• Home
  • Search
  • Deep learning-based super-resolution method for projection image compression in radiotherapy
  • Cite Icon1
  • https://doi.org/10.21037/qims-2024-2962Copy DOI Icon

Deep learning-based super-resolution method for projection image compression in radiotherapy

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

BackgroundCone-beam computed tomography (CBCT) is a three-dimensional (3D) imaging method designed for routine target verification of cancer patients during radiotherapy. The images are reconstructed from a sequence of projection images obtained by the on-board imager attached to a radiotherapy machine. CBCT images are usually stored in a health information system, but the projection images are mostly abandoned due to their massive volume. To store them economically, in this study, a deep learning (DL)-based super-resolution (SR) method for compressing the projection images was investigated.MethodsIn image compression, low-resolution (LR) images were down-sampled by a factor from the high-resolution (HR) projection images and then encoded to the video file. In image restoration, LR images were decoded from the video file and then up-sampled to HR projection images via the DL network. Three SR DL networks, convolutional neural network (CNN), residual network (ResNet), and generative adversarial network (GAN), were tested along with three video coding-decoding (CODEC) algorithms: Advanced Video Coding (AVC), High Efficiency Video Coding (HEVC), and AOMedia Video 1 (AV1). Based on the two databases of the natural and projection images, the performance of the SR networks and video codecs was evaluated with the compression ratio (CR), peak signal-to-noise ratio (PSNR), video quality metric (VQM), and structural similarity index measure (SSIM).ResultsThe codec AV1 achieved the highest CR among the three codecs. The CRs of AV1 were 13.91, 42.08, 144.32, and 289.80 for the down-sampling factor (DSF) 0 (non-SR) 2, 4, and 6, respectively. The SR network, ResNet, achieved the best restoration accuracy among the three SR networks. Its PSNRs were 69.08, 41.60, 37.08, and 32.44 dB for the four DSFs, respectively; its VQMs were 0.06%, 3.65%, 6.95%, and 13.03% for the four DSFs, respectively; and its SSIMs were 0.9984, 0.9878, 0.9798, and 0.9518 for the four DSFs, respectively. As the DSF increased, the CR increased proportionally with the modest degradation of the restored images.ConclusionsThe application of the SR model can further improve the CR based on the current result achieved by the video encoders. This compression method is not only effective for the two-dimensional (2D) projection images, but also applicable to the 3D images used in radiotherapy.

Similar Papers
  • Research Article

Synthesizing cone-beam projections in radiotherapy using deep learning network for patients with head and neck cancer.

  • Jul 01, 2026
  • Quantitative imaging in medicine and surgery
  • Yuhan Fan +8
  • Research Article
  • Citations14

Deep learning in computed tomography super resolution using multi-modality data training.

  • Nov 16, 2023
  • Medical Physics
  • Wai Yan Ryana Fok +5
  • Conference Article
  • Citations1

Thermographic image super-resolution based on neural networks

  • May 29, 2022
  • A Galvan-Hernandez +4
  • PDF
  • Research Article
  • Citations2

Enhancing Post-Disaster Damage Detection and Recovery Monitoring by Addressing Class Imbalance in Satellite Imagery Using Enhanced Super-Resolution GANs (ESRGAN)

  • Jul 29, 2025
  • The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
  • Umut Lagap +1
  • Book Chapter
  • Citations7

Robust Super-Resolution of Real Faces Using Smooth Features

  • Jan 01, 2020
  • Saurabh Goswami +2
  • Research Article

Performance Evaluation Of Convolutional Neural Network And Generative Adversarial Network For Super Resolution Of Satellite Image

  • Dec 30, 2024
  • African Journal of Biomedical Research
  • Dr Ajay Kumar Boyat
  • Research Article
  • Citations2

Fusing residual dense and attention in generative adversarial networks for super-resolution of medical images

  • Jun 03, 2025
  • Quantitative Imaging in Medicine and Surgery
  • Qiong Zhang +4
  • PDF
  • Research Article
  • Citations14

Enhancing Remote Sensing Image Super-Resolution Guided by Bicubic-Downsampled Low-Resolution Image

  • Jun 28, 2023
  • Remote Sensing
  • Minkyung Chung +2
  • PDF
  • Research Article
  • Citations1

Leukocyte super-resolution via geometry prior and structural consistency.

  • Oct 05, 2020
  • Journal of biomedical optics
  • Xia Hua +4
  • Research Article

Advanced image super-resolution using deep learning approaches

  • Feb 20, 2025
  • Radioelectronic and Computer Systems
  • Mohamed Badiy +3
  • Book Chapter
  • Citations1

Advanced Generative Adversarial Network for Image Superresolution

  • Jan 01, 2022
  • Mei Jia +2
  • Book Chapter

Super-Resolution by Latent Space Exploration: Training with Poorly-Aligned Clinical and Micro CT Image Dataset

  • Jan 01, 2021
  • Tong Zheng +5
  • Conference Article
  • Citations191

Unpaired Image Super-Resolution Using Pseudo-Supervision

  • Jun 01, 2020
  • Shunta Maeda
  • Research Article
  • Citations3

Reliable Perceptual Loss Computation for GAN-Based Super-Resolution With Edge Texture Metric

  • Jan 01, 2021
  • IEEE Access
  • J Kim +1
  • Research Article
  • Citations7

Clinical ultra-high resolution CT scans enabled by using a generative adversarial network.

  • Jan 11, 2023
  • Medical Physics
  • Yao Sun +11
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.