• Home
  • Search
  • Sparse‐View Imaging for Lung Cancer Detection Based on Generative Adversarial Networks and Deep Learning Models
  • https://doi.org/10.1002/ima.70417Copy DOI Icon

Sparse‐View Imaging for Lung Cancer Detection Based on Generative Adversarial Networks and Deep Learning Models

Show More
  • Abstract
  • Literature Map
  • Similar Papers
Abstract

ABSTRACT Lung cancer, the largest cause of cancer deaths globally, requires effective diagnostic imaging to identify and define pulmonary abnormalities. Sparse view projections lower CT radiation but diminish image quality and make diagnosis challenging. This research introduces a comprehensive approach that systematically assesses seven sparse projection levels (10–512 views) for lung cancer detection, uniquely integrating generative adversarial networks (GANs)‐based reconstruction with diagnostic performance evaluation. In contrast to previous research, our study offers a systematic framework for generating and assessing sparse‐view datasets over the entire clinical range. Given the limited availability of sparse‐view projection datasets across clinical ranges, we systematically generated sparse‐view images at multiple levels: 10, 16, 32, 64, 128, 256, and 512 projections. Three GAN architectures, standard GAN, conditional GAN (CGAN), and Pix2Pix, were employed to reconstruct high‐quality images from degraded sparse‐view data, enhancing structural integrity and diagnostic utility. A Visual Geometry Group 16‐layer (VGG16) deep learning (DL) model evaluated the diagnostic efficacy of both generated and original sparse‐view images. Results demonstrate superior performance of the Pix2Pix model, achieving structural similarity index measure values of 79.385% and 81.265% for 10‐ and 16‐view projections, respectively. Classification performance using VGG16 yielded exceptional metrics: 98.82% accuracy, 99.18% precision, 99.18% recall, 99.18% F1‐score, and 99.86% area under the receiver operating characteristic curve for 10‐view projections. This GAN‐DL integration offers a clinically viable approach for sparse‐view imaging, ensuring diagnostic reliability while minimizing radiation exposure and enhancing computational efficiency, particularly critical for cancer patients requiring reduced radiation doses.

Similar Papers
  • Research Article
  • Citations3

GANCHEST: a multi-GAN-based framework for chest CXR image generation and validation

  • Jul 01, 2025
  • Journal of Electrical Systems and Information Technology
  • Amal A Al-Shargabi +4
  • Research Article

SIGAN: a generative adversarial network architecture for sketch to photo synthesis

  • Jun 01, 2025
  • International Journal of Electrical and Computer Engineering (IJECE)
  • Buddannagari Latha +1
  • Research Article
  • Citations20

A deep learning model for generating fundus autofluorescence images from color fundus photography

  • Nov 01, 2023
  • Advances in Ophthalmology Practice and Research
  • Fan Song +4
  • Research Article
  • Citations1

Individualized Estimation of Baseline Retinal Nerve Fiber Layer Thickness Using Conditional Variational Autoencoder.

  • Nov 01, 2025
  • Ophthalmology science
  • Ou Tan +14
  • PDF
  • Research Article

Virtual Data Generation for Marine Turbochargers Using GANs

  • Dec 01, 2022
  • e-Journal of Nondestructive Testing
  • Chunling Du +1
  • Research Article
  • Citations37

Assessment of Generative Adversarial Networks for Synthetic Anterior Segment Optical Coherence Tomography Images in Closed-Angle Detection

  • Apr 30, 2021
  • Translational Vision Science & Technology
  • Ce Zheng +10
  • Research Article
  • Citations1

Application of deep learning model incorporating domain knowledge in international migration forecasting

  • Apr 12, 2024
  • Data Technologies and Applications
  • Tongzheng Pu +4
  • Conference Article
  • Citations17

GAN-LSTM Predictor for Failure Prognostics of Rolling Element Bearings

  • Jun 07, 2021
  • Hao Lu +5
  • PDF
  • Research Article
  • Citations66

A generative adversarial network for synthetization of regions of interest based on digital mammograms

  • Apr 13, 2022
  • Scientific Reports
  • Olaide N Oyelade +5
  • Research Article
  • Citations162

Spatial interpolation using conditional generative adversarial neural networks

  • Apr 16, 2019
  • International Journal of Geographical Information Science
  • Di Zhu +5
  • Research Article
  • Citations21

Designing mm-wave electromagnetic engineered surfaces using generative adversarial networks

  • Jan 11, 2021
  • Neural Computing and Applications
  • Sanaz Mohammadjafari +5
  • Research Article
  • Citations3

A Comparison of U-Net with Conditional Generative Adversarial Networks and Cycle-Consistent Adversarial Networks for real seismic data interpolation: Tupi Field

  • Jun 28, 2024
  • Research, Society and Development
  • Jaime Andres Collazos Gonzalez +4
  • PDF
  • Research Article
  • Citations2

Research on the Generation of Creative Animation Driven by Deep Learning Model

  • Apr 21, 2022
  • Scientific Programming
  • Xiaokun Sang +1
  • PDF
  • Research Article
  • Citations99

BrainGAN: Brain MRI Image Generation and Classification Framework Using GAN Architectures and CNN Models.

  • Jun 06, 2022
  • Sensors (Basel, Switzerland)
  • Halima Hamid N Alrashedy +3
  • Research Article

The Comparison of GAN and CNN Models in the Innovation of Coloring Madura and Bali Batik

  • Aug 01, 2025
  • JAREE (Journal on Advanced Research in Electrical Engineering)
  • Yohan Permana +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.