mlsanityData to 7 Oct 2026

Impact of deep learning-based image super-resolution on binary signal detection

arXiv 2107.02338 ↗First posted 6 Jul 2021eess.IV cs.CV physics.med-phcited by 9

Not on the map. Why?

Abstract (arXiv)

Deep learning-based image super-resolution (DL-SR) has shown great promise in medical imaging applications. To date, most of the proposed methods for DL-SR have only been assessed by use of traditional measures of image quality (IQ) that are commonly employed in the field of computer vision. However, the impact of these methods on objective measures of image quality that are relevant to medical imaging tasks remains largely unexplored. In this study, we investigate the impact of DL-SR methods on binary signal detection performance. Two popular DL-SR methods, the super-resolution convolutional neural network (SRCNN) and the super-resolution generative adversarial network (SRGAN), were trained by use of simulated medical image data. Binary signal-known-exactly with background-known-statistically (SKE/BKS) and signal-known-statistically with background-known-statistically (SKS/BKS) detection tasks were formulated. Numerical observers, which included a neural network-approximated ideal observer and common linear numerical observers, were employed to assess the impact of DL-SR on task performance. The impact of the complexity of the DL-SR network architectures on task-performance was quantified. In addition, the utility of DL-SR for improving the task-performance of sub-optimal observers was investigated. Our numerical experiments confirmed that, as expected, DL-SR could improve traditional measures of IQ. However, for many of the study designs considered, the DL-SR methods provided little or no improvement in task performance and could even degrade it. It was observed that DL-SR could improve the task-performance of sub-optimal observers under certain conditions. The presented study highlights the urgent need for the objective assessment of DL-SR methods and suggests avenues for improving their efficacy in medical imaging applications.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 16 of its 56 references that are in the map. First posted on arXiv 6 Jul 2021.

Builds on

16 of 56 references.

References · 16

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  3. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  4. 2016Understanding deep learning requires rethinking generalizationcited by 1,657
  5. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  6. 2019Deep Learning for Image Super-resolution: A Surveycited by 368
  7. 2018Deep Learning for Single Image Super-Resolution: A Brief Reviewcited by 158
  8. 2017Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networkscited by 138
  9. 2018CT Super-resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble(GAN-CIRCLE)cited by 81
  10. 2020On hallucinations in tomographic image reconstructioncited by 66
  11. 2021Real-World Single Image Super-Resolution: A Brief Reviewcited by 65
  12. 2015Is Image Super-resolution Helpful for Other Vision Tasks?cited by 22
4 more
  1. 2021Assessing the Impact of Deep Neural Network-based Image Denoising on Binary Signal Detection Taskscited by 20
  2. 2019Approximating the Ideal Observer and Hotelling Observer for binary signal detection tasks by use of supervised learning methodscited by 14
  3. 2021Task-Oriented Low-Dose CT Image Denoisingcited by 11
  4. 2020Markov-Chain Monte Carlo Approximation of the Ideal Observer using Generative Adversarial Networkscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 1; 2024: 1; 2025: 2; 2026: 1.

9 papers.

  1. 2022Assessing the ability of generative adversarial networks to learn canonical medical image statisticscited by 11
  2. 2023Need for Objective Task-based Evaluation of Deep Learning-Based Denoising Methods: A Study in the Context of Myocardial Perfusion SPECTcited by 3
  3. 2022Prior image-based medical image reconstruction using a style-based generative adversarial networkcited by 2
  4. 2022Evaluating Procedures for Establishing Generative Adversarial Network-based Stochastic Image Models in Medical Imagingcited by 1
  5. 2022Task-Based Assessment for Neural Networks: Evaluating Undersampled MRI Reconstructions based on Human Observer Signal Detectioncited by 0
  6. 2024Survey of Deep Learning and Physics-Based Approaches in Computational Wave Imagingcited by 0
  7. 2025A detection-task-specific deep-learning method to improve the quality of sparse-view myocardial perfusion SPECT imagescited by 0
  8. 2025Hallucinations in medical devicescited by 0
  9. 2026Image Quality in the Era of Artificial Intelligencecited by 0