenceMedical Imaging 2021: Physics of Medical Imaging
Country/TerritoryUnited States
CityVirtual, Online
Period21/2/1521/2/19

Bibliographical note

Funding Information:
This work was supported by National Research Foundation of Korea (2019R1A6A3A01092732, 2019R1A2C2084936, 2020R1A4A1016619).

Publisher Copyright:
© COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

All Science Journal Classification (ASJC) codes

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

Fingerprint

Dive into the research topics of 'Low-dose ct denoising via cnn with an observer loss function'. Together they form a unique fingerprint.

Cite this