Assessing the Impact of Deep Neural Network-based Image Denoising on Binary Signal Detection Tasks

Kaiyan Li, Weimin Zhou, Hua Lia, Mark A. Anastasio

Research output: Contribution to journalArticlepeer-review


A variety of deep neural network (DNN)-based image denoising methods have been proposed for use with medical images. Traditional measures of image quality (IQ) have been employed to optimize and evaluate these methods. However, the objective evaluation of IQ for the DNN-based denoising methods remains largely lacking. In this work, we evaluate the performance of DNN-based denoising methods by use of task-based IQ measures. Specifically, binary signal detection tasks under signal-known-exactly (SKE) with background-known-statistically (BKS) conditions are considered. The performance of the ideal observer (IO) and common linear numerical observers are quantified and detection efficiencies are computed to assess the impact of the denoising operation on task performance. The numerical results indicate that, in the cases considered, the application of a denoising network can result in a loss of task-relevant information in the image. The impact of the depth of the denoising networks on task performance is also assessed. The presented results highlight the need for the objective evaluation of IQ for DNN-based denoising technologies and may suggest future avenues for improving their effectiveness in medical imaging applications.

Original languageEnglish (US)
JournalIEEE transactions on medical imaging
StateAccepted/In press - 2021


  • Biomedical imaging
  • deep learning
  • ideal observer
  • Image denoising
  • Image denoising
  • Noise reduction
  • numerical observers
  • Observers
  • PSNR
  • Signal detection
  • Task analysis
  • task-based image quality assessment

ASJC Scopus subject areas

  • Software
  • Radiological and Ultrasound Technology
  • Computer Science Applications
  • Electrical and Electronic Engineering


Dive into the research topics of 'Assessing the Impact of Deep Neural Network-based Image Denoising on Binary Signal Detection Tasks'. Together they form a unique fingerprint.

Cite this