mlsanityData to 14 Oct 2026

Comparative clinical evaluation of "memory-efficient" synthetic 3d generative adversarial networks (gan) head-to-head to state of art: results on computed tomography of the chest

arXiv 2501.15572 ↗First posted 26 Jan 2025eess.IV cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Generative Adversarial Networks (GANs) are increasingly used to generate synthetic medical images, addressing the critical shortage of annotated data for training Artificial Intelligence systems. This study introduces CRF-GAN, a novel memory-efficient GAN architecture that enhances structural consistency in 3D medical image synthesis. Integrating Conditional Random Fields within a two-step generation process allows CRF-GAN improving spatial coherence while maintaining high-resolution image quality. The model's performance is evaluated against the state-of-the-art hierarchical (HA)-GAN model. Materials and Methods: We evaluate the performance of CRF-GAN against the HA-GAN model. The comparison between the two models was made through a quantitative evaluation, using FID and MMD metrics, and a qualitative evaluation, through a two-alternative forced choice (2AFC) test completed by a pool of 12 resident radiologists, to assess the realism of the generated images. Results: CRF-GAN outperformed HA-GAN with lower FID and MMD scores, indicating better image fidelity. The 2AFC test showed a significant preference for images generated by CRF-Gan over those generated by HA-GAN. Additionally, CRF-GAN demonstrated 9.34% lower memory usage and achieved up to 14.6% faster training speeds, offering substantial computational savings. Discussion: CRF-GAN model successfully generates high-resolution 3D medical images with non-inferior quality to conventional models, while being more memory-efficient and faster. The key objective was not only to lower the computational cost but also to reallocate the freed-up resources towards the creation of higher-resolution 3D imaging, which is still a critical factor limiting their direct clinical applicability. Moreover, unlike many previous studies, we combined qualitative and quantitative assessments to obtain a more holistic feedback on the model's performance.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 42 references that are in the map. First posted on arXiv 26 Jan 2025.

Builds on

20 of 42 references.

References · 20

  1. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  2. 2017Improved Training of Wasserstein GANscited by 2,235
  3. 2016Density estimation using Real NVPcited by 2,042
  4. 2015Autoencoding beyond pixels using a learned similarity metriccited by 407
  5. 2018GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classificationcited by 242
  6. 2016Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the LUNA16 challengecited by 201
  7. 2018An empirical study on evaluation metrics of generative adversarial networkscited by 81
  8. 2019Generation of 3D Brain MRI Using Auto-Encoding Generative Adversarial Networkscited by 65
  9. 2021GANs for Medical Image Synthesis: An Empirical Studycited by 65
  10. 2020Hierarchical Amortized Training for Memory-efficient High Resolution 3D GANcited by 60
  11. 20183D Convolutional Encoder-Decoder Network for Low-Dose CT via Transfer Learning from a 2D Trained Networkcited by 47
  12. 20213D-StyleGAN: A Style-Based Generative Adversarial Network for Generative Modeling of Three-Dimensional Medical Imagescited by 32
8 more
  1. 2018Deep CT to MR Synthesis using Paired and Unpaired Datacited by 31
  2. 2020Vox2Vox: 3D-GAN for Brain Tumour Segmentationcited by 30
  3. 2019Synthesizing Diverse Lung Nodules Wherever Massively: 3D Multi-Conditional GAN-based CT Image Augmentation for Object Detectioncited by 29
  4. 2018Cancer Metastasis Detection With Neural Conditional Random Fieldcited by 17
  5. 2019Virtual Thin Slice: 3D Conditional GAN-based Super-resolution for CT Slice Intervalcited by 11
  6. 2019Artificial Intelligence in Glioma Imaging: Challenges and Advancescited by 10
  7. 2019Multi-scale GANs for Memory-efficient Generation of High Resolution Medical Imagescited by 9
  8. 2021CT-SGAN: Computed Tomography Synthesis GANcited by 4

Built on by

Not cited yet.